1
|
MacRae C, Whittaker H, Mukherjee M, Daines L, Morgan A, Iwundu C, Alsallakh M, Vasileiou E, O’Rourke E, Williams AT, Stone PW, Sheikh A, Quint JK. Deriving a Standardised Recommended Respiratory Disease Codelist Repository for Future Research. Pragmat Obs Res 2022; 13:1-8. [PMID: 35210898 PMCID: PMC8859726 DOI: 10.2147/por.s353400] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/10/2021] [Accepted: 01/26/2022] [Indexed: 11/23/2022] Open
Abstract
Background Electronic health record (EHR) databases provide rich, longitudinal data on interactions with healthcare providers and can be used to advance research into respiratory conditions. However, since these data are primarily collected to support health care delivery, clinical coding can be inconsistent, resulting in inherent challenges in using these data for research purposes. Methods We systematically searched existing international literature and UK code repositories to find respiratory disease codelists for asthma from January 2018, and chronic obstructive pulmonary disease and respiratory tract infections from January 2020, based on prior searches. Medline searches using key terms provided in article lists. Full-text articles, supplementary files, and reference lists were examined for codelists, and codelists repositories were searched. A reproducible methodology for codelists creation was developed with recommended lists for each disease created based on multidisciplinary expert opinion and previously published literature. Results Medline searches returned 1126 asthma articles, 70 COPD articles, and 90 respiratory infection articles, with 3%, 22% and 5% including codelists, respectively. Repository searching returned 12 asthma, 23 COPD, and 64 respiratory infection codelists. We have systematically compiled respiratory disease codelists and from these derived recommended lists for use by researchers to find the most up-to-date and relevant respiratory disease codelists that can be tailored to individual research questions. Conclusion Few published papers include codelists, and where published diverse codelists were used, even when answering similar research questions. Whilst some advances have been made, greater consistency and transparency across studies using routine data to study respiratory diseases are needed.
Collapse
Affiliation(s)
- Clare MacRae
- Usher Institute, University of Edinburgh, Edinburgh, UK
| | - Hannah Whittaker
- National Heart and Lung Institute, Imperial College London, London, UK
| | | | - Luke Daines
- Usher Institute, University of Edinburgh, Edinburgh, UK
| | - Ann Morgan
- National Heart and Lung Institute, Imperial College London, London, UK
| | - Chukwuma Iwundu
- National Heart and Lung Institute, Imperial College London, London, UK
| | | | | | - Eimear O’Rourke
- National Heart and Lung Institute, Imperial College London, London, UK
| | | | - Philip W Stone
- National Heart and Lung Institute, Imperial College London, London, UK
| | - Aziz Sheikh
- Usher Institute, University of Edinburgh, Edinburgh, UK
| | - Jennifer K Quint
- National Heart and Lung Institute, Imperial College London, London, UK
- Correspondence: Jennifer K Quint, National Heart and Lung Institute, Imperial College London, G48, Emmanuel Kaye Building, Manresa Road, London, SW3 6LR, UK, Tel +44 207 594 8821, Email
| |
Collapse
|
2
|
Bu J, Lin Y, Qing LQ, Hu G, Jiang P, Hu HF, Shen EX. Prediction of skin disease using a new cytological taxonomy based on cytology and pathology with deep residual learning method. Sci Rep 2021; 11:13764. [PMID: 34215767 PMCID: PMC8253798 DOI: 10.1038/s41598-021-92848-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/13/2021] [Accepted: 05/10/2021] [Indexed: 11/12/2022] Open
Abstract
With the development of artificial intelligence, technique improvement of the classification of skin disease is addressed. However, few study concerned on the current classification system of International Classification of Diseases, Tenth Revision (ICD)-10 on Diseases of the skin and subcutaneous tissue, which is now globally used for classification of skin disease. This study was aimed to develop a new taxonomy of skin disease based on cytology and pathology, and test its predictive effect on skin disease compared to ICD-10. A new taxonomy (Taxonomy 2) containing 6 levels (Project 2–4) was developed based on skin cytology and pathology, and represents individual diseases arranged in a tree structure with three root nodes representing: (1) Keratinogenic diseases, (2) Melanogenic diseases, and (3) Diseases related to non-keratinocytes and non-melanocytes. The predictive effects of the new taxonomy including accuracy, precision, recall, F1, and Kappa were compared with those of ICD-10 on Diseases of the skin and subcutaneous tissue (Taxonomy 1, Project 1) by Deep Residual Learning method. For each project, 2/3 of the images were included as training group, and the rest 1/3 of the images acted as test group according to the category (class) as the stratification variable. Both train and test groups in the Projects (2 and 3) from Taxonomy 2 had higher F1 and Kappa scores without statistical significance on the prediction of skin disease than the corresponding groups in the Project 1 from Taxonomy 1, however both train and test groups in Project 4 had a statistically significantly higher F1-score than the corresponding groups in Project 1 (P = 0.025 and 0.005, respectively). The results showed that the new taxonomy developed based on cytology and pathology has an overall better performance on predictive effect of skin disease than the ICD-10 on Diseases of the skin and subcutaneous tissue. The level 5 (Project 4) of Taxonomy 2 is better on extension to unknown data of diagnosis system assisted by AI compared to current used classification system from ICD-10, and may have the potential application value in clinic of dermatology.
