mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-23 18:45:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: fix HTML table parser and JATS backend bugs (#1948)

Browse Source 
Fix a bug in parsing HTML tables in HTML backend.
Fix a bug in test file that prevented JATS backend tests.
Ensure that the JATS backend creates headings with the right level.
Remove unnecessary data files for testing JATS backend.

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
This commit is contained in:
Cesar Berrospi Ramis 2025-07-16 10:49:24 +02:00 committed by GitHub
parent d6d2dbe2f9
commit e1e3053695
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
27 changed files with 29206 additions and 14362 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
docling/backend/html_backend.py
View File

@ -379,6 +379,25 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
else:
_log.debug(f"list-item has no text: {element}")
@staticmethod
def _get_cell_spans(cell: Tag) -> tuple[int, int]:
"""Extract colspan and rowspan values from a table cell tag.
This function retrieves the 'colspan' and 'rowspan' attributes from a given
table cell tag.
If the attribute does not exist or it is not numeric, it defaults to 1.
"""
raw_spans: tuple[str, str] = (
str(cell.get("colspan", "1")),
str(cell.get("rowspan", "1")),
)
int_spans: tuple[int, int] = (
int(raw_spans[0]) if raw_spans[0].isnumeric() else 1,
int(raw_spans[1]) if raw_spans[0].isnumeric() else 1,
)
return int_spans
@staticmethod
def parse_table_data(element: Tag) -> Optional[TableData]: # noqa: C901
nested_tables = element.find("table")
@ -398,10 +417,9 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
if not isinstance(row, Tag):
continue
cell_tag = cast(Tag, cell)
val = cell_tag.get("colspan", "1")
colspan = int(val) if (isinstance(val, str) and val.isnumeric()) else 1
col_count += colspan
if cell_tag.name == "td" or cell_tag.get("rowspan") is None:
col_span, row_span = HTMLDocumentBackend._get_cell_spans(cell_tag)
col_count += col_span
if cell_tag.name == "td" or row_span == 1:
is_row_header = False
num_cols = max(num_cols, col_count)
if not is_row_header:
@ -428,10 +446,11 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
row_header = True
for html_cell in cells:
if isinstance(html_cell, Tag):
_, row_span = HTMLDocumentBackend._get_cell_spans(html_cell)
if html_cell.name == "td":
col_header = False
row_header = False
elif html_cell.get("rowspan") is None:
elif row_span == 1:
row_header = False
if not row_header:
row_idx += 1
@ -456,18 +475,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
text = html_cell.text
# label = html_cell.name
col_val = html_cell.get("colspan", "1")
col_span = (
int(col_val)
if isinstance(col_val, str) and col_val.isnumeric()
else 1
)
row_val = html_cell.get("rowspan", "1")
row_span = (
int(row_val)
if isinstance(row_val, str) and row_val.isnumeric()
else 1
)
col_span, row_span = HTMLDocumentBackend._get_cell_spans(html_cell)
if row_header:
row_span -= 1
while (

16
docling/backend/xml/jats_backend.py
View File

@ -93,8 +93,8 @@ class JatsDocumentBackend(DeclarativeDocumentBackend):
# Initialize the root of the document hierarchy
self.root: Optional[NodeItem] = None
self.valid = False
self.hlevel: int = 0
self.valid: bool = False
try:
if isinstance(self.path_or_stream, BytesIO):
self.path_or_stream.seek(0)
@ -147,6 +147,7 @@ class JatsDocumentBackend(DeclarativeDocumentBackend):
binary_hash=self.document_hash,
)
doc = DoclingDocument(name=self.file.stem or "file", origin=origin)
self.hlevel = 0
# Get metadata XML components
xml_components: XMLComponents = self._parse_metadata()
@ -304,7 +305,9 @@ class JatsDocumentBackend(DeclarativeDocumentBackend):
title: str = abstract["label"] or DEFAULT_HEADER_ABSTRACT
if not text:
continue
parent = doc.add_heading(parent=self.root, text=title)
parent = doc.add_heading(
parent=self.root, text=title, level=self.hlevel + 1
)
doc.add_text(
parent=parent,
text=text,
@ -637,7 +640,10 @@ class JatsDocumentBackend(DeclarativeDocumentBackend):
elif child.tag == "ack":
text = DEFAULT_HEADER_ACKNOWLEDGMENTS
if text:
new_parent = doc.add_heading(text=text, parent=parent)
self.hlevel += 1
new_parent = doc.add_heading(
text=text, parent=parent, level=self.hlevel
)
elif child.tag == "list":
new_parent = doc.add_group(
label=GroupLabel.LIST, name="list", parent=parent
@ -694,6 +700,8 @@ class JatsDocumentBackend(DeclarativeDocumentBackend):
new_text = self._walk_linear(doc, new_parent, child)
if not (node.getparent().tag == "p" and node.tag in flush_tags):
node_text += new_text
if child.tag in ("sec", "ack") and text:
self.hlevel -= 1
# pick up the tail text
node_text += child.tail.replace("\n", " ") if child.tail else ""

70
tests/data/groundtruth/docling_v2/bmj_sample.xml.itxt vendored
View File

@ -1,70 +0,0 @@
item-0 at level 0: unspecified: group _root_
item-1 at level 1: title: Evolving general practice consul ... Britain: issues of length and context
item-2 at level 2: paragraph: George K Freeman, John P Horder, ... on P Hill, Nayan C Shah, Andrew Wilson
item-3 at level 2: paragraph: Centre for Primary Care and Soci ... ersity of Leicester, Leicester LE5 4PW
item-4 at level 2: text: In 1999 Shah1 and others said th ... per consultation in general practice?
item-5 at level 2: text: We report on the outcome of exte ... review identified 14 relevant papers.
item-6 at level 2: section_header: Summary points
item-7 at level 3: list: group list
item-8 at level 4: list_item: Longer consultations are associa ... ith a range of better patient outcomes
item-9 at level 4: list_item: Modern consultations in general ... th more serious and chronic conditions
item-10 at level 4: list_item: Increasing patient participation ... interaction, which demands extra time
item-11 at level 4: list_item: Difficulties with access and wit ... e and lead to further pressure on time
item-12 at level 4: list_item: Longer consultations should be a ... t to maximise interpersonal continuity
item-13 at level 4: list_item: Research on implementation is needed
item-14 at level 2: section_header: Longer consultations: benefits for patients
item-15 at level 3: text: The systematic review consistent ... ther some doctors insist on more time.
item-16 at level 3: text: A national survey in 1998 report ... s the effects of their own experience.
item-17 at level 2: section_header: Context of modern consultations
item-18 at level 3: text: Shorter consultations were more ... potential length of the consultation.
item-19 at level 2: section_header: Participatory consultation style
item-20 at level 3: text: The most effective consultations ... style usually lengthens consultations.
item-21 at level 2: section_header: Extended professional agenda
item-22 at level 3: text: The traditional consultation in ... agerial expectations of good practice.
item-23 at level 3: text: Adequate time is essential. It m ... inevitably leads to pressure on time.
item-24 at level 2: section_header: Access problems
item-25 at level 3: text: In a service free at the point o ... ort notice squeeze consultation times.
item-26 at level 3: text: While appointment systems can an ... for the inadequate access to doctors.
item-27 at level 3: text: In response to perception of del ... ntation is currently being negotiated.
item-28 at level 3: text: Virtually all patients think tha ... e that is free at the point of access.
item-29 at level 3: text: A further government initiative ... ealth advice and first line treatment.
item-30 at level 2: section_header: Loss of interpersonal continuity
item-31 at level 3: text: If a patient has to consult seve ... unning and professional frustration.18
item-32 at level 3: text: Mechanic described how loss of l ... patient and professional satisfaction.
item-33 at level 2: section_header: Health service reforms
item-34 at level 3: text: Finally, for the past 15 years t ... ents and staff) and what is delivered.
item-35 at level 2: section_header: The future
item-36 at level 3: text: We think that the way ahead must ... p further the care of chronic disease.
item-37 at level 3: text: The challenge posed to general p ... ermedicalisation need to be exploited.
item-38 at level 3: text: We must ensure better communicat ... between planned and ad hoc consulting.
item-39 at level 2: section_header: Next steps
item-40 at level 3: text: General practitioners do not beh ... ailable time in complex consultations.
item-41 at level 3: text: Devising appropriate incentives ... and interpersonal knowledge and trust.
item-42 at level 2: section_header: Acknowledgments
item-43 at level 3: text: We thank the other members of th ... Practitioners for administrative help.
item-44 at level 2: section_header: References
item-45 at level 3: list: group list
item-46 at level 4: list_item: Shah NC. Viewpoint: Consultation ... y men!”. Br J Gen Pract 49:497 (1999).
item-47 at level 4: list_item: Mechanic D. How should hamsters ... BMJ 323:266–268 (2001). PMID: 11485957
item-48 at level 4: list_item: Howie JGR, Porter AMD, Heaney DJ ... n Pract 41:48–54 (1991). PMID: 2031735
item-49 at level 4: list_item: Howie JGR, Heaney DJ, Maxwell M, ... BMJ 319:738–743 (1999). PMID: 10487999
item-50 at level 4: list_item: Kaplan SH, Greenfield S, Ware JE ... c disease. Med Care 27:110–125 (1989).
item-51 at level 4: list_item: Airey C, Erens B. National surve ... e, 1998. London: NHS Executive (1999).
item-52 at level 4: list_item: Hart JT. Expectations of health ... h Expect 1:3–13 (1998). PMID: 11281857
item-53 at level 4: list_item: Tuckett D, Boulton M, Olson C, W ... London: Tavistock Publications (1985).
item-54 at level 4: list_item: General Medical Council. Draft r ... ctors/index.htm (accessed 2 Jan 2002).
item-55 at level 4: list_item: Balint M. The doctor, his patien ... the illness. London: Tavistock (1957).
item-56 at level 4: list_item: Stott NCH, Davies RH. The except ... J R Coll Gen Pract 29:210–205 (1979).
item-57 at level 4: list_item: Hill AP, Hill AP. Challenges for ... nium. London: King's Fund75–86 (2000).
item-58 at level 4: list_item: National service framework for c ... . London: Department of Health (2000).
item-59 at level 4: list_item: Hart JT. A new kind of doctor: t ... ommunity. London: Merlin Press (1988).
item-60 at level 4: list_item: Morrison I, Smith R. Hamster hea ... J 321:1541–1542 (2000). PMID: 11124164
item-61 at level 4: list_item: Arber S, Sawyer L. Do appointmen ... BMJ 284:478–480 (1982). PMID: 6800503
item-62 at level 4: list_item: Hjortdahl P, Borchgrevink CF. Co ... MJ 303:1181–1184 (1991). PMID: 1747619
item-63 at level 4: list_item: Howie JGR, Hopton JL, Heaney DJ, ... Pract 42:181–185 (1992). PMID: 1389427
item-64 at level 4: list_item: Freeman G, Shepperd S, Robinson ... ), Summer 2000. London: NCCSDO (2001).
item-65 at level 4: list_item: Wilson A, McDonald P, Hayes L, C ... Pract 41:184–187 (1991). PMID: 1878267
item-66 at level 4: list_item: De Maeseneer J, Hjortdahl P, Sta ... J 320:1616–1617 (2000). PMID: 10856043
item-67 at level 4: list_item: Freeman G, Hjortdahl P. What fut ... MJ 314:1870–1873 (1997). PMID: 9224130
item-68 at level 4: list_item: Kibbe DC, Bentz E, McLaughlin CP ... Pract 36:304–308 (1993). PMID: 8454977
item-69 at level 4: list_item: Williams M, Neal RD. Time for a ... ct 48:1783–1786 (1998). PMID: 10198490