Collapse
Affiliation(s)
- Jin Bu
- Hospital for Skin Disease (Institute of Dermatology), Chinese Academy of Medical Sciences and Peking Union Medical College, Nanjing, 210042, Jiangsu, China.
| | - Yu Lin
- Guangzhou South China Biomedical Research Institute, Co., Ltd, Guangzhou, 510275, Guangdong, China
| | - Li-Qiong Qing
- Nanxishan Hospital of Guangxi Zhuang Autonomous Region, Guilin, 541002, Guangxi, China
| | - Gang Hu
- School of Agriculture, Sun Yat-Sen University, Guangzhou, 510275, Guangdong, China
| | - Pei Jiang
- Xinhua College of Sun Yat-Sen University, Guangzhou, 510520, Guangdong, China
| | - Hai-Feng Hu
- School of Electronics and Information Technology (School of Microelectronics), Sun Yat-Sen University, Guangzhou, 510006, Guangdong, China.
| | - Er-Xia Shen
- Sino-French Hoffmann Institute, School of Basic Sciences, The Second Affiliated Hospital of Guangzhou Medical University, State Key Laboratory of Respiratory Disease, Guangdong Provincial Key Laboratory of Allergy & Clinical Immunology, Guangzhou Medical University, Guangzhou, 511436, Guangdong, China. .,The State Key Laboratory of Respiratory Disease, The First Affiliated Hospital, Guangzhou Medical University, Guangzhou, 510182, Guangdong, China.
| |
Collapse
|
3
|
Liu Y, Jain A, Eng C, Way DH, Lee K, Bui P, Kanada K, de Oliveira Marinho G, Gallegos J, Gabriele S, Gupta V, Singh N, Natarajan V, Hofmann-Wellenhof R, Corrado GS, Peng LH, Webster DR, Ai D, Huang SJ, Liu Y, Dunn RC, Coz D. A deep learning system for differential diagnosis of skin diseases. Nat Med 2020; 26:900-908. [PMID: 32424212 DOI: 10.1038/s41591-020-0842-3] [Citation(s) in RCA: 226] [Impact Index Per Article: 56.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/11/2019] [Accepted: 03/19/2020] [Indexed: 12/22/2022]
Abstract
Skin conditions affect 1.9 billion people. Because of a shortage of dermatologists, most cases are seen instead by general practitioners with lower diagnostic accuracy. We present a deep learning system (DLS) to provide a differential diagnosis of skin conditions using 16,114 de-identified cases (photographs and clinical data) from a teledermatology practice serving 17 sites. The DLS distinguishes between 26 common skin conditions, representing 80% of cases seen in primary care, while also providing a secondary prediction covering 419 skin conditions. On 963 validation cases, where a rotating panel of three board-certified dermatologists defined the reference standard, the DLS was non-inferior to six other dermatologists and superior to six primary care physicians (PCPs) and six nurse practitioners (NPs) (top-1 accuracy: 0.66 DLS, 0.63 dermatologists, 0.44 PCPs and 0.40 NPs). These results highlight the potential of the DLS to assist general practitioners in diagnosing skin conditions.
Collapse
Affiliation(s)
- Yuan Liu
- Google Health, Palo Alto, CA, USA
| | | | | | | | - Kang Lee
- Google Health, Palo Alto, CA, USA
| | - Peggy Bui
- Google Health, Palo Alto, CA, USA
- University of California, San Francisco, San Francisco, CA, USA
| | | | | | | | | | | | - Nalini Singh
- Google Health, Palo Alto, CA, USA
- Massachusetts Institute of Technology, Cambridge, MA, USA
| | | | | | | | | | | | | | | | - Yun Liu
- Google Health, Palo Alto, CA, USA.