1080
tests/data/groundtruth/docling_v2/bmj_sample.xml.json vendored
View File

File diff suppressed because it is too large Load Diff

105
tests/data/groundtruth/docling_v2/bmj_sample.xml.md vendored
View File

@ -1,105 +0,0 @@
# Evolving general practice consultation in Britain: issues of length and context
George K Freeman, John P Horder, John G R Howie, A Pali Hungin, Alison P Hill, Nayan C Shah, Andrew Wilson
Centre for Primary Care and Social Medicine, Imperial College of Science, Technology and Medicine, London W6 8RP; Royal College of General Practitioners, London SW7 1PU; Department of General Practice, University of Edinburgh, Edinburgh EH8 9DX; Centre for Health Studies, University of Durham, Durham DH1 3HN; Kilburn Park Medical Centre, London NW6; Department of General Practice and Primary Health Care, University of Leicester, Leicester LE5 4PW
In 1999 Shah1 and others said that the Royal College of General Practitioners should advocate longer consultations in general practice as a matter of policy. The college set up a working group chaired by A P Hungin, and a systematic review of literature on consultation length in general practice was commissioned. The working group agreed that the available evidence would be hard to interpret without discussion of the changing context within which consultations now take place. For many years general practitioners and those who have surveyed patients' opinions in the United Kingdom have complained about short consultation time, despite a steady increase in actual mean length. Recently Mechanic pointed out that this is also true in the United States.2 Is there any justification for a further increase in mean time allocated per consultation in general practice?
We report on the outcome of extensive debate among a group of general practitioners with an interest in the process of care, with reference to the interim findings of the commissioned systematic review and our personal databases. The review identified 14 relevant papers.
## Summary points
- Longer consultations are associated with a range of better patient outcomes
- Modern consultations in general practice deal with patients with more serious and chronic conditions
- Increasing patient participation means more complex interaction, which demands extra time
- Difficulties with access and with loss of continuity add to perceived stress and poor performance and lead to further pressure on time
- Longer consultations should be a professional priority, combined with increased use of technology and more flexible practice management to maximise interpersonal continuity
- Research on implementation is needed
## Longer consultations: benefits for patients
The systematic review consistently showed that doctors with longer consultation times prescribe less and offer more advice on lifestyle and other health promoting activities. Longer consultations have been significantly associated with better recognition and handling of psychosocial problems3 and with better patient enablement.4 Also clinical care for some chronic illnesses is better in practices with longer booked intervals between one appointment and the next.5 It is not clear whether time is itself the main influence or whether some doctors insist on more time.
A national survey in 1998 reported that most (87%) patients were satisfied with the length of their most recent consultation.6 Satisfaction with any service will be high if expectations are met or exceeded. But expectations are modified by previous experience.7 The result is that primary care patients are likely to be satisfied with what they are used to unless the context modifies the effects of their own experience.
## Context of modern consultations
Shorter consultations were more appropriate when the population was younger, when even a brief absence from employment due to sickness required a doctor's note, and when many simple remedies were available only on prescription. Recently at least five important influences have increased the content and hence the potential length of the consultation.
## Participatory consultation style
The most effective consultations are those in which doctors most directly acknowledge and perhaps respond to patients' problems and concerns. In addition, for patients to be committed to taking advantage of medical advice they must agree with both the goals and methods proposed. A landmark publication in the United Kingdom was Meetings Between Experts, which argued that while doctors are the experts about medical problems in general patients are the experts on how they themselves experience these problems.8 New emphasis on teaching consulting skills in general practice advocated specific attention to the patient's agenda, beliefs, understanding, and agreement. Currently the General Medical Council, aware that communication difficulties underlie many complaints about doctors, has further emphasised the importance of involving patients in consultations in its revised guidance to medical schools.9 More patient involvement should give a better outcome, but this participatory style usually lengthens consultations.
## Extended professional agenda
The traditional consultation in general practice was brief.2 The patient presented symptoms and the doctor prescribed treatment. In 1957 Balint gave new insights into the meaning of symptoms.10 By 1979 an enhanced model of consultation was presented, in which the doctors dealt with ongoing as well as presenting problems and added health promotion and education about future appropriate use of services.11 Now, with an ageing population and more community care of chronic illness, there are more issues to be considered at each consultation. Ideas of what constitutes good general practice are more complex.12 Good practice now includes both extended care of chronic medical problems—for example, coronary heart disease13—and a public health role. At first this model was restricted to those who lead change (“early adopters”) and enthusiasts14 but now it is embedded in professional and managerial expectations of good practice.
Adequate time is essential. It may be difficult for an elderly patient with several active problems to undress, be examined, and get adequate professional consideration in under 15 minutes. Here the doctor is faced with the choice of curtailing the consultation or of reducing the time available for the next patient. Having to cope with these situations often contributes to professional dissatisfaction.15 This combination of more care, more options, and more genuine discussion of those options with informed patient choice inevitably leads to pressure on time.
## Access problems
In a service free at the point of access, rising demand will tend to increase rationing by delay. But attempts to improve access by offering more consultations at short notice squeeze consultation times.
While appointment systems can and should reduce queuing time for consultations, they have long tended to be used as a brake on total demand.16 This may seriously erode patients' confidence in being able to see their doctor or nurse when they need to. Patients are offered appointments further ahead but may keep these even if their symptoms have remitted “just in case.” Availability of consultations is thus blocked. Receptionists are then inappropriately blamed for the inadequate access to doctors.
In response to perception of delay, the government has set targets in the NHS plan of “guaranteed access to a primary care professional within 24 hours and to a primary care doctor within 48 hours.” Implementation is currently being negotiated.
Virtually all patients think that they would not consult unless it was absolutely necessary. They do not think they are wasting NHS time and do not like being made to feel so. But underlying general practitioners' willingness to make patients wait several days is their perception that few of the problems are urgent. Patients and general practitioners evidently do not agree about the urgency of so called minor problems. To some extent general practice in the United Kingdom may have scored an “own goal” by setting up perceived access barriers (appointment systems and out of hours cooperatives) in the attempt to increase professional standards and control demand in a service that is free at the point of access.
A further government initiative has been to bypass general practice with new services—notably, walk-in centres (primary care clinics in which no appointment is needed) and NHS Direct (a professional telephone helpline giving advice on simple remedies and access to services). Introduced widely and rapidly, these services each potentially provide significant features of primary care—namely, quick access to skilled health advice and first line treatment.
## Loss of interpersonal continuity
If a patient has to consult several different professionals, particularly over a short period of time, there is inevitable duplication of stories, risk of naive diagnoses, potential for conflicting advice, and perhaps loss of trust. Trust is essential if patients are to accept the “wait and see” management policy which is, or should be, an important part of the management of self limiting conditions, which are often on the boundary between illness and non-illness.17 Such duplication again increases pressure for more extra (unscheduled) consultations resulting in late running and professional frustration.18
Mechanic described how loss of longitudinal (and perhaps personal and relational19) continuity influences the perception and use of time through an inability to build on previous consultations.2 Knowing the doctor well, particularly in smaller practices, is associated with enhanced patient enablement in shorter time.4 Though Mechanic pointed out that three quarters of UK patients have been registered with their general practitioner five years or more, this may be misleading. Practices are growing, with larger teams and more registered patients. Being registered with a doctor in a larger practice is usually no guarantee that the patient will be able to see the same doctor or the doctor of his or her choice, who may be different. Thus the system does not encourage adequate personal continuity. This adds to pressure on time and reduces both patient and professional satisfaction.
## Health service reforms
Finally, for the past 15 years the NHS has experienced unprecedented change with a succession of major administrative reforms. Recent reforms have focused on an NHS led by primary care, including the aim of shifting care from the secondary specialist sector to primary care. One consequence is increased demand for primary care of patients with more serious and less stable problems. With the limited piloting of reforms we do not know whether such major redirection can be achieved without greatly altering the delicate balance between expectations (of both patients and staff) and what is delivered.
## The future
We think that the way ahead must embrace both longer mean consultation times and more flexibility. More time is needed for high quality consultations with patients with major and complex problems of all kinds. But patients also need access to simpler services and advice. This should be more appropriate (and cost less) when it is given by professionals who know the patient and his or her medical history and social circumstances. For doctors, the higher quality associated with longer consultations may lead to greater professional satisfaction and, if these longer consultations are combined with more realistic scheduling, to reduced levels of stress.20 They will also find it easier to develop further the care of chronic disease.
The challenge posed to general practice by walk-in centres and NHS Direct is considerable, and the diversion of funding from primary care is large. The risk of waste and duplication increases as more layers of complexity are added to a primary care service that started out as something familiar, simple, and local and which is still envied in other developed countries.21 Access needs to be simple, and the advantages of personal knowledge and trust in minimising duplication and overmedicalisation need to be exploited.
We must ensure better communication and access so that patients can more easily deal with minor issues and queries with someone they know and trust and avoid the formality and inconvenience of a full face to face consultation. Too often this has to be with a different professional, unfamiliar with the nuances of the case. There should be far more managerial emphasis on helping patients to interact with their chosen practitioner22; such a programme has been described.23 Modern information systems make it much easier to record which doctor(s) a patient prefers to see and to monitor how often this is achieved. The telephone is hardly modern but is underused. Email avoids the problems inherent in arranging simultaneous availability necessary for telephone consultations but at the cost of reducing the communication of emotions. There is a place for both.2 Access without prior appointment is a valued feature of primary care, and we need to know more about the right balance between planned and ad hoc consulting.
## Next steps
General practitioners do not behave in a uniform way. They can be categorised as slow, medium, and fast and react in different ways to changes in consulting speed.18 They are likely to have differing views about a widespread move to lengthen consultation time. We do not need further confirmation that longer consultations are desirable and necessary, but research could show us the best way to learn how to introduce them with minimal disruption to the way in which patients and practices like primary care to be provided.24 We also need to learn how to make the most of available time in complex consultations.
Devising appropriate incentives and helping practices move beyond just reacting to demand in the traditional way by working harder and faster is perhaps our greatest challenge in the United Kingdom. The new primary are trusts need to work together with the growing primary care research networks to carry out the necessary development work. In particular, research is needed on how a primary care team can best provide the right balance of quick access and interpersonal knowledge and trust.
## Acknowledgments
We thank the other members of the working group: Susan Childs, Paul Freeling, Iona Heath, Marshall Marinker, and Bonnie Sibbald. We also thank Fenny Green of the Royal College of General Practitioners for administrative help.
## References
- Shah NC. Viewpoint: Consultation time—time for a change? Still the “perfunctory work of perfunctory men!”. Br J Gen Pract 49:497 (1999).
- Mechanic D. How should hamsters run? Some observations about sufficient patient time in primary care. BMJ 323:266–268 (2001). PMID: 11485957
- Howie JGR, Porter AMD, Heaney DJ, Hopton JL. Long to short consultation ratio: a proxy measure of quality of care for general practice. Br J Gen Pract 41:48–54 (1991). PMID: 2031735
- Howie JGR, Heaney DJ, Maxwell M, Walker JJ, Freeman GK, Rai H. Quality at general practice consultations: cross-sectional survey. BMJ 319:738–743 (1999). PMID: 10487999
- Kaplan SH, Greenfield S, Ware JE. Assessing the effects of physician-patient interactions on the outcome of chronic disease. Med Care 27:110–125 (1989).
- Airey C, Erens B. National surveys of NHS patients: general practice, 1998. London: NHS Executive (1999).
- Hart JT. Expectations of health care: promoted, managed or shared?. Health Expect 1:3–13 (1998). PMID: 11281857
- Tuckett D, Boulton M, Olson C, Williams A. Meetings between experts: an approach to sharing ideas in medical consultations. London: Tavistock Publications (1985).
- General Medical Council. Draft recommendations on undergraduate medical education. July 2001. www.gmc-uk.org/med\_ed/tomorrowsdoctors/index.htm (accessed 2 Jan 2002).
- Balint M. The doctor, his patient and the illness. London: Tavistock (1957).
- Stott NCH, Davies RH. The exceptional potential in each primary care consultation. J R Coll Gen Pract 29:210–205 (1979).
- Hill AP, Hill AP. Challenges for primary care. What's gone wrong with health care? Challenges for the new millennium. London: King's Fund75–86 (2000).
- National service framework for coronary heart disease. London: Department of Health (2000).
- Hart JT. A new kind of doctor: the general practitioner's part in the health of the community. London: Merlin Press (1988).
- Morrison I, Smith R. Hamster health care. BMJ 321:1541–1542 (2000). PMID: 11124164
- Arber S, Sawyer L. Do appointment systems work?. BMJ 284:478–480 (1982). PMID: 6800503
- Hjortdahl P, Borchgrevink CF. Continuity of care: influence of general practitioners' knowledge about their patients on use of resources in consultations. BMJ 303:1181–1184 (1991). PMID: 1747619
- Howie JGR, Hopton JL, Heaney DJ, Porter AMD. Attitudes to medical care, the organization of work, and stress among general practitioners. Br J Gen Pract 42:181–185 (1992). PMID: 1389427
- Freeman G, Shepperd S, Robinson I, Ehrich K, Richards SC, Pitman P. Continuity of care: report of a scoping exercise for the national co-ordinating centre for NHS Service Delivery and Organisation R&amp;D (NCCSDO), Summer 2000. London: NCCSDO (2001).
- Wilson A, McDonald P, Hayes L, Cooney J. Longer booking intervals in general practice: effects on doctors' stress and arousal. Br J Gen Pract 41:184–187 (1991). PMID: 1878267
- De Maeseneer J, Hjortdahl P, Starfield B. Fix what's wrong, not what's right, with general practice in Britain. BMJ 320:1616–1617 (2000). PMID: 10856043
- Freeman G, Hjortdahl P. What future for continuity of care in general practice?. BMJ 314:1870–1873 (1997). PMID: 9224130
- Kibbe DC, Bentz E, McLaughlin CP. Continuous quality improvement for continuity of care. J Fam Pract 36:304–308 (1993). PMID: 8454977
- Williams M, Neal RD. Time for a change? The process of lengthening booking intervals in general practice. Br J Gen Pract 48:1783–1786 (1998). PMID: 10198490

0
tests/data/groundtruth/docling_v2/elife-56337.xml.itxt → tests/data/groundtruth/docling_v2/elife-56337.nxml.itxt vendored
View File

7265
tests/data/groundtruth/docling_v2/elife-56337.nxml.json vendored Normal file
View File

File diff suppressed because it is too large Load Diff

26
tests/data/groundtruth/docling_v2/elife-56337.xml.md → tests/data/groundtruth/docling_v2/elife-56337.nxml.md vendored
View File

@ -99,16 +99,16 @@ Key resources table
| Cell line (Mus musculus) | B6;129‐ Gt(ROSA)26Sortm1(cre/ERT)Nat/J | The Jackson Laboratory | 004847 | ES cells used to generate KO cell lines and mice |
| Cell line (Mus musculus) | R1 ES cells | Andras Nagy lab | R1 | 129 ES cells used to generate KO cell lines and mice |
| Cell line (Mus musculus) | F9 Embryonic carcinoma cells | ATCC | ATCC CRL-1720 | |
| Antibody | Mouse monoclonal ANTI-FLAG M2 antibody | Sigma-Aldrich | Cat# F1804, RRID:AB\_262044 | ChIP (1 µg/107 cells) |
| Antibody | Rabbit polyclonal anti-HA | Abcam | Cat# ab9110, RRID:AB\_307019 | ChIP (1 µg/107 cells) |
| Antibody | Mouse monoclonal anti-HA | Covance | Cat# MMS-101P-200, RRID:AB\_10064068 | |
| Antibody | Rabbit polyclonal anti-H3K9me3 | Active Motif | Cat# 39161, RRID:AB\_2532132 | ChIP (3 µl/107 cells) |
| Antibody | Rabbit polyclonal anti-GFP | Thermo Fisher Scientific | Cat# A-11122, RRID:AB\_221569 | ChIP (1 µg/107 cells) |
| Antibody | Rabbit polyclonal anti- H3K4me3 | Abcam | Cat# ab8580, RRID:AB\_306649 | ChIP (1 µg/107 cells) |
| Antibody | Rabbit polyclonal anti- H3K4me1 | Abcam | Cat# ab8895, RRID:AB\_306847 | ChIP (1 µg/107 cells) |
| Antibody | Rabbit polyclonal anti- H3K27ac | Abcam | Cat# ab4729, RRID:AB\_2118291 | ChIP (1 µg/107 cells) |
| Recombinant DNA reagent | pCW57.1 | Addgene | RRID:Addgene\_41393 | Inducible lentiviral expression vector |
| Recombinant DNA reagent | pX330-U6-Chimeric\_BB-CBh-hSpCas9 | Addgene | RRID:Addgene\_42230 | CRISPR/Cas9 expression construct |
| Antibody | Mouse monoclonal ANTI-FLAG M2 antibody | Sigma-Aldrich | Cat# F1804, RRID:AB_262044 | ChIP (1 µg/107 cells) |
| Antibody | Rabbit polyclonal anti-HA | Abcam | Cat# ab9110, RRID:AB_307019 | ChIP (1 µg/107 cells) |
| Antibody | Mouse monoclonal anti-HA | Covance | Cat# MMS-101P-200, RRID:AB_10064068 | |
| Antibody | Rabbit polyclonal anti-H3K9me3 | Active Motif | Cat# 39161, RRID:AB_2532132 | ChIP (3 µl/107 cells) |
| Antibody | Rabbit polyclonal anti-GFP | Thermo Fisher Scientific | Cat# A-11122, RRID:AB_221569 | ChIP (1 µg/107 cells) |
| Antibody | Rabbit polyclonal anti- H3K4me3 | Abcam | Cat# ab8580, RRID:AB_306649 | ChIP (1 µg/107 cells) |
| Antibody | Rabbit polyclonal anti- H3K4me1 | Abcam | Cat# ab8895, RRID:AB_306847 | ChIP (1 µg/107 cells) |
| Antibody | Rabbit polyclonal anti- H3K27ac | Abcam | Cat# ab4729, RRID:AB_2118291 | ChIP (1 µg/107 cells) |
| Recombinant DNA reagent | pCW57.1 | Addgene | RRID:Addgene_41393 | Inducible lentiviral expression vector |
| Recombinant DNA reagent | pX330-U6-Chimeric_BB-CBh-hSpCas9 | Addgene | RRID:Addgene_42230 | CRISPR/Cas9 expression construct |
| Sequence-based reagent | Chr2-cl KO gRNA.1 | This paper | Cas9 gRNA | GCCGTTGCTCAGTCCAAATG |
| Sequenced-based reagent | Chr2-cl KO gRNA.2 | This paper | Cas9 gRNA | GATACCAGAGGTGGCCGCAAG |
| Sequenced-based reagent | Chr4-cl KO gRNA.1 | This paper | Cas9 gRNA | GCAAAGGGGCTCCTCGATGGA |
@ -120,9 +120,9 @@ Key resources table
| Sequenced-based reagent | Chr13.2-cl KO gRNA.1 | This paper | Cas9 gRNA | GGGTTTCTGAGAAACGTGTA |
| Sequenced-based reagent | Chr13.2-cl KO gRNA.2 | This paper | Cas9 gRNA | GTGTAATGAGTTCTTATATC |
| Commercial assay or kit | SureSelectQXT Target Enrichment kit | Agilent | G9681-90000 | |
| Software, algorithm | Bowtie | http://bowtie-bio.sourceforge.net | RRID:SCR\_005476 | |
| Software, algorithm | MACS14 | https://bio.tools/macs | RRID:SCR\_013291 | |
| Software, algorithm | Tophat | https://ccb.jhu.edu | RRID:SCR\_013035 | |
| Software, algorithm | Bowtie | http://bowtie-bio.sourceforge.net | RRID:SCR_005476 | |
| Software, algorithm | MACS14 | https://bio.tools/macs | RRID:SCR_013291 | |
| Software, algorithm | Tophat | https://ccb.jhu.edu | RRID:SCR_013035 | |
### Cell lines and transgenic mice

8
tests/data/groundtruth/docling_v2/example_8.html.itxt vendored
View File

@ -1,8 +0,0 @@
item-0 at level 0: unspecified: group _root_
item-1 at level 1: section: group header-1
item-2 at level 2: section_header: Pivot table with with 1 row header
item-3 at level 3: table with [6x4]
item-4 at level 2: section_header: Pivot table with 2 row headers
item-5 at level 3: table with [6x5]
item-6 at level 2: section_header: Equivalent pivot table
item-7 at level 3: table with [6x5]

2008
tests/data/groundtruth/docling_v2/example_8.html.json vendored
View File

File diff suppressed because it is too large Load Diff

29
tests/data/groundtruth/docling_v2/example_8.html.md vendored
View File

@ -1,29 +0,0 @@
## Pivot table with with 1 row header
| Year | Month | Revenue | Cost |
|--------|----------|-----------|--------|
| 2025 | January | $134 | $162 |
| 2025 | February | $150 | $155 |
| 2025 | March | $160 | $143 |
| 2025 | April | $210 | $150 |
| 2025 | May | $280 | $120 |
## Pivot table with 2 row headers
| Year | Quarter | Month | Revenue | Cost |
|--------|-----------|----------|-----------|--------|
| 2025 | Q1 | January | $134 | $162 |
| 2025 | Q1 | February | $150 | $155 |
| 2025 | Q1 | March | $160 | $143 |
| 2025 | Q2 | April | $210 | $150 |
| 2025 | Q2 | May | $280 | $120 |
## Equivalent pivot table
| Year | Quarter | Month | Revenue | Cost |
|--------|-----------|----------|-----------|--------|
| 2025 | Q1 | January | $134 | $162 |
| 2025 | Q1 | February | $150 | $155 |
| 2025 | Q1 | March | $160 | $143 |
| 2025 | Q2 | April | $210 | $150 |
| 2025 | Q2 | May | $280 | $120 |

148
tests/data/groundtruth/docling_v2/pnas_sample.xml.itxt vendored
View File

@ -1,148 +0,0 @@
item-0 at level 0: unspecified: group _root_
item-1 at level 1: title: The coreceptor mutation CCR5Δ32 ... V epidemics and is selected for by HIV
item-2 at level 2: paragraph: Amy D. Sullivan, Janis Wigginton, Denise Kirschner
item-3 at level 2: paragraph: Department of Microbiology and I ... dical School, Ann Arbor, MI 48109-0620
item-4 at level 2: section_header: Abstract
item-5 at level 3: text: We explore the impact of a host ... creasing the frequency of this allele.
item-6 at level 2: text: Nineteen million people have die ... factors such as host genetics (4, 5).
item-7 at level 2: text: To exemplify the contribution of ... follow the CCR5Δ32 allelic frequency.
item-8 at level 2: text: We hypothesize that CCR5Δ32 limi ... g the frequency of this mutant allele.
item-9 at level 2: text: CCR5 is a host-cell chemokine re ... iral strain (such as X4 or R5X4) (30).
item-10 at level 2: section_header: The Model
item-11 at level 3: text: Because we are most concerned wi ... t both economic and social conditions.
item-12 at level 3: picture
item-12 at level 4: caption: Figure 1 A schematic representation of the basic compartmental HIV epidemic model. The criss-cross lines indicate the sexual mixing between different compartments. Each of these interactions has a positive probability of taking place; they also incorporate individual rates of transmission indicated as λ, but in full notation is λ î,,→i,j, where i,j,k is the phenotype of the infected partner and î, is the phenotype of the susceptible partner. Also shown are the different rates of disease progression, γ i,j,k , that vary according to genotype, gender, and stage. Thus, the interactions between different genotypes, genders, and stages are associated with a unique probability of HIV infection. M, male; F, female.
item-13 at level 3: table with [6x5]
item-13 at level 4: caption: Table 1 Children's genotype
item-14 at level 3: section_header: Parameter Estimates for the Model.
item-15 at level 4: text: Estimates for rates that govern ... d in Fig. 1 are summarized as follows:
item-16 at level 4: formula: \frac{dS_{i,j}(t)}{dt}={\chi}_{ ... ,\hat {k}{\rightarrow}i,j}S_{i,j}(t),
item-17 at level 4: formula: \hspace{1em}\hspace{1em}\hspace ... j,A}(t)-{\gamma}_{i,j,A}I_{i,j,A}(t),
item-18 at level 4: formula: \frac{dI_{i,j,B}(t)}{dt}={\gamm ... j,B}(t)-{\gamma}_{i,j,B}I_{i,j,B}(t),
item-19 at level 4: formula: \frac{dA(t)}{dt}={\gamma}_{i,j, ... \right) -{\mu}_{A}A(t)-{\delta}A(t),
item-20 at level 4: text: where, in addition to previously ... on of the infected partner, and j ≠ .
item-21 at level 4: table with [14x5]
item-21 at level 5: caption: Table 2 Transmission probabilities
item-22 at level 4: table with [8x3]
item-22 at level 5: caption: Table 3 Progression rates
item-23 at level 4: table with [20x3]
item-23 at level 5: caption: Table 4 Parameter values
item-24 at level 4: text: The effects of the CCR5 W/Δ32 an ... nting this probability of infection is
item-25 at level 4: formula: {\lambda}_{\hat {i},\hat {j},\h ... \hat {i},\hat {j},\hat {k}} \right] ,
item-26 at level 4: text: where j ≠  is either male or fe ... e those with AIDS in the simulations).
item-27 at level 4: text: The average rate of partner acqu ... owing the male rates to vary (36, 37).
item-28 at level 4: section_header: Transmission probabilities.
item-29 at level 5: text: The effect of a genetic factor i ... reported; ref. 42) (ref. 43, Table 2).
item-30 at level 5: text: Given the assumption of no treat ... ases during the end stage of disease).
item-31 at level 4: section_header: Disease progression.
item-32 at level 5: text: We assume three stages of HIV in ... ssion rates are summarized in Table 3.
item-33 at level 3: section_header: Demographic Setting.
item-34 at level 4: text: Demographic parameters are based ... [suppressing (t) notation]: χ1,j 1,j =
item-35 at level 4: formula: B_{r}\hspace{.167em}{ \,\substa ... }+I_{2,M,k})}{N_{M}} \right] + \right
item-36 at level 4: formula: p_{v} \left \left( \frac{(I_{1, ... ght] \right) \right] ,\hspace{.167em}
item-37 at level 4: text: where the probability of HIV ver ... heir values are summarized in Table 4.
item-38 at level 2: section_header: Prevalence of HIV
item-39 at level 3: section_header: Demographics and Model Validation.
item-40 at level 4: text: The model was validated by using ... 5% to capture early epidemic behavior.
item-41 at level 4: text: In deciding on our initial value ... n within given subpopulations (2, 49).
item-42 at level 4: text: In the absence of HIV infection, ... those predicted by our model (Fig. 2).
item-43 at level 4: picture
item-43 at level 5: caption: Figure 2 Model simulation of HIV infection in a population lacking the protective CCR5Δ32 allele compared with national data from Kenya (healthy adults) and Mozambique (blood donors, ref. 17). The simulated population incorporates parameter estimates from sub-Saharan African demographics. Note the two outlier points from the Mozambique data were likely caused by underreporting in the early stages of the epidemic.
item-44 at level 3: section_header: Effects of the Allele on Prevalence.
item-45 at level 4: text: After validating the model in th ... among adults for total HIV/AIDS cases.
item-46 at level 4: text: Although CCR5Δ32/Δ32 homozygosit ... frequency of the mutation as 0.105573.
item-47 at level 4: text: Fig. 3 shows the prevalence of H ... mic, reaching 18% before leveling off.
item-48 at level 4: picture
item-48 at level 5: caption: Figure 3 Prevalence of HIV/AIDS in the adult population as predicted by the model. The top curve (○) indicates prevalence in a population lacking the protective allele. We compare that to a population with 19% heterozygous and 1% homozygous for the allele (implying an allelic frequency of 0.105573. Confidence interval bands (light gray) are shown around the median simulation () providing a range of uncertainty in evaluating parameters for the effect of the mutation on the infectivity and the duration of asymptomatic HIV for heterozygotes.
item-49 at level 4: text: In contrast, when a proportion o ... gins to decline slowly after 70 years.
item-50 at level 4: text: In the above simulations we assu ... in the presence of the CCR5 mutation.
item-51 at level 4: text: Because some parameters (e.g., r ... s a major influence on disease spread.
item-52 at level 2: section_header: HIV Induces Selective Pressure on Genotype Frequency
item-53 at level 3: text: To observe changes in the freque ... for ≈1,600 years before leveling off.
item-54 at level 3: picture
item-54 at level 4: caption: Figure 4 Effects of HIV-1 on selection of the CCR5Δ32 allele. The Hardy-Weinberg equilibrium level is represented in the no-infection simulation (solid lines) for each population. Divergence from the original Hardy-Weinberg equilibrium is shown to occur in the simulations that include HIV infection (dashed lines). Fraction of the total subpopulations are presented: (A) wild types (W/W), (B) heterozygotes (W/Δ32), and (C) homozygotes (Δ32/Δ32). Note that we initiate this simulation with a much lower allelic frequency (0.00105) than used in the rest of the study to better exemplify the actual selective effect over a 1,000-year time scale. (D) The allelic selection effect over a 2,000-year time scale.
item-55 at level 2: section_header: Discussion
item-56 at level 3: text: This study illustrates how popul ... pulations where the allele is present.
item-57 at level 3: text: We also observed that HIV can pr ... is) have been present for much longer.
item-58 at level 3: text: Two mathematical models have con ... ce of the pathogen constant over time.
item-59 at level 3: text: Even within our focus on host pr ... f a protective allele such as CCR5Δ32.
item-60 at level 3: text: Although our models demonstrate ... f the population to epidemic HIV (16).
item-61 at level 3: text: In assessing the HIV/AIDS epidem ... for education and prevention programs.
item-62 at level 2: section_header: Acknowledgments
item-63 at level 3: text: We thank Mark Krosky, Katia Koel ... ers for extremely insightful comments.
item-64 at level 2: section_header: References
item-65 at level 3: list: group list
item-66 at level 4: list_item: Weiss HA, Hawkes S. Leprosy Rev 72:92–98 (2001). PMID: 11355525
item-67 at level 4: list_item: Taha TE, Dallabetta GA, Hoover D ... AIDS 12:197–203 (1998). PMID: 9468369
item-68 at level 4: list_item: AIDS Epidemic Update. Geneva: World Health Organization1–17 (1998).
item-69 at level 4: list_item: D'Souza MP, Harden VA. Nat Med 2:1293–1300 (1996). PMID: 8946819
item-70 at level 4: list_item: Martinson JJ, Chapman NH, Rees D ... Genet 16:100–103 (1997). PMID: 9140404
item-71 at level 4: list_item: Roos MTL, Lange JMA, deGoede REY ... Dis 165:427–432 (1992). PMID: 1347054
item-72 at level 4: list_item: Garred P, Eugen-Olsen J, Iversen ... Lancet 349:1884 (1997). PMID: 9217763
item-73 at level 4: list_item: Katzenstein TL, Eugen-Olsen J, H ... rovirol 16:10–14 (1997). PMID: 9377119
item-74 at level 4: list_item: deRoda H, Meyer K, Katzenstain W ... ce 273:1856–1862 (1996). PMID: 8791590
item-75 at level 4: list_item: Meyer L, Magierowska M, Hubert J ... AIDS 11:F73–F78 (1997). PMID: 9302436
item-76 at level 4: list_item: Smith MW, Dean M, Carrington M, ... ence 277:959–965 (1997). PMID: 9252328
item-77 at level 4: list_item: Samson M, Libert F, Doranz BJ, R ... don) 382:722–725 (1996). PMID: 8751444
item-78 at level 4: list_item: McNicholl JM, Smith DK, Qari SH, ... ct Dis 3:261–271 (1997). PMID: 9284370
item-79 at level 4: list_item: Michael NL, Chang G, Louie LG, M ... at Med 3:338–340 (1997). PMID: 9055864
item-80 at level 4: list_item: Mayaud P, Mosha F, Todd J, Balir ... IDS 11:1873–1880 (1997). PMID: 9412707
item-81 at level 4: list_item: Hoffman IF, Jere CS, Taylor TE, ... li P, Dyer JR. AIDS 13:487–494 (1998).
item-82 at level 4: list_item: HIV/AIDS Surveillance Database. ... International Programs Center (1999).
item-83 at level 4: list_item: Anderson RM, May RM, McLean AR. ... don) 332:228–234 (1988). PMID: 3279320
item-84 at level 4: list_item: Berger EA, Doms RW, Fenyo EM, Ko ... (London) 391:240 (1998). PMID: 9440686
item-85 at level 4: list_item: Alkhatib G, Broder CC, Berger EA ... rol 70:5487–5494 (1996). PMID: 8764060
item-86 at level 4: list_item: Choe H, Farzan M, Sun Y, Sulliva ... ell 85:1135–1148 (1996). PMID: 8674119
item-87 at level 4: list_item: Deng H, Liu R, Ellmeier W, Choe ... don) 381:661–666 (1996). PMID: 8649511
item-88 at level 4: list_item: Doranz BJ, Rucker J, Yi Y, Smyth ... ell 85:1149–1158 (1996). PMID: 8674120
item-89 at level 4: list_item: Dragic T, Litwin V, Allaway GP, ... don) 381:667–673 (1996). PMID: 8649512
item-90 at level 4: list_item: Zhu T, Mo H, Wang N, Nam DS, Cao ... ce 261:1179–1181 (1993). PMID: 8356453
item-91 at level 4: list_item: Bjorndal A, Deng H, Jansson M, F ... rol 71:7478–7487 (1997). PMID: 9311827
item-92 at level 4: list_item: Conner RI, Sheridan KE, Ceradini ... Med 185:621–628 (1997). PMID: 9034141
item-93 at level 4: list_item: Liu R, Paxton WA, Choe S, Ceradi ... Cell 86:367–377 (1996). PMID: 8756719
item-94 at level 4: list_item: Mussico M, Lazzarin A, Nicolosi ... w) 154:1971–1976 (1994). PMID: 8074601
item-95 at level 4: list_item: Michael NL, Nelson JA, KewalRama ... rol 72:6040–6047 (1998). PMID: 9621067
item-96 at level 4: list_item: Hethcote HW, Yorke JA. Gonorrhea ... and Control. Berlin: Springer (1984).
item-97 at level 4: list_item: Anderson RM, May RM. Nature (London) 333:514–522 (1988). PMID: 3374601
item-98 at level 4: list_item: Asiimwe-Okiror G, Opio AA, Musin ... IDS 11:1757–1763 (1997). PMID: 9386811
item-99 at level 4: list_item: Carael M, Cleland J, Deheneffe J ... AIDS 9:1171–1175 (1995). PMID: 8519454
item-100 at level 4: list_item: Blower SM, Boe C. J AIDS 6:1347–1352 (1993). PMID: 8254474
item-101 at level 4: list_item: Kirschner D. J Appl Math 56:143–166 (1996).
item-102 at level 4: list_item: Le Pont F, Blower S. J AIDS 4:987–999 (1991). PMID: 1890608
item-103 at level 4: list_item: Kim MY, Lagakos SW. Ann Epidemiol 1:117–128 (1990). PMID: 1669741
item-104 at level 4: list_item: Anderson RM, May RM. Infectious ... ol. Oxford: Oxford Univ. Press (1992).
item-105 at level 4: list_item: Ragni MV, Faruki H, Kingsley LA. ... ed Immune Defic Syndr 17:42–45 (1998).
item-106 at level 4: list_item: Kaplan JE, Khabbaz RF, Murphy EL ... virol 12:193–201 (1996). PMID: 8680892
item-107 at level 4: list_item: Padian NS, Shiboski SC, Glass SO ... nghoff E. Am J Edu 146:350–357 (1997).
item-108 at level 4: list_item: Leynaert B, Downs AM, de Vincenzi I. Am J Edu 148:88–96 (1998).
item-109 at level 4: list_item: Garnett GP, Anderson RM. J Acquired Immune Defic Syndr 9:500–513 (1995).
item-110 at level 4: list_item: Stigum H, Magnus P, Harris JR, S ... eteig LS. Am J Edu 145:636–643 (1997).
item-111 at level 4: list_item: Ho DD, Neumann AU, Perelson AS, ... don) 373:123–126 (1995). PMID: 7816094
item-112 at level 4: list_item: World Resources (1998–1999). Oxford: Oxford Univ. Press (1999).
item-113 at level 4: list_item: Kostrikis LG, Neumann AU, Thomso ... 73:10264–10271 (1999). PMID: 10559343
item-114 at level 4: list_item: Low-Beer D, Stoneburner RL, Muku ... at Med 3:553–557 (1997). PMID: 9142126
item-115 at level 4: list_item: Grosskurth H, Mosha F, Todd J, S ... . AIDS 9:927–934 (1995). PMID: 7576329
item-116 at level 4: list_item: Melo J, Beby-Defaux A, Faria C, ... AIDS 23:203–204 (2000). PMID: 10737436
item-117 at level 4: list_item: Iman RL, Helton JC, Campbell JE. J Quality Technol 13:174–183 (1981).
item-118 at level 4: list_item: Iman RL, Helton JC, Campbell JE. J Quality Technol 13:232–240 (1981).
item-119 at level 4: list_item: Blower SM, Dowlatabadi H. Int Stat Rev 62:229–243 (1994).
item-120 at level 4: list_item: Porco TC, Blower SM. Theor Popul Biol 54:117–132 (1998). PMID: 9733654
item-121 at level 4: list_item: Blower SM, Porco TC, Darby G. Nat Med 4:673–678 (1998). PMID: 9623975
item-122 at level 4: list_item: Libert F, Cochaux P, Beckman G, ... Genet 7:399–406 (1998). PMID: 9466996
item-123 at level 4: list_item: Lalani AS, Masters J, Zeng W, Ba ... e 286:1968–1971 (1999). PMID: 10583963
item-124 at level 4: list_item: Kermack WO, McKendrick AG. Proc R Soc London 261:700–721 (1927).
item-125 at level 4: list_item: Gupta S, Hill AVS. Proc R Soc London Ser B 260:271–277 (1995).
item-126 at level 4: list_item: Ruwende C, Khoo SC, Snow RW, Yat ... don) 376:246–249 (1995). PMID: 7617034
item-127 at level 4: list_item: McDermott DH, Zimmerman PA, Guig ... ncet 352:866–870 (1998). PMID: 9742978
item-128 at level 4: list_item: Kostrikis LG, Huang Y, Moore JP, ... at Med 4:350–353 (1998). PMID: 9500612
item-129 at level 4: list_item: Winkler C, Modi W, Smith MW, Nel ... ence 279:389–393 (1998). PMID: 9430590
item-130 at level 4: list_item: Martinson JJ, Hong L, Karanicola ... AIDS 14:483–489 (2000). PMID: 10780710
item-131 at level 4: list_item: Vernazza PL, Eron JJ, Fiscus SA, ... AIDS 13:155–166 (1999). PMID: 10202821
item-132 at level 1: caption: Figure 1 A schematic representat ... of HIV infection. M, male; F, female.
item-133 at level 1: caption: Table 1 Children's genotype
item-134 at level 1: caption: Table 2 Transmission probabilities
item-135 at level 1: caption: Table 3 Progression rates
item-136 at level 1: caption: Table 4 Parameter values
item-137 at level 1: caption: Figure 2 Model simulation of HIV ... g in the early stages of the epidemic.
item-138 at level 1: caption: Figure 3 Prevalence of HIV/AIDS ... of asymptomatic HIV for heterozygotes.
item-139 at level 1: caption: Figure 4 Effects of HIV-1 on sel ... n effect over a 2,000-year time scale.