| | | | | |
Collapse
|
4
|
Ramsey A, Sheikh A. Innovations in Health Care Delivery: Drug Allergy. THE JOURNAL OF ALLERGY AND CLINICAL IMMUNOLOGY-IN PRACTICE 2019; 7:2143-2150. [DOI: 10.1016/j.jaip.2019.04.050] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/05/2019] [Revised: 04/18/2019] [Accepted: 04/23/2019] [Indexed: 01/03/2023]
|
5
|
González-López G, García-Doval I, Molina-Leyva A, Descalzo-Gallego M, Taberner R, Gilaberte Y, Buendía-Eisman A, Fernández-Peñas P. Difficulties Coding Dermatological Disorders Using the ICD-10: The DIADERM Study. ACTAS DERMO-SIFILIOGRAFICAS 2018. [DOI: 10.1016/j.adengl.2018.10.010] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/27/2022] Open
|
6
|
González-López G, García-Doval I, Molina-Leyva A, Descalzo-Gallego MA, Taberner R, Gilaberte Y, Buendía-Eisman A, Fernández-Peñas P. Difficulties Coding Dermatological Disorders Using the ICD-10: The DIADERM Study. ACTAS DERMO-SIFILIOGRAFICAS 2018; 109:893-899. [PMID: 30268517 DOI: 10.1016/j.ad.2018.06.006] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/15/2018] [Revised: 06/10/2018] [Accepted: 06/14/2018] [Indexed: 12/17/2022] Open
Abstract
BACKGROUND AND OBJECTIVES The International Statistical Classification of Diseases and Related Health Problems, Tenth Revision (ICD-10) has some shortcomings when it comes to coding certain dermatological disorders. To overcome these shortcomings, a compatible version of the ICD-10 specifically adapted to dermatology was produced in Spain in 1999. The recent DIADERM study recorded 10 999 dermatological diagnoses using a representative sample of dermatologists working at outpatient clinics in Spain. The aims of the current study were to identify diagnoses from the DIADERM study that could not be coded using the adapted ICD-10, determine why, and check if they could be coded using the draft ICD-11. MATERIAL AND METHODS We included all dermatological diagnoses from the DIADERM study that could not be assigned a code from the adapted ICD-10. We then quantified and recorded all the diagnoses that could not be coded using either the adapted ICD-10 or the draft ICD-11. RESULTS Of the 10 999 diagnoses analyzed, 41 had not been assigned a code. Of these, 19 were assigned an adapted ICD-10 code on reassessment. However, the adapted ICD-10 and the draft ICD-11 lacked specific codes for 22 and 17 diagnoses, respectively. CONCLUSIONS The adapted ICD-10 can be used to correctly code the vast majority of dermatological diagnoses seen in routine clinical practice. Nevertheless, the system does have some minor shortcomings when it comes to coding certain diseases, particularly newly discovered and emerging diseases. Some of these problems, however, were resolved with the new ICD-11. Based on our findings, we propose some modifications to the ICD-11.
Collapse
Affiliation(s)
- G González-López
- Servicio de Dermatología, Hospital Universitario La Paz, Madrid, España.
| | - I García-Doval
- Unidad de Investigación, Fundación Piel Sana AEDV, Madrid, España; Servicio de Dermatología, Complejo Hospitalario de Vigo, Vigo, Pontevedra, España
| | - A Molina-Leyva
- Servicio de Dermatología, Hospital Universitario Virgen de las Nieves, Granada, España
| | | | - R Taberner
- Servicio de Dermatología, Hospital Son Llàtzer, Palma de Mallorca, Baleares, España
| | - Y Gilaberte
- Unidad de Dermatología, Hospital San Jorge de Huesca, Huesca, España
| | | | - P Fernández-Peñas
- The University of Sydney, Department of Dermatology, Westmead Hospital, Westmead, Sídney, New South Wales, Australia
| |
Collapse
|
7
|
Abstract
Supplemental Digital Content is Available in the Text. Patients with chronic widespread pain may regularly consult in primary care for regional pain without being recognized as having a generalized condition. Chronic widespread pain (CWP) is common in the general population. It is unclear how people reporting this problem present in primary care; they may regularly consult for regional pains without being recognized as having a generalized condition. Our objectives were to determine the prevalence of people consulting in primary care for musculoskeletal conditions in different body regions on different occasions (recurrent regional pain consultation), the proportion with diagnosed generalized pain and survey-reported widespread pain, and if they have features characteristic of CWP. Phase 1 used electronic records from 12 general practices in North Staffordshire (Consultations in Primary Care Archive) from 2005 to 2009. Phase 2 used linked self-reported health and primary health care data from 8286 people aged >50 years in 8 general practices (North Staffordshire Osteoarthritis Project) between 2002 and 2005. In Phase 1, 11% of registered patients fulfilled criteria for recurrent regional pain consultation. Three-quarters had no recorded CWP-related generalized pain condition (eg, fibromyalgia). In Phase 2, 53% of recurrent regional pain consulters had survey-reported widespread pain and 88% had consulted for somatic symptoms. Self-reported general health was worse in recurrent regional pain consulters than in single-region consulters and poorest in those who also reported persistent widespread pain. Recurrent regional pain consulters are a heterogeneous group of frequent consulters sharing features with CWP (eg, somatic symptoms) but including those less severely affected. They lie on the spectrum of polysymptomatic distress characteristic of CWP and represent a group whose needs may be better met by earlier diagnosis of multisite pain.