6353
tests/data/groundtruth/docling_v2/pnas_sample.xml.json vendored
View File

File diff suppressed because it is too large Load Diff

258
tests/data/groundtruth/docling_v2/pnas_sample.xml.md vendored
View File

@ -1,258 +0,0 @@
# The coreceptor mutation CCR5Δ32 influences the dynamics of HIV epidemics and is selected for by HIV
Amy D. Sullivan, Janis Wigginton, Denise Kirschner
Department of Microbiology and Immunology, University of Michigan Medical School, Ann Arbor, MI 48109-0620
## Abstract
We explore the impact of a host genetic factor on heterosexual HIV epidemics by using a deterministic mathematical model. A protective allele unequally distributed across populations is exemplified in our models by the 32-bp deletion in the host-cell chemokine receptor CCR5, CCR5Δ32. Individuals homozygous for CCR5Δ32 are protected against HIV infection whereas those heterozygous for CCR5Δ32 have lower pre-AIDS viral loads and delayed progression to AIDS. CCR5Δ32 may limit HIV spread by decreasing the probability of both risk of infection and infectiousness. In this work, we characterize epidemic HIV within three dynamic subpopulations: CCR5/CCR5 (homozygous, wild type), CCR5/CCR5Δ32 (heterozygous), and CCR5Δ32/CCR5Δ32 (homozygous, mutant). Our results indicate that prevalence of HIV/AIDS is greater in populations lacking the CCR5Δ32 alleles (homozygous wild types only) as compared with populations that include people heterozygous or homozygous for CCR5Δ32. Also, we show that HIV can provide selective pressure for CCR5Δ32, increasing the frequency of this allele.
Nineteen million people have died of AIDS since the discovery of HIV in the 1980s. In 1999 alone, 5.4 million people were newly infected with HIV (ref. 1 and http://www.unaids.org/epidemicupdate/report/Epireport.html). (For brevity, HIV-1 is referred to as HIV in this paper.) Sub-Saharan Africa has been hardest hit, with more than 20% of the general population HIV-positive in some countries (2, 3). In comparison, heterosexual epidemics in developed, market-economy countries have not reached such severe levels. Factors contributing to the severity of the epidemic in economically developing countries abound, including economic, health, and social differences such as high levels of sexually transmitted diseases and a lack of prevention programs. However, the staggering rate at which the epidemic has spread in sub-Saharan Africa has not been adequately explained. The rate and severity of this epidemic also could indicate a greater underlying susceptibility to HIV attributable not only to sexually transmitted disease, economics, etc., but also to other more ubiquitous factors such as host genetics (4, 5).
To exemplify the contribution of such a host genetic factor to HIV prevalence trends, we consider a well-characterized 32-bp deletion in the host-cell chemokine receptor CCR5, CCR5Δ32. When HIV binds to host cells, it uses the CD4 receptor on the surface of host immune cells together with a coreceptor, mainly the CCR5 and CXCR4 chemokine receptors (6). Homozygous mutations for this 32-bp deletion offer almost complete protection from HIV infection, and heterozygous mutations are associated with lower pre-AIDS viral loads and delayed progression to AIDS (7–14). CCR5Δ32 generally is found in populations of European descent, with allelic frequencies ranging from 0 to 0.29 (13). African and Asian populations studied outside the United States or Europe appear to lack the CCR5Δ32 allele, with an allelic frequency of almost zero (5, 13). Thus, to understand the effects of a protective allele, we use a mathematical model to track prevalence of HIV in populations with or without CCR5Δ32 heterozygous and homozygous people and also to follow the CCR5Δ32 allelic frequency.
We hypothesize that CCR5Δ32 limits epidemic HIV by decreasing infection rates, and we evaluate the relative contributions to this by the probability of infection and duration of infectivity. To capture HIV infection as a chronic infectious disease together with vertical transmission occurring in untreated mothers, we model a dynamic population (i.e., populations that vary in growth rates because of fluctuations in birth or death rates) based on realistic demographic characteristics (18). This scenario also allows tracking of the allelic frequencies over time. This work considers how a specific host genetic factor affecting HIV infectivity and viremia at the individual level might influence the epidemic in a dynamic population and how HIV exerts selective pressure, altering the frequency of this mutant allele.
CCR5 is a host-cell chemokine receptor, which is also used as a coreceptor by R5 strains of HIV that are generally acquired during sexual transmission (6, 19–25). As infection progresses to AIDS the virus expands its repertoire of potential coreceptors to include other CC-family and CXC-family receptors in roughly 50% of patients (19, 26, 27). CCR5Δ32 was identified in HIV-resistant people (28). Benefits to individuals from the mutation in this allele are as follows. Persons homozygous for the CCR5Δ32 mutation are almost nonexistent in HIV-infected populations (11, 12) (see ref. 13 for review). Persons heterozygous for the mutant allele (CCR5 W/Δ32) tend to have lower pre-AIDS viral loads. Aside from the beneficial effects that lower viral loads may have for individuals, there is also an altruistic effect, as transmission rates are reduced for individuals with low viral loads (as compared with, for example, AZT and other studies; ref. 29). Finally, individuals heterozygous for the mutant allele (CCR5 W/Δ32) also have a slower progression to AIDS than those homozygous for the wild-type allele (CCR5 W/W) (7–10), remaining in the population 2 years longer, on average. Interestingly, the dearth of information on HIV disease progression in people homozygous for the CCR5Δ32 allele (CCR5 Δ32/Δ32) stems from the rarity of HIV infection in this group (4, 12, 28). However, in case reports of HIV-infected CCR5 Δ32/Δ32 homozygotes, a rapid decline in CD4+ T cells and a high viremia are observed, likely because of initial infection with a more aggressive viral strain (such as X4 or R5X4) (30).
## The Model
Because we are most concerned with understanding the severity of the epidemic in developing countries where the majority of infection is heterosexual, we consider a purely heterosexual model. To model the effects of the allele in the population, we examine the rate of HIV spread by using an enhanced susceptible-infected-AIDS model of epidemic HIV (for review see ref. 31). Our model compares two population scenarios: a CCR5 wild-type population and one with CCR5Δ32 heterozygotes and homozygotes in addition to the wild type. To model the scenario where there are only wild-type individuals present in the population (i.e., CCR5 W/W), we track the sexually active susceptibles at time t [Si,j (t)], where i = 1 refers to genotype (CCR5 W/W only in this case) and j is either the male or female subpopulation. We also track those who are HIV-positive at time t not yet having AIDS in Ii,j,k (t) where k refers to stage of HIV infection [primary (A) or asymptomatic (B)]. The total number of individuals with AIDS at time t are tracked in A(t). The source population are children, χ i,j (t), who mature into the sexually active population at time t (Fig. 1, Table 1). We compare the model of a population lacking the CCR5Δ32 allele to a demographically similar population with a high frequency of the allele. When genetic heterogeneity is included, male and female subpopulations are each further divided into three distinct genotypic groups, yielding six susceptible subpopulations, [Si,j (t), where i ranges from 1 to 3, where 1 = CCR5W/W; 2 = CCR5 W/Δ32; 3 = CCR5 Δ32/Δ32]. The infected classes, Ii,j,k (t), also increase in number to account for these new genotype compartments. In both settings we assume there is no treatment available and no knowledge of HIV status by people in the early acute and middle asymptomatic stages (both conditions exist in much of sub-Saharan Africa). In addition, we assume that sexual mixing in the population occurs randomly with respect to genotype and HIV disease status, all HIV-infected people eventually progress to AIDS, and no barrier contraceptives are used. These last assumptions reflect both economic and social conditions.
Figure 1 A schematic representation of the basic compartmental HIV epidemic model. The criss-cross lines indicate the sexual mixing between different compartments. Each of these interactions has a positive probability of taking place; they also incorporate individual rates of transmission indicated as λ, but in full notation is λ î,,→i,j, where i,j,k is the phenotype of the infected partner and î, is the phenotype of the susceptible partner. Also shown are the different rates of disease progression, γ i,j,k , that vary according to genotype, gender, and stage. Thus, the interactions between different genotypes, genders, and stages are associated with a unique probability of HIV infection. M, male; F, female.
<!-- image -->
Table 1 Children's genotype
| Parents | Mother | Mother | Mother | Mother |
|-----------|----------|--------------------|------------------------------|--------------------|
| | | | | |
| Father | | W/W | W/Δ32 | Δ32/Δ32 |
| | W/W | χ1,j 1,j | χ1,j 1,j, χ2,j 2,j | χ2,j 2,j |
| | W/Δ32 | χ1,j 1,j, χ2,j 2,j | χ1,j 1,j, χ2,j 2,j, χ3,j 3,j | χ2,j 2,j, χ3,j 3,j |
| | Δ32/Δ32 | χ2,j 2,j | χ2,j 2,j, χ3,j 3,j | χ3,j 3,j |
### Parameter Estimates for the Model.
Estimates for rates that govern the interactions depicted in Fig. 1 were derived from the extensive literature on HIV. Our parameters and their estimates are summarized in Tables 2–4. The general form of the equations describing the rates of transition between population classes as depicted in Fig. 1 are summarized as follows:
$$ \frac{dS_{i,j}(t)}{dt}={\chi}_{i,j}(t)-{\mu}_{j}S_{i,j}(t)-{\lambda}_{\hat {\imath},\hat {},\hat {k}{\rightarrow}i,j}S_{i,j}(t), $$
$$ \hspace{1em}\hspace{1em}\hspace{.167em}\frac{dI_{i,j,A}(t)}{dt}={\lambda}_{\hat {\imath},\hat {},\hat {k}{\rightarrow}i,j}S_{i,j}(t)-{\mu}_{j}I_{i,j,A}(t)-{\gamma}_{i,j,A}I_{i,j,A}(t), $$
$$ \frac{dI_{i,j,B}(t)}{dt}={\gamma}_{i,j,A}I_{i,j,A}(t)-{\mu}_{j}I_{i,j,B}(t)-{\gamma}_{i,j,B}I_{i,j,B}(t), $$
$$ \frac{dA(t)}{dt}={\gamma}_{i,j,B} \left( { \,\substack{ ^{3} \\ {\sum} \\ _{i=1} }\, }I_{i,F,B}(t)+I_{i,M,B}(t) \right) -{\mu}_{A}A(t)-{\delta}A(t), $$
where, in addition to previously defined populations and rates (with i equals genotype, j equals gender, and k equals stage of infection, either A or B), μ j , represents the non-AIDS (natural) death rate for males and females respectively, and μA is estimated by the average (μF + μM/2). This approximation allows us to simplify the model (only one AIDS compartment) without compromising the results, as most people with AIDS die of AIDS (δAIDS) and very few of other causes (μA). These estimates include values that affect infectivity (λ î,,→i,j ), transmission (β î,,→i,j ), and disease progression (γ i , j , k ) where the î,, notation represents the genotype, gender, and stage of infection of the infected partner, and j ≠ .
Table 2 Transmission probabilities
| HIV-infected partner (îıı^^, ^^, k k^^) | Susceptible partner (i, j) | Susceptible partner (i, j) | Susceptible partner (i, j) | Susceptible partner (i, j) |
|-----------------------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|
| HIV-infected partner (îıı^^, ^^, k k^^) | | | | |
| HIV-infected partner (îıı^^, ^^, k k^^) | (^^ to j) | W/W | W/Δ32 | Δ32/Δ32 |
| | | | | |
| Acute/primary | | | | |
| W/W or Δ32/Δ32 | M to F | 0.040 | 0.040 | 0.00040 |
| | F to M | 0.020 | 0.020 | 0.00020 |
| W/Δ32 | M to F | 0.030 | 0.030 | 0.00030 |
| | F to M | 0.015 | 0.015 | 0.00015 |
| Asymptomatic | | | | |
| W/W or Δ32/Δ32 | M to F | 0.0010 | 0.0010 | 10 × 10−6 |
| | F to M | 0.0005 | 0.0005 | 5 × 10−6 |
| W/Δ32 | M to F | 0.0005 | 0.0005 | 5 × 10−6 |
| | F to M | 0.00025 | 0.00025 | 2.5 × 10−6 |
Table 3 Progression rates
| Genotype | Disease stage | Males/females |
|------------|-----------------|------------------|
| | | |
| W/W | A | 3.5 |
| | B | 0.16667 |
| W/Δ32 | A | 3.5 |
| | B | 0.125 |
| Δ32/Δ32 | A | 3.5 |
| | B | 0.16667 |
Table 4 Parameter values
| Parameter | Definition | Value |
|-----------------------------------------|----------------------------------------------------------|-------------------------|
| | | |
| μ F F, μ M M | All-cause mortality for adult females (males) | 0.015 (0.016) per year |
| μχχ | All-cause childhood mortality (&lt;15 years of age) | 0.01 per year |
| B r r | Birthrate | 0.25 per woman per year |
| SA F F | Percent females acquiring new partners (sexual activity) | 10% |
| SA M M | Percent males acquiring new partners (sexual activity) | 25% |
| m F F(ς$$ {\mathrm{_{{F}}^{{2}}}} $$) | Mean (variance) no. of new partners for females | 1.8 (1.2) per year |
| ς$$ {\mathrm{_{{M}}^{{2}}}} $$ | Variance in no. of new partners for males | 5.5 per year |
| 1 − p v v | Probability of vertical transmission | 0.30 per birth |
| I i,j,k i,j,k(0) | Initial total population HIV-positive | 0.50% |
| χ i,j i,j(0) | Initial total children in population (&lt;15 years of age) | 45% |
| W/W (0) | Initial total wild types (W/W) in population | 80% |
| W/Δ32(0) | Initial total heterozygotes (W/Δ32) in population | 19% |
| Δ32/Δ32(0) | Initial total homozygotes (Δ32/Δ32) in population | 1% |
| r M M(r F F) | Initial percent males (females) in total population | 49% (51%) |
| ϕ F F, ϕ M M | Number of sexual contacts a female (male) has | 30 (24) per partner |
| ɛ i,j,k i,j,k | % effect of mutation on transmission rates (see Table 2) | 0 &lt; ɛ i,j,k i,j,k &lt; 1 |
| δ | Death rate for AIDS population | 1.0 per year |
| q | Allelic frequency of Δ32 allele | 0.105573 |
The effects of the CCR5 W/Δ32 and CCR5 Δ32/Δ32 genotypes are included in our model through both the per-capita probabilities of infection, λ î,,→i,j , and the progression rates, γ i , j , k . The infectivity coefficients, λ î,,→i,j , are calculated for each population subgroup based on the following: likelihood of HIV transmission in a sexual encounter between a susceptible and an infected (βîıı^^,j,k k^^→i,j ) person; formation of new partnerships (c j j); number of contacts in a given partnership (ϕ j ); and probability of encountering an infected individual (I î,, /N  ). The formula representing this probability of infection is
$$ {\lambda}_{\hat {i},\hat {j},\hat {k}{\rightarrow}i,j}=\frac{C_{j}{\cdot}{\phi}_{j}}{N_{\hat {j}}}\hspace{.167em} \left[ { \,\substack{ \\ {\sum} \\ _{\hat {i},\hat {k}} }\, }{\beta}_{\hat {i},\hat {j},\hat {k}{\rightarrow}i,j}{\cdot}I_{\hat {i},\hat {j},\hat {k}} \right] , $$
where j ≠  is either male or female. N  represents the total population of gender  (this does not include those with AIDS in the simulations).
The average rate of partner acquisition, cj , includes the mean plus the variance to mean ratio of the relevant distribution of partner-change rates to capture the small number of high-risk people: cj = mj + (ς/m j) where the mean (mj ) and variance (ς) are annual figures for new partnerships only (32). These means are estimated from Ugandan data for the number of heterosexual partners in the past year (33) and the number of nonregular heterosexual partners (i.e., spouses or long-term partners) in the past year (34). In these sexual activity surveys, men invariably have more new partnerships; thus, we assumed that they would have fewer average contacts per partnership than women (a higher rate of new partner acquisition means fewer sexual contacts with a given partner; ref. 35). To incorporate this assumption in our model, the male contacts/partnership, ϕ M , was reduced by 20%. In a given population, the numbers of heterosexual interactions must equate between males and females. The balancing equation applied here is SA F·m F·N F = SA M·m M·N M, where SAj are the percent sexually active and Nj are the total in the populations for gender j. To specify changes in partner acquisition, we apply a male flexibility mechanism, holding the female rate of acquisition constant and allowing the male rates to vary (36, 37).
#### Transmission probabilities.
The effect of a genetic factor in a model of HIV transmission can be included by reducing the transmission coefficient. The probabilities of transmission per contact with an infected partner, βîıı^^,^^,k k^^→i,j , have been estimated in the literature (see ref. 38 for estimates in minimally treated groups). We want to capture a decreased risk in transmission based on genotype (ref. 39, Table 2). No studies have directly evaluated differences in infectivity between HIV-infected CCR5 W/Δ32 heterozygotes and HIV-infected CCR5 wild types. Thus, we base estimates for reduced transmission on studies of groups with various HIV serum viral loads (40), HTLV-I/II viral loads (41), and a study of the effect of AZT treatment on transmission (29). We decrease transmission probabilities for infecting CCR5Δ32/Δ32 persons by 100-fold to reflect the rarity of infections in these persons. However, we assume that infected CCR5Δ32/Δ32 homozygotes can infect susceptibles at a rate similar to CCR5W/W homozygotes, as the former generally have high viremias (ref. 30, Table 2). We also assume that male-to-female transmission is twice as efficient as female-to-male transmission (up to a 9-fold difference has been reported; ref. 42) (ref. 43, Table 2).
Given the assumption of no treatment, the high burden of disease in people with AIDS is assumed to greatly limit their sexual activity. Our initial model excludes people with AIDS from the sexually active groups. Subsequently, we allow persons with AIDS to be sexually active, fixing their transmission rates (βAIDS) to be the same across all CCR5 genotypes, and lower than transmission rates for primary-stage infection (as the viral burden on average is not as high as during the acute phase), and larger than transmission rates for asymptomatic-stage infection (as the viral burden characteristically increases during the end stage of disease).
#### Disease progression.
We assume three stages of HIV infection: primary (acute, stage A), asymptomatic HIV (stage B), and AIDS. The rates of transition through the first two stages are denoted by γ i,j,k i,j,k, where i represents genotype, j is male/female, and k represents either stage A or stage B. Transition rates through each of these stages are assumed to be inversely proportional to the duration of that stage; however, other distributions are possible (31, 44, 45). Although viral loads generally peak in the first 2 months of infection, steady-state viral loads are established several months beyond this (46). For group A, the primary HIV-infecteds, duration is assumed to be 3.5 months. Based on results from European cohort studies (7–10), the beneficial effects of the CCR5 W/Δ32 genotype are observed mainly in the asymptomatic years of HIV infection; ≈7 years after seroconversion survival rates appear to be quite similar between heterozygous and homozygous individuals. We also assume that CCR5Δ32/Δ32-infected individuals and wild-type individuals progress similarly, and that men and women progress through each disease stage at the same rate. Given these observations, and that survival after infection may be shorter in untreated populations, we choose the duration time in stage B to be 6 years for wild-type individuals and 8 years for heterozygous individuals. Transition through AIDS, δAIDS, is inversely proportional to the duration of AIDS. We estimate this value to be 1 year for the time from onset of AIDS to death. The progression rates are summarized in Table 3.
### Demographic Setting.
Demographic parameters are based on data from Malawi, Zimbabwe, and Botswana (3, 47). Estimated birth and child mortality rates are used to calculate the annual numbers of children (χ i,j i,j) maturing into the potentially sexually active, susceptible group at the age of 15 years (3). For example, in the case where the mother is CCR5 wild type and the father is CCR5 wild type or heterozygous, the number of CCR5 W/W children is calculated as follows [suppressing (t) notation]: χ1,j 1,j =
$$ B_{r}\hspace{.167em}{ \,\substack{ \\ {\sum} \\ _{k} }\, } \left[ S_{1,F}\frac{(S_{1,M}+I_{1,M,k})}{N_{M}}+ \left[ (0.5)S_{1,F}\frac{(S_{2,M}+I_{2,M,k})}{N_{M}} \right] + \right $$
$$ p_{v} \left \left( \frac{(I_{1,F,k}(S_{1,M}+I_{1,M,k}))}{N_{M}}+ \left[ (0.5)I_{1,F,k}\frac{(S_{2,M}+I_{2,M,k})}{N_{M}} \right] \right) \right] ,\hspace{.167em} $$
where the probability of HIV vertical transmission, 1 − pv , and the birthrate, Br , are both included in the equations together with the Mendelian inheritance values as presented in Table 1. The generalized version of this equation (i.e., χ i,j i,j) can account for six categories of children (including gender and genotype). We assume that all children of all genotypes are at risk, although we can relax this condition if data become available to support vertical protection (e.g., ref. 48). All infected children are assumed to die before age 15. Before entering the susceptible group at age 15, there is additional loss because of mortality from all non-AIDS causes occurring less than 15 years of age at a rate of μχχ × χ i,j i,j (where μχ is the mortality under 15 years of age). Children then enter the population as susceptibles at an annual rate, ς j j × χ i,j i,j/15, where ς j distributes the children 51% females and 49% males. All parameters and their values are summarized in Table 4.
## Prevalence of HIV
### Demographics and Model Validation.
The model was validated by using parameters estimated from available demographic data. Simulations were run in the absence of HIV infection to compare the model with known population growth rates. Infection was subsequently introduced with an initial low HIV prevalence of 0.5% to capture early epidemic behavior.
In deciding on our initial values for parameters during infection, we use Joint United Nations Programme on HIV/AIDS national prevalence data for Malawi, Zimbabwe, and Botswana. Nationwide seroprevalence of HIV in these countries varies from ≈11% to over 20% (3), although there may be considerable variation within given subpopulations (2, 49).
In the absence of HIV infection, the annual percent population growth rate in the model is ≈2.5%, predicting the present-day values for an average of sub-Saharan African cities (data not shown). To validate the model with HIV infection, we compare our simulation of the HIV epidemic to existing prevalence data for Kenya and Mozambique (http://www.who.int/emc-hiv/fact-sheets/pdfs/kenya.pdf and ref. 51). Prevalence data collected from these countries follow similar trajectories to those predicted by our model (Fig. 2).
Figure 2 Model simulation of HIV infection in a population lacking the protective CCR5Δ32 allele compared with national data from Kenya (healthy adults) and Mozambique (blood donors, ref. 17). The simulated population incorporates parameter estimates from sub-Saharan African demographics. Note the two outlier points from the Mozambique data were likely caused by underreporting in the early stages of the epidemic.
<!-- image -->
### Effects of the Allele on Prevalence.
After validating the model in the wild type-only population, both CCR5Δ32 heterozygous and homozygous people are included. Parameter values for HIV transmission, duration of illness, and numbers of contacts per partner are assumed to be the same within both settings. We then calculate HIV/AIDS prevalence among adults for total HIV/AIDS cases.
Although CCR5Δ32/Δ32 homozygosity is rarely seen in HIV-positive populations (prevalence ranges between 0 and 0.004%), 1–20% of people in HIV-negative populations of European descent are homozygous. Thus, to evaluate the potential impact of CCR5Δ32, we estimate there are 19% CCR5 W/Δ32 heterozygous and 1% CCR5 Δ32/Δ32 homozygous people in our population. These values are in Hardy-Weinberg equilibrium with an allelic frequency of the mutation as 0.105573.
Fig. 3 shows the prevalence of HIV in two populations: one lacking the mutant CCR5 allele and another carrying that allele. In the population lacking the protective mutation, prevalence increases logarithmically for the first 35 years of the epidemic, reaching 18% before leveling off.
Figure 3 Prevalence of HIV/AIDS in the adult population as predicted by the model. The top curve (○) indicates prevalence in a population lacking the protective allele. We compare that to a population with 19% heterozygous and 1% homozygous for the allele (implying an allelic frequency of 0.105573. Confidence interval bands (light gray) are shown around the median simulation () providing a range of uncertainty in evaluating parameters for the effect of the mutation on the infectivity and the duration of asymptomatic HIV for heterozygotes.
<!-- image -->
In contrast, when a proportion of the population carries the CCR5Δ32 allele, the epidemic increases more slowly, but still logarithmically, for the first 50 years, and HIV/AIDS prevalence reaches ≈12% (Fig. 3). Prevalence begins to decline slowly after 70 years.
In the above simulations we assume that people with AIDS are not sexually active. However, when these individuals are included in the sexually active population the severity of the epidemic increases considerably (data not shown). Consistent with our initial simulations, prevalences are still relatively lower in the presence of the CCR5 mutation.
Because some parameters (e.g., rate constants) are difficult to estimate based on available data, we implement an uncertainty analysis to assess the variability in the model outcomes caused by any inaccuracies in estimates of the parameter values with regard to the effect of the allelic mutation. For these analyses we use Latin hypercube sampling, as described in refs. 52–56, Our uncertainty and sensitivity analyses focus on infectivity vs. duration of infectiousness. To this end, we assess the effects on the dynamics of the epidemic for a range of values of the parameters governing transmission and progression rates: βîıı^^,^^,k k^^→i,j and γ i,j,k i,j,k. All other parameters are held constant. These results are presented as an interval band about the average simulation for the population carrying the CCR5Δ32 allele (Fig. 3). Although there is variability in the model outcomes, the analysis indicates that the overall model predictions are consistent for a wide range of transmission and progression rates. Further, most of the variation observed in the outcome is because of the transmission rates for both heterosexual males and females in the primary stage of infection (β2,M,A → i ,F, β2,F,A → i ,M). As mentioned above, we assume lower viral loads correlate with reduced infectivity; thus, the reduction in viral load in heterozygotes has a major influence on disease spread.
## HIV Induces Selective Pressure on Genotype Frequency
To observe changes in the frequency of the CCR5Δ32 allele in a setting with HIV infection as compared with the Hardy-Weinberg equilibrium in the absence of HIV, we follow changes in the total number of CCR5Δ32 heterozygotes and homozygotes over 1,000 years (Fig. 4). We initially perform simulations in the absence of HIV infection as a negative control to show there is not significant selection of the allele in the absence of infection. To determine how long it would take for the allelic frequency to reach present-day levels (e.g., q = 0.105573), we initiate this simulation for 1,000 years with a very small allelic frequency (q = 0.00105). In the absence of HIV, the allelic frequency is maintained in equilibrium as shown by the constant proportions of CCR5Δ32 heterozygotes and homozygotes (Fig. 4, solid lines). The selection for CCR5Δ32 in the presence of HIV is seen in comparison (Fig. 4, dashed lines). We expand the time frame of this simulation to 2,000 years to view the point at which the frequency reaches present levels (where q ∼0.105573 at year = 1200). Note that the allelic frequency increases for ≈1,600 years before leveling off.
Figure 4 Effects of HIV-1 on selection of the CCR5Δ32 allele. The Hardy-Weinberg equilibrium level is represented in the no-infection simulation (solid lines) for each population. Divergence from the original Hardy-Weinberg equilibrium is shown to occur in the simulations that include HIV infection (dashed lines). Fraction of the total subpopulations are presented: (A) wild types (W/W), (B) heterozygotes (W/Δ32), and (C) homozygotes (Δ32/Δ32). Note that we initiate this simulation with a much lower allelic frequency (0.00105) than used in the rest of the study to better exemplify the actual selective effect over a 1,000-year time scale. (D) The allelic selection effect over a 2,000-year time scale.
<!-- image -->
## Discussion
This study illustrates how populations can differ in susceptibility to epidemic HIV/AIDS depending on a ubiquitous attribute such as a prevailing genotype. We have examined heterosexual HIV epidemics by using mathematical models to assess HIV transmission in dynamic populations either with or without CCR5Δ32 heterozygous and homozygous persons. The most susceptible population lacks the protective mutation in CCR5. In less susceptible populations, the majority of persons carrying the CCR5Δ32 allele are heterozygotes. We explore the hypothesis that lower viral loads (CCR5Δ32 heterozygotes) or resistance to infection (CCR5Δ32 homozygotes) observed in persons with this coreceptor mutation ultimately can influence HIV epidemic trends. Two contrasting influences of the protective CCR5 allele are conceivable: it may limit the epidemic by decreasing the probability of infection because of lower viral loads in infected heterozygotes, or it may exacerbate the epidemic by extending the time that infectious individuals remain in the sexually active population. Our results strongly suggest the former. Thus, the absence of this allele in Africa could explain the severity of HIV disease as compared with populations where the allele is present.
We also observed that HIV can provide selective pressure for the CCR5Δ32 allele within a population, increasing the allelic frequency. Other influences may have additionally selected for this allele. Infectious diseases such as plague and small pox have been postulated to select for CCR5Δ32 (57, 58). For plague, relatively high levels of CCR5Δ32 are believed to have arisen within ≈4,000 years, accounting for the prevalence of the mutation only in populations of European descent. Smallpox virus uses the CC-coreceptor, indicating that direct selection for mutations in CCR5 may have offered resistance to smallpox. Given the differences in the epidemic rates of plague (59), smallpox, and HIV, it is difficult to directly compare our results to these findings. However, our model suggests that the CCR5Δ32 mutation could have reached its present allelic frequency in Northern Europe within this time frame if selected for by a disease with virulence patterns similar to HIV. Our results further support the idea that HIV has been only recently introduced as a pathogen into African populations, as the frequency of the protective allele is almost zero, and our model predicts that selection of the mutant allele in this population by HIV alone takes at least 1,000 years. This prediction is distinct from the frequency of the CCR5Δ32 allele in European populations, where pathogens that may have influenced its frequency (e.g., Yersinia pestis) have been present for much longer.
Two mathematical models have considered the role of parasite and host genetic heterogeneity with regard to susceptibility to another pathogen, namely malaria (60, 61). In each it was determined that heterogeneity of host resistance facilitates the maintenance of diversity in parasite virulence. Given our underlying interest in the coevolution of pathogen and host, we focus on changes in a host protective mutation, holding the virulence of the pathogen constant over time.
Even within our focus on host protective mutations, numerous genetic factors, beneficial or detrimental, could potentially influence epidemics. Other genetically determined host factors affecting HIV susceptibility and disease progression include a CCR5 A/A to G/G promoter polymorphism (62), a CCR2 point mutation (11, 63), and a mutation in the CXCR4 ligand (64). The CCR2b mutation, CCR264I, is found in linkage with at least one CCR5 promoter polymorphism (65) and is prevalent in populations where CCR5Δ32 is nonexistent, such as sub-Saharan Africa (63). However, as none of these mutations have been consistently shown to be as protective as the CCR5Δ32 allele, we simplified our model to incorporate only the effect of CCR5Δ32. Subsequent models could be constructed from our model to account for the complexity of multiple protective alleles. It is interesting to note that our model predicts that even if CCR264I is present at high frequencies in Africa, its protective effects may not augment the lack of a protective allele such as CCR5Δ32.
Although our models demonstrate that genetic factors can contribute to the high prevalence of HIV in sub-Saharan Africa, demographic factors are also clearly important in this region. Our models explicitly incorporated such factors, for example, lack of treatment availability. Additional factors were implicitly controlled for by varying only the presence of the CCR5Δ32 allele. More complex models eventually could include interactions with infectious diseases that serve as cofactors in HIV transmission. The role of high sexually transmitted disease prevalences in HIV infection has long been discussed, especially in relation to core populations (15, 50, 66). Malaria, too, might influence HIV transmission, as it is associated with transient increases in semen HIV viral loads and thus could increase the susceptibility of the population to epidemic HIV (16).
In assessing the HIV/AIDS epidemic, considerable attention has been paid to the influence of core groups in driving sexually transmitted disease epidemics. Our results also highlight how characteristics more uniformly distributed in a population can affect susceptibility. We observed that the genotypic profile of a population affects its susceptibility to epidemic HIV/AIDS. Additional studies are needed to better characterize the influence of these genetic determinants on HIV transmission, as they may be crucial in estimating the severity of the epidemic in some populations. This information can influence the design of treatment strategies as well as point to the urgency for education and prevention programs.
## Acknowledgments
We thank Mark Krosky, Katia Koelle, and Kevin Chung for programming and technical assistance. We also thank Drs. V. J. DiRita, P. Kazanjian, and S. M. Blower for helpful comments and discussions. We thank the reviewers for extremely insightful comments.
## References
- Weiss HA, Hawkes S. Leprosy Rev 72:92–98 (2001). PMID: 11355525
- Taha TE, Dallabetta GA, Hoover DR, Chiphangwi JD, Mtimavalye LAR. AIDS 12:197–203 (1998). PMID: 9468369
- AIDS Epidemic Update. Geneva: World Health Organization1–17 (1998).
- D'Souza MP, Harden VA. Nat Med 2:1293–1300 (1996). PMID: 8946819
- Martinson JJ, Chapman NH, Rees DC, Liu YT, Clegg JB. Nat Genet 16:100–103 (1997). PMID: 9140404
- Roos MTL, Lange JMA, deGoede REY, Miedema PT, Tersmette F, Coutinho M, Schellekens RA. J Infect Dis 165:427–432 (1992). PMID: 1347054
- Garred P, Eugen-Olsen J, Iversen AKN, Benfield TL, Svejgaard A, Hofmann B. Lancet 349:1884 (1997). PMID: 9217763
- Katzenstein TL, Eugen-Olsen J, Hofman B, Benfield T, Pedersen C, Iversen AK, Sorensen AM, Garred P, Koppelhus U, Svejgaard A, Gerstoft J. J Acquired Immune Defic Syndr Hum Retrovirol 16:10–14 (1997). PMID: 9377119
- deRoda H, Meyer K, Katzenstain W, Dean M. Science 273:1856–1862 (1996). PMID: 8791590
- Meyer L, Magierowska M, Hubert JB, Rouzioux C, Deveau C, Sanson F, Debre P, Delfraissy JF, Theodorou I. AIDS 11:F73–F78 (1997). PMID: 9302436
- Smith MW, Dean M, Carrington M, Winkler C, Huttley DA, Lomb GA, Goedert JJ, O'Brien TR, Jacobson LP, Kaslow R, et al. Science 277:959–965 (1997). PMID: 9252328
- Samson M, Libert F, Doranz BJ, Rucker J, Liesnard C, Farber CM, Saragosti S, Lapoumeroulie C, Cognaux J, Forceille C, et al. Nature (London) 382:722–725 (1996). PMID: 8751444
- McNicholl JM, Smith DK, Qari SH, Hodge T. Emerging Infect Dis 3:261–271 (1997). PMID: 9284370
- Michael NL, Chang G, Louie LG, Mascola JR, Dondero D, Birx DL, Sheppard HW. Nat Med 3:338–340 (1997). PMID: 9055864
- Mayaud P, Mosha F, Todd J, Balira R, Mgara J, West B, Rusizoka M, Mwijarubi E, Gabone R, Gavyole A, et al. AIDS 11:1873–1880 (1997). PMID: 9412707
- Hoffman IF, Jere CS, Taylor TE, Munthali P, Dyer JR. AIDS 13:487–494 (1998).
- HIV/AIDS Surveillance Database. Washington, DC: Population Division, International Programs Center (1999).
- Anderson RM, May RM, McLean AR. Nature (London) 332:228–234 (1988). PMID: 3279320
- Berger EA, Doms RW, Fenyo EM, Korber BT, Littman DR, Moore JP, Sattentau QJ, Schuitemaker H, Sodroski J, Weiss RA. Nature (London) 391:240 (1998). PMID: 9440686
- Alkhatib G, Broder CC, Berger EA. J Virol 70:5487–5494 (1996). PMID: 8764060
- Choe H, Farzan M, Sun Y, Sullivan N, Rollins B, Ponath PD, Wu L, Mackay CR, LaRosa G, Newman W, et al. Cell 85:1135–1148 (1996). PMID: 8674119
- Deng H, Liu R, Ellmeier W, Choe S, Unutmaz D, Burkhart M, Di Marzio P, Marmon S, Sutton RE, Hill CM, et al. Nature (London) 381:661–666 (1996). PMID: 8649511
- Doranz BJ, Rucker J, Yi Y, Smyth RJ, Samsom M, Peiper M, Parmentier SC, Collman RG, Doms RW. Cell 85:1149–1158 (1996). PMID: 8674120
- Dragic T, Litwin V, Allaway GP, Martin SR, Huang Y, Nagashima KA, Cayanan C, Maddon PJ, Koup RA, Moore JP, Paxton WA. Nature (London) 381:667–673 (1996). PMID: 8649512
- Zhu T, Mo H, Wang N, Nam DS, Cao Y, Koup RA, Ho DD. Science 261:1179–1181 (1993). PMID: 8356453
- Bjorndal A, Deng H, Jansson M, Fiore JR, Colognesi C, Karlsson A, Albert J, Scarlatti G, Littman DR, Fenyo EM. J Virol 71:7478–7487 (1997). PMID: 9311827
- Conner RI, Sheridan KE, Ceradinin D, Choe S, Landau NR. J Exp Med 185:621–628 (1997). PMID: 9034141
- Liu R, Paxton WA, Choe S, Ceradini D, Martin SR, Horuk R, MacDonald ME, Stuhlmann H, Koup RA, Landau NR. Cell 86:367–377 (1996). PMID: 8756719
- Mussico M, Lazzarin A, Nicolosi A, Gasparini M, Costigliola P, Arici C, Saracco A. Arch Intern Med (Moscow) 154:1971–1976 (1994). PMID: 8074601
- Michael NL, Nelson JA, KewalRamani VN, Chang G, O'Brien SJ, Mascola JR, Volsky B, Louder M, White GC, Littman DR, et al. J Virol 72:6040–6047 (1998). PMID: 9621067
- Hethcote HW, Yorke JA. Gonorrhea Transmission Dynamics and Control. Berlin: Springer (1984).
- Anderson RM, May RM. Nature (London) 333:514–522 (1988). PMID: 3374601
- Asiimwe-Okiror G, Opio AA, Musinguzi J, Madraa E, Tembo G, Carael M. AIDS 11:1757–1763 (1997). PMID: 9386811
- Carael M, Cleland J, Deheneffe JC, Ferry B, Ingham R. AIDS 9:1171–1175 (1995). PMID: 8519454
- Blower SM, Boe C. J AIDS 6:1347–1352 (1993). PMID: 8254474
- Kirschner D. J Appl Math 56:143–166 (1996).
- Le Pont F, Blower S. J AIDS 4:987–999 (1991). PMID: 1890608
- Kim MY, Lagakos SW. Ann Epidemiol 1:117–128 (1990). PMID: 1669741
- Anderson RM, May RM. Infectious Disease of Humans: Dynamics and Control. Oxford: Oxford Univ. Press (1992).
- Ragni MV, Faruki H, Kingsley LA. J Acquired Immune Defic Syndr 17:42–45 (1998).
- Kaplan JE, Khabbaz RF, Murphy EL, Hermansen S, Roberts C, Lal R, Heneine W, Wright D, Matijas L, Thomson R, et al. J Acquired Immune Defic Syndr Hum Retrovirol 12:193–201 (1996). PMID: 8680892
- Padian NS, Shiboski SC, Glass SO, Vittinghoff E. Am J Edu 146:350–357 (1997).
- Leynaert B, Downs AM, de Vincenzi I. Am J Edu 148:88–96 (1998).
- Garnett GP, Anderson RM. J Acquired Immune Defic Syndr 9:500–513 (1995).
- Stigum H, Magnus P, Harris JR, Samualson SO, Bakketeig LS. Am J Edu 145:636–643 (1997).
- Ho DD, Neumann AU, Perelson AS, Chen W, Leonard JM, Markowitz M. Nature (London) 373:123–126 (1995). PMID: 7816094
- World Resources (1998–1999). Oxford: Oxford Univ. Press (1999).
- Kostrikis LG, Neumann AU, Thomson B, Korber BT, McHardy P, Karanicolas R, Deutsch L, Huang Y, Lew JF, McIntosh K, et al. J Virol 73:10264–10271 (1999). PMID: 10559343
- Low-Beer D, Stoneburner RL, Mukulu A. Nat Med 3:553–557 (1997). PMID: 9142126
- Grosskurth H, Mosha F, Todd J, Senkoro K, Newell J, Klokke A, Changalucha J, West B, Mayaud P, Gavyole A. AIDS 9:927–934 (1995). PMID: 7576329
- Melo J, Beby-Defaux A, Faria C, Guiraud G, Folgosa E, Barreto A, Agius G. J AIDS 23:203–204 (2000). PMID: 10737436
- Iman RL, Helton JC, Campbell JE. J Quality Technol 13:174–183 (1981).
- Iman RL, Helton JC, Campbell JE. J Quality Technol 13:232–240 (1981).
- Blower SM, Dowlatabadi H. Int Stat Rev 62:229–243 (1994).
- Porco TC, Blower SM. Theor Popul Biol 54:117–132 (1998). PMID: 9733654
- Blower SM, Porco TC, Darby G. Nat Med 4:673–678 (1998). PMID: 9623975
- Libert F, Cochaux P, Beckman G, Samson M, Aksenova M, Cao A, Czeizel A, Claustres M, de la Rua C, Ferrari M, et al. Hum Mol Genet 7:399–406 (1998). PMID: 9466996
- Lalani AS, Masters J, Zeng W, Barrett J, Pannu R, Everett H, Arendt CW, McFadden G. Science 286:1968–1971 (1999). PMID: 10583963
- Kermack WO, McKendrick AG. Proc R Soc London 261:700–721 (1927).
- Gupta S, Hill AVS. Proc R Soc London Ser B 260:271–277 (1995).
- Ruwende C, Khoo SC, Snow RW, Yates SNR, Kwiatkowski D, Gupta S, Warn P, Allsopp CE, Gilbert SC, Peschu N. Nature (London) 376:246–249 (1995). PMID: 7617034
- McDermott DH, Zimmerman PA, Guignard F, Kleeberger CA, Leitman SF, Murphy PM. Lancet 352:866–870 (1998). PMID: 9742978
- Kostrikis LG, Huang Y, Moore JP, Wolinsky SM, Zhang L, Guo Y, Deutsch L, Phair J, Neumann AU, Ho DD. Nat Med 4:350–353 (1998). PMID: 9500612
- Winkler C, Modi W, Smith MW, Nelson GW, Wu X, Carrington M, Dean M, Honjo T, Tashiro K, Yabe D, et al. Science 279:389–393 (1998). PMID: 9430590
- Martinson JJ, Hong L, Karanicolas R, Moore JP, Kostrikis LG. AIDS 14:483–489 (2000). PMID: 10780710
- Vernazza PL, Eron JJ, Fiscus SA, Cohen MS. AIDS 13:155–166 (1999). PMID: 10202821