Collapse
|
8
|
Mukherjee M, Wyatt JC, Simpson CR, Sheikh A. Usage of allergy codes in primary care electronic health records: a national evaluation in Scotland. Allergy 2016; 71:1594-1602. [PMID: 27146325 DOI: 10.1111/all.12928] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 04/30/2016] [Indexed: 02/06/2023]
Abstract
BACKGROUND The UK's NHS intends to move from the current Read code system to the international, detailed Systematized Nomenclature of Medicine Clinical Terms (SNOMED-CT) to facilitate more clinically appropriate coding of conditions and associated risk factors and outcomes. Given concerns about coding behaviour of general practitioners, we sought to study the current coding patterns in allergies and identify lessons for the future migration to SNOMED-CT. METHODS Data from 2 014 551 primary care consultations in over 100 000 patients with one or more of 11 potentially allergic diseases (anaphylaxis, angioedema, asthma, conjunctivitis, drug allergies, eczema, food allergy, rhinitis, urticaria, venom allergy and other probable allergic disorders) from the Scottish Primary Care Clinical Informatics Unit Research (PCCIU-R) database were descriptively analysed and visualized to understand Read code usage patterns. RESULTS We identified 352 Read codes for these allergic diseases, but only 36 codes (10%) were used in 95% of consultations; 73 codes (21%) were never used. Half of all usage was for Quality and Outcomes Framework codes for asthma. Despite 149 detailed codes (42%) being available for allergic triggers, these were infrequently used. CONCLUSIONS This analysis of Read codes use suggests that introduction of the more detailed SNOMED-CT, in isolation, will not improve the quality of allergy coding in Scottish primary care. The introduction of SNOMED-CT should be accompanied by initiatives aimed at improving coding quality, such as the definition of terms/codes, the availability of terminology browsers, a recommended list of codes and mechanisms to incentivize detailed coding of the condition and the underlying allergic trigger.
Collapse
Affiliation(s)
- M. Mukherjee
- Edinburgh Clinical Trials Unit (ECTU); The University of Edinburgh; Edinburgh UK
- Asthma UK Centre for Applied Research; Centre for Medical Informatics; Usher Institute of Population Health Sciences and Informatics; The University of Edinburgh; Edinburgh UK
| | - J. C. Wyatt
- Faculty of Medicine; Wessex Institute of Health & Research; University of Southampton; Southampton UK
| | - C. R. Simpson
- Asthma UK Centre for Applied Research; Centre for Medical Informatics; Usher Institute of Population Health Sciences and Informatics; The University of Edinburgh; Edinburgh UK
| | - A. Sheikh
- Asthma UK Centre for Applied Research; Centre for Medical Informatics; Usher Institute of Population Health Sciences and Informatics; The University of Edinburgh; Edinburgh UK
| |
Collapse
|
9
|
Coding of Electronic Laboratory Reports for Biosurveillance, Selected United States Hospitals, 2011. Online J Public Health Inform 2015; 7:e220. [PMID: 26392850 PMCID: PMC4576438 DOI: 10.5210/ojphi.v7i2.5859] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022] Open
Abstract
Objective Electronic laboratory reporting has been promoted as a public health priority.
The Office of the U.S. National Coordinator for Health Information Technology
has endorsed two coding systems: Logical Observation Identifiers Names and Codes
(LOINC) for laboratory test orders and Systemized Nomenclature of
Medicine-Clinical Terms (SNOMED CT) for test results. Materials and Methods We examined LOINC and SNOMED CT code use in electronic laboratory data reported
in 2011 by 63 non-federal hospitals to BioSense electronic syndromic
surveillance system. We analyzed the frequencies, characteristics, and code
concepts of test orders and results. Results A total of 14,028,774 laboratory test orders or results were reported. No test
orders used SNOMED CT codes. To describe test orders, 77% used a LOINC code, 17%
had no value, and 6% had a non-informative value, “OTH”.
Thirty-three percent (33%) of test results had missing or non-informative codes.
For test results with at least one informative value, 91.8% had only LOINC
codes, 0.7% had only SNOMED codes, and 7.4% had both. Of 108 SNOMED CT codes
reported without LOINC codes, 45% could be matched to at least one LOINC
code. Conclusion Missing or non-informative codes comprised almost a quarter of laboratory test
orders and a third of test results reported to BioSense by non-federal
hospitals. Use of LOINC codes for laboratory test results was more common than
use of SNOMED CT. Complete and standardized coding could improve the usefulness
of laboratory data for public health surveillance and response.
Collapse
|
10
|
Tanno LK, Calderon MA, Goldberg BJ, Gayraud J, Bircher AJ, Casale T, Li J, Sanchez-Borges M, Rosenwasser LJ, Pawankar R, Papadopoulos NG, Demoly P. Constructing a classification of hypersensitivity/allergic diseases for ICD-11 by crowdsourcing the allergist community. Allergy 2015; 70:609-15. [PMID: 25736171 DOI: 10.1111/all.12604] [Citation(s) in RCA: 54] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 03/01/2015] [Indexed: 11/29/2022]
Abstract
The global allergy community strongly believes that the 11th revision of the International Classification of Diseases (ICD-11) offers a unique opportunity to improve the classification and coding of hypersensitivity/allergic diseases via inclusion of a specific chapter dedicated to this disease area to facilitate epidemiological studies, as well as to evaluate the true size of the allergy epidemic. In this context, an international collaboration has decided to revise the classification of hypersensitivity/allergic diseases and to validate it for ICD-11 by crowdsourcing the allergist community. After careful comparison between ICD-10 and 11 beta phase linearization codes, we identified gaps and trade-offs allowing us to construct a classification proposal, which was sent to the European Academy of Allergy and Clinical Immunology (EAACI) sections, interest groups, executive committee as well as the World Allergy Organization (WAO), and American Academy of Allergy Asthma and Immunology (AAAAI) leaderships. The crowdsourcing process produced comments from 50 of 171 members contacted by e-mail. The classification proposal has also been discussed at face-to-face meetings with experts of EAACI sections and interest groups and presented in a number of business meetings during the 2014 EAACI annual congress in Copenhagen. As a result, a high-level complex structure of classification for hypersensitivity/allergic diseases has been constructed. The model proposed has been presented to the WHO groups in charge of the ICD revision. The international collaboration of allergy experts appreciates bilateral discussion and aims to get endorsement of their proposals for the final ICD-11.