0
tests/data/groundtruth/docling_v2/pntd.0008301.xml.itxt → tests/data/groundtruth/docling_v2/pntd.0008301.nxml.itxt vendored
View File

7237
tests/data/groundtruth/docling_v2/pntd.0008301.nxml.json vendored Normal file
View File

File diff suppressed because it is too large Load Diff

24
tests/data/groundtruth/docling_v2/pntd.0008301.xml.md → tests/data/groundtruth/docling_v2/pntd.0008301.nxml.md vendored
View File

@ -34,16 +34,16 @@ Table 1 Categorization of potential factors influencing pre-TAS results.
| Domain | Factor | Covariate | Description | Reference Group | Summary statistic | Temporal Resolution | Source |
|------------------------|-----------------------|-------------------------------|-----------------------------------------------------------------|----------------------|---------------------|-----------------------|--------------------|
| Prevalence | Baseline prevalence | 5% cut off | Maximum reported mapping or baseline sentinel site prevalence | &lt;5% | Maximum | Varies | Programmatic data |
| Prevalence | Baseline prevalence | 10% cut off | Maximum reported mapping or baseline sentinel site prevalence | &lt;10% | Maximum | Varies | Programmatic data |
| Agent | Parasite | Parasite | Predominate parasite in district | W. bancrofti &amp; mixed | Binary value | 2018 | Programmatic data |
| Environment | Vector | Vector | Predominate vector in district | Anopheles &amp; Mansonia | Binary value | 2018 | Country expert |
| Environment | Geography | Elevation | Elevation measured in meters | &gt;350 | Mean | 2000 | CGIAR-CSI SRTM [9] |
| Environment | Geography | District area | Area measured in km2 | &gt;2,500 | Maximum sum | Static | Programmatic data |
| Environment | Climate | EVI | Enhanced vegetation index | &gt; 0.3 | Mean | 2015 | MODIS [10] |
| Prevalence | Baseline prevalence | 5% cut off | Maximum reported mapping or baseline sentinel site prevalence | <5% | Maximum | Varies | Programmatic data |
| Prevalence | Baseline prevalence | 10% cut off | Maximum reported mapping or baseline sentinel site prevalence | <10% | Maximum | Varies | Programmatic data |
| Agent | Parasite | Parasite | Predominate parasite in district | W. bancrofti & mixed | Binary value | 2018 | Programmatic data |
| Environment | Vector | Vector | Predominate vector in district | Anopheles & Mansonia | Binary value | 2018 | Country expert |
| Environment | Geography | Elevation | Elevation measured in meters | >350 | Mean | 2000 | CGIAR-CSI SRTM [9] |
| Environment | Geography | District area | Area measured in km2 | >2,500 | Maximum sum | Static | Programmatic data |
| Environment | Climate | EVI | Enhanced vegetation index | > 0.3 | Mean | 2015 | MODIS [10] |
| Environment | Climate | Rainfall | Annual rainfall measured in mm | ≤ 700 | Mean | 2015 | CHIRPS [11] |
| Environment | Socio-economic | Population density | Number of people per km2 | ≤ 100 | Mean | 2015 | WorldPop [12] |
| Environment | Socio-economic | Nighttime lights | Nighttime light index from 0 to 63 | &gt;1.5 | Mean | 2015 | VIIRS [13] |
| Environment | Socio-economic | Nighttime lights | Nighttime light index from 0 to 63 | >1.5 | Mean | 2015 | VIIRS [13] |
| Environment | Co-endemicity | Co-endemic for onchocerciasis | Part or all of district is also endemic for onchocerciases | Non-endemic | Binary value | 2018 | Programmatic data |
| MDA | Drug efficacy | Drug package | DEC-ALB or IVM-ALB | DEC-ALB | Binary value | 2018 | Programmatic data |
| MDA | Implementation of MDA | Coverage | Median MDA coverage for last 5 rounds | ≥ 65% | Median | Varies | Programmatic data |
@ -134,12 +134,12 @@ Table 2 Adjusted risk ratios for pre-TAS failure from log-binomial model sensiti
| Number of Failures | 74 | 74 | 44 | 72 | 46 |
| Number of total districts | (N = 554) | (N = 420) | (N = 407) | (N = 518) | (N = 414) |
| Covariate | RR (95% CI) | RR (95% CI) | RR (95% CI) | RR (95% CI) | RR (95% CI) |
| Baseline prevalence &gt; = 10% &amp; used FTS test | 2.38 (0.96–5.90) | 1.23 (0.52–2.92) | 14.52 (1.79–117.82) | 2.61 (1.03–6.61) | 15.80 (1.95–127.67) |
| Baseline prevalence &gt; = 10% &amp; used ICT test | 0.80 (0.20–3.24) | 0.42 (0.11–1.68) | 1.00 (0.00–0.00) | 0.88 (0.21–3.60) | 1.00 (0.00–0.00) |
| Baseline prevalence > = 10% & used FTS test | 2.38 (0.96–5.90) | 1.23 (0.52–2.92) | 14.52 (1.79–117.82) | 2.61 (1.03–6.61) | 15.80 (1.95–127.67) |
| Baseline prevalence > = 10% & used ICT test | 0.80 (0.20–3.24) | 0.42 (0.11–1.68) | 1.00 (0.00–0.00) | 0.88 (0.21–3.60) | 1.00 (0.00–0.00) |
| +Used FTS test | 1.16 (0.52–2.59) | 2.40 (1.12–5.11) | 0.15 (0.02–1.11) | 1.03 (0.45–2.36) | 0.13 (0.02–0.96) |
| +Used ICT test | 0.92 (0.32–2.67) | 1.47 (0.51–4.21) | 0.33 (0.04–2.54) | 0.82 (0.28–2.43) | 0.27 (0.03–2.04) |
| +Baseline prevalence &gt; = 10% | 2.52 (1.37–4.64) | 2.42 (1.31–4.47) | 2.03 (1.06–3.90) | 2.30 (1.21–4.36) | 2.01 (1.07–3.77) |
| Elevation &lt; 350m | 3.07 (1.95–4.83) | 2.21 (1.42–3.43) | 4.68 (2.22–9.87) | 3.04 (1.93–4.79) | 3.76 (1.92–7.37) |
| +Baseline prevalence > = 10% | 2.52 (1.37–4.64) | 2.42 (1.31–4.47) | 2.03 (1.06–3.90) | 2.30 (1.21–4.36) | 2.01 (1.07–3.77) |
| Elevation < 350m | 3.07 (1.95–4.83) | 2.21 (1.42–3.43) | 4.68 (2.22–9.87) | 3.04 (1.93–4.79) | 3.76 (1.92–7.37) |
Overall 74 districts in the dataset failed pre-TAS. Fig 5 summarizes the likelihood of failure by variable combinations identified in the log-binomial model. For those districts with a baseline prevalence ≥10% that used a FTS diagnostic test and have an average elevation below 350 meters (Combination C01), 87% of the 23 districts failed. Of districts with high baseline that used an ICT diagnostic test and have a low average elevation (C02) 45% failed. Overall, combinations with high baseline and low elevation C01, C02, and C04 accounted for 51% of all the failures (38 of 74).

0
tests/data/groundtruth/docling_v2/pone.0234687.xml.itxt → tests/data/groundtruth/docling_v2/pone.0234687.nxml.itxt vendored
View File

14628
tests/data/groundtruth/docling_v2/pone.0234687.nxml.json vendored Normal file
View File

File diff suppressed because it is too large Load Diff

0
tests/data/groundtruth/docling_v2/pone.0234687.xml.md → tests/data/groundtruth/docling_v2/pone.0234687.nxml.md vendored
View File

842
tests/data/jats/bmj_sample.xml vendored
View File

@ -1,842 +0,0 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.1 20151215//EN" "JATS-journalpublishing1.dtd">
<article article-type="research-article" dtd-version="1.1" xml:lang="en"
xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" >
<front>
<journal-meta>
<journal-id journal-id-type="pmc">bmj</journal-id>
<journal-id journal-id-type="pubmed">BMJ</journal-id>
<journal-id journal-id-type="publisher">BMJ</journal-id>
<issn>0959-8138</issn>
<publisher>
<publisher-name>BMJ</publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id pub-id-type="other">jBMJ.v324.i7342.pg880</article-id>
<article-id pub-id-type="pmid">11950738</article-id>
<article-categories>
<subj-group>
<subject>Primary care</subject>
<subj-group>
<subject>190</subject>
<subject>10</subject>
<subject>218</subject>
<subject>219</subject>
<subject>355</subject>
<subject>357</subject>
</subj-group>
</subj-group>
</article-categories>
<title-group>
<article-title>Evolving general practice consultation in Britain: issues of length and
context</article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname>Freeman</surname>
<given-names>George K</given-names>
</name>
<role>professor of general practice</role>
<xref ref-type="aff" rid="aff-a"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname>Horder</surname>
<given-names>John P</given-names>
</name>
<role>past president</role>
<xref ref-type="aff" rid="aff-b"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname>Howie</surname>
<given-names>John G R</given-names>
</name>
<role>emeritus professor of general practice</role>
<xref ref-type="aff" rid="aff-c"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname>Hungin</surname>
<given-names>A Pali</given-names>
</name>
<role>professor of general practice</role>
<xref ref-type="aff" rid="aff-d"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname>Hill</surname>
<given-names>Alison P</given-names>
</name>
<role>general practitioner</role>
<xref ref-type="aff" rid="aff-e"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname>Shah</surname>
<given-names>Nayan C</given-names>
</name>
<role>general practitioner</role>
<xref ref-type="aff" rid="aff-b"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname>Wilson</surname>
<given-names>Andrew</given-names>
</name>
<role>senior lecturer</role>
<xref ref-type="aff" rid="aff-f"/>
</contrib>
</contrib-group>
<aff id="aff-a">Centre for Primary Care and Social Medicine, Imperial College of Science,
Technology and Medicine, London W6 8RP</aff>
<aff id="aff-b">Royal College of General Practitioners, London SW7 1PU</aff>
<aff id="aff-c">Department of General Practice, University of Edinburgh, Edinburgh EH8 9DX</aff>
<aff id="aff-d">Centre for Health Studies, University of Durham, Durham DH1 3HN</aff>
<aff id="aff-e">Kilburn Park Medical Centre, London NW6</aff>
<aff id="aff-f">Department of General Practice and Primary Health Care, University of Leicester,
Leicester LE5 4PW</aff>
<author-notes>
<fn fn-type="con">
<p>Contributors: GKF wrote the paper and revised it after repeated and detailed comments from
all of the other authors and feedback from the first referee and from the <italic>BMJ</italic>
editorial panel. All other authors gave detailed and repeated comments and cristicisms. GKF is
the guarantor of the paper.</p>
</fn>
<fn>
<p>Correspondence to: G Freeman <email>g.freeman@ic.ac.uk</email> </p>
</fn>
</author-notes>
<pub-date date-type="pub" publication-format="print" iso-8601-date="2002-04-13">
<day>13</day>
<month>4</month>
<year>2002</year>
</pub-date>
<volume>324</volume>
<issue>7342</issue>
<fpage>880</fpage>
<lpage>882</lpage>
<history>
<date date-type="accepted" iso-8601-date="2002-02-07" publication-format="print">
<day>7</day>
<month>2</month>
<year>2002</year>
</date>
</history>
<permissions>
<copyright-statement>Copyright &#x00A9; 2002, BMJ</copyright-statement>
<copyright-year>2002, </copyright-year>
</permissions>
</article-meta>
</front>
<body>
<p>In 1999 Shah<xref ref-type="bibr" rid="B1">1</xref> and others said that the Royal College of
General Practitioners should advocate longer consultations in general practice as a matter of
policy. The college set up a working group chaired by A P Hungin, and a systematic review of
literature on consultation length in general practice was commissioned. The working group agreed
that the available evidence would be hard to interpret without discussion of the changing context
within which consultations now take place. For many years general practitioners and those who
have surveyed patients' opinions in the United Kingdom have complained about short consultation
time, despite a steady increase in actual mean length. Recently Mechanic pointed out that this is
also true in the United States.<xref ref-type="bibr" rid="B2">2</xref> Is there any justification
for a further increase in mean time allocated per consultation in general practice?</p>
<p>We report on the outcome of extensive debate among a group of general practitioners with an
interest in the process of care, with reference to the interim findings of the commissioned
systematic review and our personal databases. The review identified 14 relevant papers. <boxed-text>
<sec>
<title>Summary points</title>
<p> <list list-type="bullet">
<list-item>
<p>Longer consultations are associated with a range of better patient outcomes</p>
</list-item>
<list-item>
<p>Modern consultations in general practice deal with patients with more serious and chronic
conditions</p>
</list-item>
<list-item>
<p>Increasing patient participation means more complex interaction, which demands extra
time</p>
</list-item>
<list-item>
<p>Difficulties with access and with loss of continuity add to perceived stress and poor
performance and lead to further pressure on time</p>
</list-item>
<list-item>
<p>Longer consultations should be a professional priority, combined with increased use of
technology and more flexible practice management to maximise interpersonal continuity</p>
</list-item>
<list-item>
<p>Research on implementation is needed</p>
</list-item>
</list> </p>
</sec>
</boxed-text> </p>
<sec sec-type="subjects">
<title>Longer consultations: benefits for patients</title>
<p>The systematic review consistently showed that doctors with longer consultation times
prescribe less and offer more advice on lifestyle and other health promoting activities. Longer
consultations have been significantly associated with better recognition and handling of
psychosocial problems<xref ref-type="bibr" rid="B3">3</xref> and with better patient
enablement.<xref ref-type="bibr" rid="B4">4</xref> Also clinical care for some chronic illnesses
is better in practices with longer booked intervals between one appointment and the next.<xref
ref-type="bibr" rid="B5">5</xref> It is not clear whether time is itself the main influence or
whether some doctors insist on more time.</p>
<p>A national survey in 1998 reported that most (87&#x0025;) patients were satisfied with the
length of their most recent consultation.<xref ref-type="bibr" rid="B6">6</xref> Satisfaction
with any service will be high if expectations are met or exceeded. But expectations are modified
by previous experience.<xref ref-type="bibr" rid="B7">7</xref> The result is that primary care
patients are likely to be satisfied with what they are used to unless the context modifies the
effects of their own experience.</p>
</sec>
<sec>
<title>Context of modern consultations</title>
<p>Shorter consultations were more appropriate when the population was younger, when even a brief
absence from employment due to sickness required a doctor's note, and when many simple remedies
were available only on prescription. Recently at least five important influences have increased
the content and hence the potential length of the consultation.</p>
</sec>
<sec>
<title>Participatory consultation style</title>
<p>The most effective consultations are those in which doctors most directly acknowledge and
perhaps respond to patients' problems and concerns. In addition, for patients to be committed to
taking advantage of medical advice they must agree with both the goals and methods proposed. A
landmark publication in the United Kingdom was <italic>Meetings Between Experts</italic>, which
argued that while doctors are the experts about medical problems in general patients are the
experts on how they themselves experience these problems.<xref ref-type="bibr" rid="B8">8</xref>
New emphasis on teaching consulting skills in general practice advocated specific attention to
the patient's agenda, beliefs, understanding, and agreement. Currently the General Medical
Council, aware that communication difficulties underlie many complaints about doctors, has
further emphasised the importance of involving patients in consultations in its revised guidance
to medical schools.<xref ref-type="bibr" rid="B9">9</xref> More patient involvement should give
a better outcome, but this participatory style usually lengthens consultations.</p>
</sec>
<sec>
<title>Extended professional agenda</title>
<p>The traditional consultation in general practice was brief.<xref ref-type="bibr" rid="B2"
>2</xref> The patient presented symptoms and the doctor prescribed treatment. In 1957 Balint
gave new insights into the meaning of symptoms.<xref ref-type="bibr" rid="B10">10</xref> By 1979
an enhanced model of consultation was presented, in which the doctors dealt with ongoing as well
as presenting problems and added health promotion and education about future appropriate use of
services.<xref ref-type="bibr" rid="B11">11</xref> Now, with an ageing population and more
community care of chronic illness, there are more issues to be considered at each consultation.
Ideas of what constitutes good general practice are more complex.<xref ref-type="bibr" rid="B12"
>12</xref> Good practice now includes both extended care of chronic medical problems&#x2014;for
example, coronary heart disease<xref ref-type="bibr" rid="B13">13</xref>&#x2014;and a public
health role. At first this model was restricted to those who lead change (&#x201C;early
adopters&#x201D;) and enthusiasts<xref ref-type="bibr" rid="B14">14</xref> but now it is
embedded in professional and managerial expectations of good practice.</p>
<p>Adequate time is essential. It may be difficult for an elderly patient with several active
problems to undress, be examined, and get adequate professional consideration in under 15
minutes. Here the doctor is faced with the choice of curtailing the consultation or of reducing
the time available for the next patient. Having to cope with these situations often contributes
to professional dissatisfaction.<xref ref-type="bibr" rid="B15">15</xref> This combination of
more care, more options, and more genuine discussion of those options with informed patient
choice inevitably leads to pressure on time.</p>
</sec>
<sec>
<title>Access problems</title>
<p>In a service free at the point of access, rising demand will tend to increase rationing by
delay. But attempts to improve access by offering more consultations at short notice squeeze
consultation times.</p>
<p>While appointment systems can and should reduce queuing time for consultations, they have long
tended to be used as a brake on total demand.<xref ref-type="bibr" rid="B16">16</xref> This may
seriously erode patients' confidence in being able to see their doctor or nurse when they need
to. Patients are offered appointments further ahead but may keep these even if their symptoms
have remitted &#x201C;just in case.&#x201D; Availability of consultations is thus blocked.
Receptionists are then inappropriately blamed for the inadequate access to doctors.</p>
<p>In response to perception of delay, the government has set targets in the NHS plan of
&#x201C;guaranteed access to a primary care professional within 24 hours and to a primary care
doctor within 48 hours.&#x201D; Implementation is currently being negotiated.</p>
<p>Virtually all patients think that they would not consult unless it was absolutely necessary.
They do not think they are wasting NHS time and do not like being made to feel so. But
underlying general practitioners' willingness to make patients wait several days is their
perception that few of the problems are urgent. Patients and general practitioners evidently do
not agree about the urgency of so called minor problems. To some extent general practice in the
United Kingdom may have scored an &#x201C;own goal&#x201D; by setting up perceived access
barriers (appointment systems and out of hours cooperatives) in the attempt to increase
professional standards and control demand in a service that is free at the point of access.</p>
<p>A further government initiative has been to bypass general practice with new
services&#x2014;notably, walk-in centres (primary care clinics in which no appointment is
needed) and NHS Direct (a professional telephone helpline giving advice on simple remedies and
access to services). Introduced widely and rapidly, these services each potentially provide
significant features of primary care&#x2014;namely, quick access to skilled health advice and
first line treatment.</p>
</sec>
<sec>
<title>Loss of interpersonal continuity</title>
<p>If a patient has to consult several different professionals, particularly over a short period
of time, there is inevitable duplication of stories, risk of naive diagnoses, potential for
conflicting advice, and perhaps loss of trust. Trust is essential if patients are to accept the
&#x201C;wait and see&#x201D; management policy which is, or should be, an important part of the
management of self limiting conditions, which are often on the boundary between illness and
non-illness.<xref ref-type="bibr" rid="B17">17</xref> Such duplication again increases pressure
for more extra (unscheduled) consultations resulting in late running and professional
frustration.<xref ref-type="bibr" rid="B18">18</xref> </p>
<p>Mechanic described how loss of longitudinal (and perhaps personal and relational<xref
ref-type="bibr" rid="B19">19</xref>) continuity influences the perception and use of time
through an inability to build on previous consultations.<xref ref-type="bibr" rid="B2">2</xref>
Knowing the doctor well, particularly in smaller practices, is associated with enhanced patient
enablement in shorter time.<xref ref-type="bibr" rid="B4">4</xref> Though Mechanic pointed out
that three quarters of UK patients have been registered with their general practitioner five
years or more, this may be misleading. Practices are growing, with larger teams and more
registered patients. Being registered with a doctor in a larger practice is usually no guarantee
that the patient will be able to see the same doctor or the doctor of his or her choice, who may
be different. Thus the system does not encourage adequate personal continuity. This adds to
pressure on time and reduces both patient and professional satisfaction.</p>
</sec>
<sec>
<title>Health service reforms</title>
<p>Finally, for the past 15 years the NHS has experienced unprecedented change with a succession
of major administrative reforms. Recent reforms have focused on an NHS led by primary care,
including the aim of shifting care from the secondary specialist sector to primary care. One
consequence is increased demand for primary care of patients with more serious and less stable
problems. With the limited piloting of reforms we do not know whether such major redirection can
be achieved without greatly altering the delicate balance between expectations (of both patients
and staff) and what is delivered.</p>
</sec>
<sec>
<title>The future</title>
<p>We think that the way ahead must embrace both longer mean consultation times and more
flexibility. More time is needed for high quality consultations with patients with major and
complex problems of all kinds. But patients also need access to simpler services and advice.
This should be more appropriate (and cost less) when it is given by professionals who know the
patient and his or her medical history and social circumstances. For doctors, the higher quality
associated with longer consultations may lead to greater professional satisfaction and, if these
longer consultations are combined with more realistic scheduling, to reduced levels of
stress.<xref ref-type="bibr" rid="B20">20</xref> They will also find it easier to develop
further the care of chronic disease.</p>
<p>The challenge posed to general practice by walk-in centres and NHS Direct is considerable, and
the diversion of funding from primary care is large. The risk of waste and duplication increases
as more layers of complexity are added to a primary care service that started out as something
familiar, simple, and local and which is still envied in other developed countries.<xref
ref-type="bibr" rid="B21">21</xref> Access needs to be simple, and the advantages of personal
knowledge and trust in minimising duplication and overmedicalisation need to be exploited.</p>
<p>We must ensure better communication and access so that patients can more easily deal with
minor issues and queries with someone they know and trust and avoid the formality and
inconvenience of a full face to face consultation. Too often this has to be with a different
professional, unfamiliar with the nuances of the case. There should be far more managerial
emphasis on helping patients to interact with their chosen practitioner<xref ref-type="bibr"
rid="B22">22</xref>; such a programme has been described.<xref ref-type="bibr" rid="B23"
>23</xref> Modern information systems make it much easier to record which doctor(s) a patient
prefers to see and to monitor how often this is achieved. The telephone is hardly modern but is
underused. Email avoids the problems inherent in arranging simultaneous availability necessary
for telephone consultations but at the cost of reducing the communication of emotions. There is
a place for both.<xref ref-type="bibr" rid="B2">2</xref> Access without prior appointment is a
valued feature of primary care, and we need to know more about the right balance between planned
and ad hoc consulting.</p>
</sec>
<sec>
<title>Next steps</title>
<p>General practitioners do not behave in a uniform way. They can be categorised as slow, medium,
and fast and react in different ways to changes in consulting speed.<xref ref-type="bibr"
rid="B18">18</xref> They are likely to have differing views about a widespread move to lengthen
consultation time. We do not need further confirmation that longer consultations are desirable
and necessary, but research could show us the best way to learn how to introduce them with
minimal disruption to the way in which patients and practices like primary care to be
provided.<xref ref-type="bibr" rid="B24">24</xref> We also need to learn how to make the most of
available time in complex consultations.</p>
<p>Devising appropriate incentives and helping practices move beyond just reacting to demand in
the traditional way by working harder and faster is perhaps our greatest challenge in the United
Kingdom. The new primary are trusts need to work together with the growing primary care research
networks to carry out the necessary development work. In particular, research is needed on how a
primary care team can best provide the right balance of quick access and interpersonal knowledge
and trust.</p>
</sec>
</body>
<back>
<ack>
<p>We thank the other members of the working group: Susan Childs, Paul Freeling, Iona Heath,
Marshall Marinker, and Bonnie Sibbald. We also thank Fenny Green of the Royal College of General
Practitioners for administrative help.</p>
</ack>
<ref-list>
<ref id="B1">
<label>1</label>
<element-citation publication-type="journal" publication-format="print">
<person-group person-group-type="author"> <name>
<surname>Shah</surname>
<given-names>NC</given-names>
</name> </person-group>
<article-title>Viewpoint: Consultation time&#x2014;time for a change? Still the
&#x201C;perfunctory work of perfunctory men!&#x201D;</article-title>
<source>Br J Gen Pract</source>
<year iso-8601-date="1999">1999</year>
<volume>49</volume>
<fpage>497</fpage>
</element-citation>
</ref>
<ref id="B2">
<label>2</label>
<element-citation publication-type="journal" publication-format="print">
<person-group person-group-type="author"> <name>
<surname>Mechanic</surname>
<given-names>D</given-names>
</name> </person-group>
<article-title>How should hamsters run? Some observations about sufficient patient time in
primary care</article-title>
<source>BMJ</source>
<year iso-8601-date="2001">2001</year>
<volume>323</volume>
<fpage>266</fpage>
<lpage>268</lpage>
<pub-id pub-id-type="pmid">11485957</pub-id>
</element-citation>
</ref>
<ref id="B3">
<label>3</label>
<element-citation publication-type="journal" publication-format="print">
<person-group person-group-type="author"> <name>
<surname>Howie</surname>
<given-names>JGR</given-names>
</name> <name>
<surname>Porter</surname>
<given-names>AMD</given-names>
</name> <name>
<surname>Heaney</surname>
<given-names>DJ</given-names>
</name> <name>
<surname>Hopton</surname>
<given-names>JL</given-names>
</name> </person-group>
<article-title>Long to short consultation ratio: a proxy measure of quality of care for general
practice</article-title>
<source>Br J Gen Pract</source>
<year iso-8601-date="1991">1991</year>
<volume>41</volume>
<fpage>48</fpage>
<lpage>54</lpage>
<pub-id pub-id-type="pmid">2031735</pub-id>
</element-citation>
</ref>
<ref id="B4">
<label>4</label>
<element-citation publication-type="journal" publication-format="print">
<person-group person-group-type="author"> <name>
<surname>Howie</surname>
<given-names>JGR</given-names>
</name> <name>
<surname>Heaney</surname>
<given-names>DJ</given-names>
</name> <name>
<surname>Maxwell</surname>
<given-names>M</given-names>
</name> <name>
<surname>Walker</surname>
<given-names>JJ</given-names>
</name> <name>
<surname>Freeman</surname>
<given-names>GK</given-names>
</name> <name>
<surname>Rai</surname>
<given-names>H</given-names>
</name> </person-group>
<article-title>Quality at general practice consultations: cross-sectional
survey</article-title>
<source>BMJ</source>
<year iso-8601-date="1999">1999</year>
<volume>319</volume>
<fpage>738</fpage>
<lpage>743</lpage>
<pub-id pub-id-type="pmid">10487999</pub-id>
</element-citation>
</ref>
<ref id="B5">
<label>5</label>
<element-citation publication-type="journal" publication-format="print">
<person-group person-group-type="author"> <name>
<surname>Kaplan</surname>
<given-names>SH</given-names>
</name> <name>
<surname>Greenfield</surname>
<given-names>S</given-names>
</name> <name>
<surname>Ware</surname>
<given-names>JE</given-names>
</name> </person-group>
<article-title>Assessing the effects of physician-patient interactions on the outcome of
chronic disease</article-title>
<source>Med Care</source>
<year iso-8601-date="1989">1989</year>
<volume>27</volume>
<supplement>suppl 3</supplement>
<fpage>110</fpage>
<lpage>125</lpage>
</element-citation>
</ref>
<ref id="B6">
<label>6</label>
<element-citation publication-type="book" publication-format="print">
<person-group person-group-type="editor"> <name>
<surname>Airey</surname>
<given-names>C</given-names>
</name> <name>
<surname>Erens</surname>
<given-names>B</given-names>
</name> </person-group>
<source>National surveys of NHS patients: general practice, 1998</source>
<year iso-8601-date="1999">1999</year>
<publisher-loc>London</publisher-loc>
<publisher-name>NHS Executive</publisher-name>
</element-citation>
</ref>
<ref id="B7">
<label>7</label>
<element-citation publication-type="journal" publication-format="print">
<person-group person-group-type="author"> <name>
<surname>Hart</surname>
<given-names>JT</given-names>
</name> </person-group>
<article-title>Expectations of health care: promoted, managed or shared?</article-title>
<source>Health Expect</source>
<year iso-8601-date="1998">1998</year>
<volume>1</volume>
<fpage>3</fpage>
<lpage>13</lpage>
<pub-id pub-id-type="pmid">11281857</pub-id>
</element-citation>
</ref>
<ref id="B8">
<label>8</label>
<element-citation publication-type="book" publication-format="print">
<person-group person-group-type="author"> <name>
<surname>Tuckett</surname>
<given-names>D</given-names>
</name> <name>
<surname>Boulton</surname>
<given-names>M</given-names>
</name> <name>
<surname>Olson</surname>
<given-names>C</given-names>
</name> <name>
<surname>Williams</surname>
<given-names>A</given-names>
</name> </person-group>
<source>Meetings between experts: an approach to sharing ideas in medical
consultations</source>
<year iso-8601-date="1985">1985</year>
<publisher-loc>London</publisher-loc>
<publisher-name>Tavistock Publications</publisher-name>
</element-citation>
</ref>
<ref id="B9">
<label>9</label>
<mixed-citation publication-type="webpage" publication-format="web">General Medical Council.
<source>Draft recommendations on undergraduate medical education</source>. July 2001.
www.gmc-uk.org/med_ed/tomorrowsdoctors/index.htm (accessed 2 Jan 2002).</mixed-citation>
</ref>
<ref id="B10">
<label>10</label>
<element-citation publication-type="book" publication-format="print">
<person-group person-group-type="author"> <name>
<surname>Balint</surname>
<given-names>M</given-names>
</name> </person-group>
<source>The doctor, his patient and the illness</source>
<year iso-8601-date="1957">1957</year>
<publisher-loc>London</publisher-loc>
<publisher-name>Tavistock</publisher-name>
</element-citation>
</ref>
<ref id="B11">
<label>11</label>
<element-citation publication-type="journal" publication-format="print">
<person-group person-group-type="author"> <name>
<surname>Stott</surname>
<given-names>NCH</given-names>
</name> <name>
<surname>Davies</surname>
<given-names>RH</given-names>
</name> </person-group>
<article-title>The exceptional potential in each primary care consultation</article-title>
<source>J R Coll Gen Pract</source>
<year iso-8601-date="1979">1979</year>
<volume>29</volume>
<fpage>210</fpage>
<lpage>205</lpage>
</element-citation>
</ref>
<ref id="B12">
<label>12</label>
<element-citation publication-type="book" publication-format="print">
<person-group person-group-type="author"> <name>
<surname>Hill</surname>
<given-names>AP</given-names>
</name> </person-group>
<person-group person-group-type="editor"> <name>
<surname>Hill</surname>
<given-names>AP</given-names>
</name> </person-group>
<article-title>Challenges for primary care</article-title>
<source>What's gone wrong with health care? Challenges for the new millennium</source>
<year iso-8601-date="2000">2000</year>
<publisher-loc>London</publisher-loc>
<publisher-name>King's Fund</publisher-name>
<fpage>75</fpage>
<lpage>86</lpage>
</element-citation>
</ref>
<ref id="B13">
<label>13</label>
<element-citation publication-type="book" publication-format="print">
<collab>Department of Health</collab>
<source>National service framework for coronary heart disease</source>
<year iso-8601-date="2000">2000</year>
<publisher-loc>London</publisher-loc>
<publisher-name>Department of Health</publisher-name>
</element-citation>
</ref>
<ref id="B14">
<label>14</label>
<element-citation publication-type="book" publication-format="print">
<person-group person-group-type="author"> <name>
<surname>Hart</surname>
<given-names>JT</given-names>
</name> </person-group>
<source>A new kind of doctor: the general practitioner's part in the health of the
community</source>
<year iso-8601-date="1988">1988</year>
<publisher-loc>London</publisher-loc>
<publisher-name>Merlin Press</publisher-name>
</element-citation>
</ref>
<ref id="B15">
<label>15</label>
<element-citation publication-type="journal" publication-format="print">
<person-group person-group-type="author"> <name>
<surname>Morrison</surname>
<given-names>I</given-names>
</name> <name>
<surname>Smith</surname>
<given-names>R</given-names>
</name> </person-group>
<article-title>Hamster health care</article-title>
<source>BMJ</source>
<year iso-8601-date="2000">2000</year>
<volume>321</volume>
<fpage>1541</fpage>
<lpage>1542</lpage>
<pub-id pub-id-type="pmid">11124164</pub-id>
</element-citation>
</ref>
<ref id="B16">
<label>16</label>
<element-citation publication-type="journal" publication-format="print">
<person-group person-group-type="author"> <name>
<surname>Arber</surname>
<given-names>S</given-names>
</name> <name>
<surname>Sawyer</surname>
<given-names>L</given-names>
</name> </person-group>
<article-title>Do appointment systems work?</article-title>
<source>BMJ</source>
<year iso-8601-date="1982">1982</year>
<volume>284</volume>
<fpage>478</fpage>
<lpage>480</lpage>
<pub-id pub-id-type="pmid">6800503</pub-id>
</element-citation>
</ref>
<ref id="B17">
<label>17</label>
<element-citation publication-type="journal" publication-format="print">
<person-group person-group-type="author"> <name>
<surname>Hjortdahl</surname>
<given-names>P</given-names>
</name> <name>
<surname>Borchgrevink</surname>
<given-names>CF</given-names>
</name> </person-group>
<article-title>Continuity of care: influence of general practitioners' knowledge about their
patients on use of resources in consultations</article-title>
<source>BMJ</source>
<year iso-8601-date="1991">1991</year>
<volume>303</volume>
<fpage>1181</fpage>
<lpage>1184</lpage>
<pub-id pub-id-type="pmid">1747619</pub-id>
</element-citation>
</ref>
<ref id="B18">
<label>18</label>
<element-citation publication-type="journal" publication-format="print">
<person-group person-group-type="author"> <name>
<surname>Howie</surname>
<given-names>JGR</given-names>
</name> <name>
<surname>Hopton</surname>
<given-names>JL</given-names>
</name> <name>
<surname>Heaney</surname>
<given-names>DJ</given-names>
</name> <name>
<surname>Porter</surname>
<given-names>AMD</given-names>
</name> </person-group>
<article-title>Attitudes to medical care, the organization of work, and stress among general
practitioners</article-title>
<source>Br J Gen Pract</source>
<year iso-8601-date="1992">1992</year>
<volume>42</volume>
<fpage>181</fpage>
<lpage>185</lpage>
<pub-id pub-id-type="pmid">1389427</pub-id>
</element-citation>
</ref>
<ref id="B19">
<label>19</label>
<element-citation publication-type="book" publication-format="web">
<person-group person-group-type="author"> <name>
<surname>Freeman</surname>
<given-names>G</given-names>
</name> <name>
<surname>Shepperd</surname>
<given-names>S</given-names>
</name> <name>
<surname>Robinson</surname>
<given-names>I</given-names>
</name> <name>
<surname>Ehrich</surname>
<given-names>K</given-names>
</name> <name>
<surname>Richards</surname>
<given-names>SC</given-names>
</name> <name>
<surname>Pitman</surname>
<given-names>P</given-names>
</name> </person-group>
<source>Continuity of care: report of a scoping exercise for the national co-ordinating centre
for NHS Service Delivery and Organisation R&#x0026;D (NCCSDO), Summer 2000</source>
<year iso-8601-date="2001">2001</year>
<publisher-loc>London</publisher-loc>
<publisher-name>NCCSDO</publisher-name>
<comment><ext-link ext-link-type="url" xmlns:xlink="http://www.w3.org/1999/xlink"
xlink:href="http://www.sdo.lshtm.ac.uk/continuityofcare.htm"
>www.sdo.lshtm.ac.uk/continuityofcare.htm</ext-link> (accessed 2 Jan 2002)</comment>
</element-citation>
</ref>
<ref id="B20">
<label>20</label>
<element-citation publication-type="journal" publication-format="print">
<person-group person-group-type="author"> <name>
<surname>Wilson</surname>
<given-names>A</given-names>
</name> <name>
<surname>McDonald</surname>
<given-names>P</given-names>
</name> <name>
<surname>Hayes</surname>
<given-names>L</given-names>
</name> <name>
<surname>Cooney</surname>
<given-names>J</given-names>
</name> </person-group>
<article-title>Longer booking intervals in general practice: effects on doctors' stress and
arousal</article-title>
<source>Br J Gen Pract</source>
<year iso-8601-date="1991">1991</year>
<volume>41</volume>
<fpage>184</fpage>
<lpage>187</lpage>
<pub-id pub-id-type="pmid">1878267</pub-id>
</element-citation>
</ref>
<ref id="B21">
<label>21</label>
<element-citation publication-type="journal" publication-format="print">
<person-group person-group-type="author"> <name>
<surname>De Maeseneer</surname>
<given-names>J</given-names>
</name> <name>
<surname>Hjortdahl</surname>
<given-names>P</given-names>
</name> <name>
<surname>Starfield</surname>
<given-names>B</given-names>
</name> </person-group>
<article-title>Fix what's wrong, not what's right, with general practice in
Britain</article-title>
<source>BMJ</source>
<year iso-8601-date="2000">2000</year>
<volume>320</volume>
<fpage>1616</fpage>
<lpage>1617</lpage>
<pub-id pub-id-type="pmid">10856043</pub-id>
</element-citation>
</ref>
<ref id="B22">
<label>22</label>
<element-citation publication-type="journal" publication-format="print">
<person-group person-group-type="author"> <name>
<surname>Freeman</surname>
<given-names>G</given-names>
</name> <name>
<surname>Hjortdahl</surname>
<given-names>P</given-names>
</name> </person-group>
<article-title>What future for continuity of care in general practice?</article-title>
<source>BMJ</source>
<year iso-8601-date="1997">1997</year>
<volume>314</volume>
<fpage>1870</fpage>
<lpage>1873</lpage>
<pub-id pub-id-type="pmid">9224130</pub-id>
</element-citation>
</ref>
<ref id="B23">
<label>23</label>
<element-citation publication-type="journal" publication-format="print">
<person-group person-group-type="author"> <name>
<surname>Kibbe</surname>
<given-names>DC</given-names>
</name> <name>
<surname>Bentz</surname>
<given-names>E</given-names>
</name> <name>
<surname>McLaughlin</surname>
<given-names>CP</given-names>
</name> </person-group>
<article-title>Continuous quality improvement for continuity of care</article-title>
<source>J Fam Pract</source>
<year iso-8601-date="1993">1993</year>
<volume>36</volume>
<fpage>304</fpage>
<lpage>308</lpage>
<pub-id pub-id-type="pmid">8454977</pub-id>
</element-citation>
</ref>
<ref id="B24">
<label>24</label>
<element-citation publication-type="journal" publication-format="print">
<person-group person-group-type="author"> <name>
<surname>Williams</surname>
<given-names>M</given-names>
</name> <name>
<surname>Neal</surname>
<given-names>RD</given-names>
</name> </person-group>
<article-title>Time for a change? The process of lengthening booking intervals in general
practice</article-title>
<source>Br J Gen Pract</source>
<year iso-8601-date="1998">1998</year>
<volume>48</volume>
<fpage>1783</fpage>
<lpage>1786</lpage>
<pub-id pub-id-type="pmid">10198490</pub-id>
</element-citation>
</ref>
</ref-list>
<fn-group>
<fn id="fn1">
<p>Funding: Meetings of the working group in 1999-2000 were funded by the
<funding-source>Scientific Foundation Board of the RCGP</funding-source>.</p>
</fn>
<fn id="fn2">
<p>Competing interests: None declared.</p>
</fn>
</fn-group>
</back>
</article>