Collapse
Affiliation(s)
| | - M. A. Calderon
- Section of Allergy and Clinical Immunology; Imperial College London; National Heart and Lung Institute; Royal Brompton Hospital; London UK
| | - B. J. Goldberg
- Kaiser-Permanente Southern California Regional Allergy-Immunology Laboratory; Los Angeles, CA USA
- International Health Terminology Standards Development Organization; Los Angeles, CA USA
| | | | - A. J. Bircher
- Allergy Unit; Department of Dermatology; University Hospital Basel; Basel Switzerland
| | - T. Casale
- Internal Medicine; Morsani College of Medicine; University of South Florida; Tampa FL USA
| | - J. Li
- Division of Allergic Diseases; Mayo Clinic; Rochester MN USA
| | - M. Sanchez-Borges
- Allergy and Clinical Immunology Department; Centro Medico Docente La Trinidad; Caracas Venezuela
| | - L. J. Rosenwasser
- Division of Immunology Research; Department of Pediatrics; Children's Mercy Hospitals & Clinics; Kansas City MO USA
| | - R. Pawankar
- Division of Allergy; Department of Pediatrics; Nippon Medical School; Tokyo Japan
| | - N. G. Papadopoulos
- Centre for Paediatrics and Child Health; Institute of Human Development; University of Manchester; Manchester UK
- Department of Allergy; 2nd Pediatric Clinic; University of Athens; Athens Greece
| | - P. Demoly
- University Hospital of Montpellier; Montpellier France
- Sorbonne Universités; UPMC Paris 06; UMR-S 1136; IPLESP; Equipe EPAR; Paris France
| |
Collapse
|
11
|
Fernando B, Morrison Z, Kalra D, Cresswell K, Sheikh A. Approaches to recording drug allergies in electronic health records: qualitative study. PLoS One 2014; 9:e93047. [PMID: 24740090 PMCID: PMC3989180 DOI: 10.1371/journal.pone.0093047] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/04/2013] [Accepted: 02/28/2014] [Indexed: 11/19/2022] Open
Abstract
BACKGROUND Drug allergy represent an important subset of adverse drug reactions that is worthy of attention because many of these reactions are potentially preventable with use of computerised decision support systems. This is however dependent on the accurate and comprehensive recording of these reactions in the electronic health record. The objectives of this study were to understand approaches to the recording of drug allergies in electronic health record systems. MATERIALS AND METHODS We undertook a case study comprising of 21 in-depth interviews with a purposefully selected group of primary and secondary care clinicians, academics, and members of the informatics and drug regulatory communities, observations in four General Practices and an expert group discussion with 15 participants from the Allergy and Respiratory Expert Resource Group of the Royal College of General Practitioners. RESULTS There was widespread acceptance among healthcare professionals of the need for accurate recording of drug allergies and adverse drug reactions. Most drug reactions were however likely to go unreported to and/or unrecognised by healthcare professionals and, even when recognised and reported, not all reactions were accurately recorded. The process of recording these reactions was not standardised. CONCLUSIONS There is considerable variation in the way drug allergies are recorded in electronic health records. This limits the potential of computerised decision support systems to help alert clinicians to the risk of further reactions. Inaccurate recording of information may in some instances introduce new problems as patients are denied treatments that they are erroneously believed to be allergic to.
Collapse
Affiliation(s)
- Bernard Fernando
- eHealth Research Group, Centre for Population Health Sciences, The University of Edinburgh, Edinburgh, United Kingdom
| | - Zoe Morrison
- eHealth Research Group, Centre for Population Health Sciences, The University of Edinburgh, Edinburgh, United Kingdom
| | - Dipak Kalra
- Centre for Health Informatics and Multiprofessional Education, University College London, London, United Kingdom
| | - Kathrin Cresswell
- The School of Health in Social Science, The University of Edinburgh, Edinburgh, United Kingdom
| | - Aziz Sheikh
- eHealth Research Group, Centre for Population Health Sciences, The University of Edinburgh, Edinburgh, United Kingdom
- Allergy and Respiratory Research Group, Centre for Population Health Sciences, The University of Edinburgh, Edinburgh, United Kingdom
- Harvard Medical School & Harkness Fellow in Health Care Policy and Practice, Division of General Internal Medicine and Primary Care, Brigham and Women's Hospital/Harvard Medical School, Boston, Massachusetts, United States of America
- * E-mail:
| |
Collapse
|
12
|
King AJ, Gehl RW, Grossman D, Jensen JD. Skin self-examinations and visual identification of atypical nevi: comparing individual and crowdsourcing approaches. Cancer Epidemiol 2013; 37:979-84. [PMID: 24075797 DOI: 10.1016/j.canep.2013.09.004] [Citation(s) in RCA: 23] [Impact Index Per Article: 2.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/23/2013] [Revised: 08/29/2013] [Accepted: 09/02/2013] [Indexed: 11/25/2022]
Abstract
PURPOSE Skin self-examination (SSE) is one method for identifying atypical nevi among members of the general public. Unfortunately, past research has shown that SSE has low sensitivity in detecting atypical nevi. The current study investigates whether crowdsourcing (collective effort) can improve SSE identification accuracy. Collective effort is potentially useful for improving people's visual identification of atypical nevi during SSE because, even when a single person has low reliability at a task, the pattern of the group can overcome the limitations of each individual. METHODS Adults (N=500) were recruited from a shopping mall in the Midwest. Participants viewed educational pamphlets about SSE and then completed a mole identification task. For the task, participants were asked to circle mole images that appeared atypical. Forty nevi images were provided; nine of the images were of nevi that were later diagnosed as melanoma. RESULTS Consistent with past research, individual effort exhibited modest sensitivity (.58) for identifying atypical nevi in the mole identification task. As predicted, collective effort overcame the limitations of individual effort. Specifically, a 19% collective effort identification threshold exhibited superior sensitivity (.90). CONCLUSIONS The results of the current study suggest that limitations of SSE can be countered by collective effort, a finding that supports the pursuit of interventions promoting early melanoma detection that contain crowdsourced visual identification components.
Collapse
Affiliation(s)
- Andy J King
- College of Media & Communication, Texas Tech University, United States.
| | | | | | | |
Collapse
|
13
|
Agrawal A, He Z, Perl Y, Wei D, Halper M, Elhanan G, Chen Y. The readiness of SNOMED problem list concepts for meaningful use of electronic health records. Artif Intell Med 2013; 58:73-80. [PMID: 23602702 DOI: 10.1016/j.artmed.2013.03.008] [Citation(s) in RCA: 23] [Impact Index Per Article: 2.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/04/2012] [Revised: 03/05/2013] [Accepted: 03/17/2013] [Indexed: 11/24/2022]
Abstract
OBJECTIVE By 2015, SNOMED CT (SCT) will become the USA's standard for encoding diagnoses and problem lists in electronic health records (EHRs). To facilitate this effort, the National Library of Medicine has published the "SCT Clinical Observations Recording and Encoding" and the "Veterans Health Administration and Kaiser Permanente" problem lists (collectively, the "PL"). The PL is studied in regard to its readiness to support meaningful use of EHRs. In particular, we wish to determine if inconsistencies appearing in SCT, in general, occur as frequently in the PL, and whether further quality-assurance (QA) efforts on the PL are required. METHODS AND MATERIALS A study is conducted where two random samples of SCT concepts are compared. The first consists of concepts strictly from the PL and the second contains general SCT concepts distributed proportionally to the PL's in terms of their hierarchies. Each sample is analyzed for its percentage of primitive concepts and for frequency of modeling errors of various severity levels as quality measures. A simple structural indicator, namely, the number of parents, is suggested to locate high likelihood inconsistencies in hierarchical relationships. The effectiveness of this indicator is evaluated. RESULTS PL concepts are found to be slightly better than other concepts in the respective SCT hierarchies with regards to the quality measure of the percentage of primitive concepts and the frequency of modeling errors. There were 58% primitive concepts in the PL sample versus 62% in the control sample. The structural indicator of number of parents is shown to be statistically significant in its ability to identify concepts having a higher likelihood of inconsistencies in their hierarchical relationships. The absolute number of errors in the group of concepts having 1-3 parents was shown to be significantly lower than that for concepts with 4-6 parents and those with 7 or more parents based on Chi-squared analyses. CONCLUSION PL concepts suffer from the same issues as general SCT concepts, although to a slightly lesser extent, and do require further QA efforts to promote meaningful use of EHRs. To support such efforts, a structural indicator is shown to effectively ferret out potentially problematic concepts where those QA efforts should be focused.
Collapse
Affiliation(s)
- Ankur Agrawal
- Computer Science Department, New Jersey Institute of Technology, Newark, NJ 07102, USA.