3089
tests/data/jats/pnas_sample.xml vendored
View File

File diff suppressed because it is too large Load Diff

96
tests/data/jats/pntd.0008301.txt vendored
View File

File diff suppressed because one or more lines are too long

96
tests/data/jats/pntd.0008301.xml vendored
View File

File diff suppressed because one or more lines are too long

60
tests/data/jats/pone.0234687.txt vendored
View File

File diff suppressed because one or more lines are too long

60
tests/data/jats/pone.0234687.xml vendored
View File

File diff suppressed because one or more lines are too long

28
tests/test_backend_jats.py
View File

@ -14,9 +14,9 @@ from .verify_utils import verify_document, verify_export
GENERATE = GEN_TEST_DATA
def get_pubmed_paths():
directory = Path(os.path.dirname(__file__) + "/data/pubmed/")
xml_files = sorted(directory.rglob("*.xml"))
def get_jats_paths():
directory = Path(os.path.dirname(__file__) + "/data/jats/")
xml_files = sorted(directory.rglob("*.nxml"))
return xml_files
@ -25,20 +25,20 @@ def get_converter():
return converter
def test_e2e_pubmed_conversions(use_stream=False):
pubmed_paths = get_pubmed_paths()
def test_e2e_jats_conversions(use_stream=False):
jats_paths = get_jats_paths()
converter = get_converter()
for pubmed_path in pubmed_paths:
for jats_path in jats_paths:
gt_path = (
pubmed_path.parent.parent / "groundtruth" / "docling_v2" / pubmed_path.name
jats_path.parent.parent / "groundtruth" / "docling_v2" / jats_path.name
)
if use_stream:
buf = BytesIO(pubmed_path.open("rb").read())
stream = DocumentStream(name=pubmed_path.name, stream=buf)
buf = BytesIO(jats_path.open("rb").read())
stream = DocumentStream(name=jats_path.name, stream=buf)
conv_result: ConversionResult = converter.convert(stream)
else:
conv_result: ConversionResult = converter.convert(pubmed_path)
conv_result: ConversionResult = converter.convert(jats_path)
doc: DoclingDocument = conv_result.document
pred_md: str = doc.export_to_markdown()
@ -54,9 +54,9 @@ def test_e2e_pubmed_conversions(use_stream=False):
assert verify_document(doc, str(gt_path) + ".json", GENERATE), "export to json"
def test_e2e_pubmed_conversions_stream():
test_e2e_pubmed_conversions(use_stream=True)
def test_e2e_jats_conversions_stream():
test_e2e_jats_conversions(use_stream=True)
def test_e2e_pubmed_conversions_no_stream():
test_e2e_pubmed_conversions(use_stream=False)
def test_e2e_jats_conversions_no_stream():
test_e2e_jats_conversions(use_stream=False)