| | | | | | | | | | | | | |
Collapse
|
14
|
Warrer P, Hansen EH, Juhl-Jensen L, Aagaard L. Using text-mining techniques in electronic patient records to identify ADRs from medicine use. Br J Clin Pharmacol 2012; 73:674-84. [PMID: 22122057 DOI: 10.1111/j.1365-2125.2011.04153.x] [Citation(s) in RCA: 68] [Impact Index Per Article: 5.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/18/2022] Open
Abstract
This literature review included studies that use text-mining techniques in narrative documents stored in electronic patient records (EPRs) to investigate ADRs. We searched PubMed, Embase, Web of Science and International Pharmaceutical Abstracts without restrictions from origin until July 2011. We included empirically based studies on text mining of electronic patient records (EPRs) that focused on detecting ADRs, excluding those that investigated adverse events not related to medicine use. We extracted information on study populations, EPR data sources, frequencies and types of the identified ADRs, medicines associated with ADRs, text-mining algorithms used and their performance. Seven studies, all from the United States, were eligible for inclusion in the review. Studies were published from 2001, the majority between 2009 and 2010. Text-mining techniques varied over time from simple free text searching of outpatient visit notes and inpatient discharge summaries to more advanced techniques involving natural language processing (NLP) of inpatient discharge summaries. Performance appeared to increase with the use of NLP, although many ADRs were still missed. Due to differences in study design and populations, various types of ADRs were identified and thus we could not make comparisons across studies. The review underscores the feasibility and potential of text mining to investigate narrative documents in EPRs for ADRs. However, more empirical studies are needed to evaluate whether text mining of EPRs can be used systematically to collect new information about ADRs.
Collapse
Affiliation(s)
- Pernille Warrer
- Department of Pharmacology and Pharmacotherapy, Section for Social Pharmacy, Faculty of Pharmaceutical Sciences, University of Copenhagen, Copenhagen, Denmark.
| | | | | | | |
Collapse
|
15
|
Hammersley V, Flint R, Pinnock H, Sheikh A. Developing and testing search strategies to identify patients with active seasonal allergic rhinitis in general practice. PRIMARY CARE RESPIRATORY JOURNAL : JOURNAL OF THE GENERAL PRACTICE AIRWAYS GROUP 2011; 20:71-4. [PMID: 21190011 DOI: 10.4104/pcrj.2010.00086] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
Abstract
AIM We sought to assess the accuracy of different search terms to identify individuals with active seasonal allergic rhinitis (SAR) in general practice. METHODS A reference search strategy was developed to identify patients with active SAR. This was applied through inspection of electronic health records of patients aged 15-45 years in a 10% random sample of a general practice database. Searches used Read codes and medication relating to SAR. Sensitivity, specificity, and positive and negative predictive values were calculated. RESULTS Using the reference search strategy, 54/1092 (4.9%) of 15-45 year-old patients had current SAR. Searching for drugs used in nasal allergy had the highest sensitivity (85%) and good specificity (86%). Searching for a recorded history of SAR (H170) in the last two years was more specific (100%) but this approach only had limited sensitivity (17%). CONCLUSIONS Electronic searches can be used to identify patients with current SAR, but the accuracy varies widely. Larger numbers of sufferers can be identified using broader search parameters, but with increasing numbers of false positives. In contrast, more focused search strategies give a smaller yield needing less cleaning of data to identify true positives, but there is an associated increase in the number of false negatives.
Collapse
Affiliation(s)
- Vicky Hammersley
- Allergy and Respiratory Research Group, Centre for Population Health Sciences: GP Section, The University of Edinburgh, Edinburgh, Scotland, United Kingdom.
| | | | | | | |
Collapse
|
16
|
Wedgeworth E, Powell A, Flohr C. Incidence of cancer in the context of atopic dermatitis. Br J Dermatol 2011; 164:896-7; authors' reply 897-8. [DOI: 10.1111/j.1365-2133.2011.10227.x] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
|
17
|
Kotz D, Simpson CR, Sheikh A. Incidence, prevalence, and trends of general practitioner-recorded diagnosis of peanut allergy in England, 2001 to 2005. J Allergy Clin Immunol 2011; 127:623-30.e1. [PMID: 21236479 DOI: 10.1016/j.jaci.2010.11.021] [Citation(s) in RCA: 75] [Impact Index Per Article: 5.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/05/2010] [Revised: 09/20/2010] [Accepted: 11/05/2010] [Indexed: 11/25/2022]
Abstract
BACKGROUND Previous descriptions of the epidemiology of peanut allergy have mainly been derived from small cross-sectional studies. OBJECTIVE To interrogate a large national research database to provide estimates for the incidence, prevalence, and trends of general practitioner (GP)-recorded diagnosis of peanut allergy in the English population. METHODS Version 10 of the QRESEARCH database was used with data from 2,958,366 patients who were registered with 422 United Kingdom general practices in the years 2001 to 2005. The primary outcome was a recording of clinician-diagnosed peanut allergy. RESULTS The age-sex standardized incidence rate of peanut allergy in 2005 was 0.08 per 1000 person-years (95% CI, 0.07-0.08), and the prevalence rate was 0.51 per 1000 patients (95% CI, 0.49-0.54). This translated into an estimated 4000 incident cases (95% CI, 3500-4600) and 25,700 prevalent cases (95% CI, 24,400-27,100) of GP-recorded diagnosis of peanut allergy in England in 2005. During the study period, the incidence rate of peanut allergy remained fairly stable, whereas the prevalence rate doubled. In those under 18 years of age, the crude lifetime prevalence rate was higher in males than females. A significant inverse relationship between prevalence and socioeconomic status was found. CONCLUSION These data on GP-recorded diagnosis of peanut allergy from a large general practice database suggest a much lower prevalence in peanut allergy than has hitherto been found. This difference may in part be explained by underrecording of peanut allergy in general practice. Further research is needed to assess the true frequency of peanut allergy in the population and whether there has been a true increase in recent years.
Collapse
Affiliation(s)
- Daniel Kotz
- Department of General Practice, CAPHRI School for Public Health and Primary Care, Maastricht University Medical Center, Maastricht, The Netherlands
| | | | | |
Collapse
|
18
|
Simpson CR, Sheikh A. Adrenaline is first line treatment for the emergency treatment of anaphylaxis. Resuscitation 2010; 81:641-2. [DOI: 10.1016/j.resuscitation.2010.04.002] [Citation(s) in RCA: 16] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/26/2023]
|
19
|
Simpson CR, Sheikh A. Trends in the epidemiology of asthma in England: a national study of 333,294 patients. J R Soc Med 2010; 103:98-106. [PMID: 20200181 PMCID: PMC3072257 DOI: 10.1258/jrsm.2009.090348] [Citation(s) in RCA: 89] [Impact Index Per Article: 6.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022] Open
Abstract
BACKGROUND Observations in the UK at the end of the last century found increasing trends of asthma prevalence over time. However, it has been reported that the number of new cases of asthma presenting to general practice has declined, especially among younger children. Aim To study national trends in the epidemiology of asthma. METHODS A cross-sectional observation analysis was performed using the QRESEARCH database, which is one of the world's largest national aggregated health databases containing records from 422 English practices yielding 30 million patient-years of observation. Data was extracted on 333,294 individuals with a recorded diagnosis of asthma and calculated annual age-sex standardized incidence, lifetime period prevalence and asthma-related prescribing rates for each year from 2001-2005. RESULTS The incidence rate of asthma decreased in all patients (2001: 6.9 (95% confidence intervals [CI] 6.8-7.0); 2005: 5.2 (95% CI 5.1-5.3) per 1000 patient-years, p<0.001), but most particularly in children under 5 years of age (-38.4%) where a decrease in the lifetime prevalence of asthma (-34.3%) was also found. However, the lifetime prevalence rate of asthma for adults increased (15-44 years: 23.3%; 45-64 years: 27.7%; >65 years: 21.5%) with an estimated 5,658,900 (95% CI 5,639,700-5,678,200) or approximately one person in nine having being diagnosed with asthma in England. The number of asthma-related prescriptions also increased over the study period (17.1%), such that in 2005 an estimated 32,577,300 (95%CI 32,531,600-32,623,000) prescriptions were issued. CONCLUSIONS This large national study reveals that the rate of new diagnoses of asthma appears to have passed its peak; however, the number of adults with a lifetime asthma diagnosis continues to rise. Whether these trends are genuine or are a result of the introduction of incentives and guidelines to improve identification and recording of asthma or changing diagnostic trends is a question with important public health implications and one, therefore, that warrants detailed further enquiry.
Collapse
Affiliation(s)
- Colin R Simpson
- Allergy & Respiratory Research Group, Centre for Population Health Sciences, University of Edinburgh, Medical School (Doorway 3) Teviot Place, Edinburgh EH8 9AG, UK.
| | | |
Collapse
|
20
|
Anandan C, Gupta R, Simpson CR, Fischbacher C, Sheikh A. Epidemiology and disease burden from allergic disease in Scotland: analyses of national databases. J R Soc Med 2009; 102:431-42. [PMID: 19797601 DOI: 10.1258/jrsm.2009.090027] [Citation(s) in RCA: 66] [Impact Index Per Article: 4.4] [Reference Citation Analysis] [Abstract] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022] Open
Abstract
BACKGROUND There are ongoing concerns about the quality of care provided to patients with allergic disorders in Scotland, but there are relatively few reliable data on the overall disease burden. We sought to: (1) describe the incidence, prevalence and outcome of allergic disorders; (2) estimate healthcare burden and costs; and (3) investigate ethnic variations in the epidemiology and outcomes from allergic disorders in Scotland. METHODS DATA SOURCES national surveys; primary care data; prescribing and medication data; hospital admissions data and mortality data. RESULTS Allergic disorders are extremely common in Scotland, affecting about one in three of the population at some time in their lives. Incidence was highest for eczema (10.2 per 1000 registered patients). Over 4% of all GP consultations and 1.5% of hospital admissions were for allergic disorders. There were 100 asthma deaths in 2005 (20 per million people). Direct healthcare costs for allergic disorders were an estimated pound130 million per year, the majority of these being incurred in primary care and related to asthma. CONCLUSIONS Allergic disorders are common in Scotland and given the very high proportion of children now affected, the high disease burden associated with these conditions is likely to persist for many decades.
Collapse
Affiliation(s)
- C Anandan
- Allergy & Respiratory Research Group, Centre for Population Health Sciences, University of Edinburgh, Edinburgh EH8 9DX, UK
| | | | | | | | | |
Collapse
|
21
|
Shahpori R, Doig C. Systematized Nomenclature of Medicine-Clinical Terms direction and its implications on critical care. J Crit Care 2009; 25:364.e1-9. [PMID: 19836194 DOI: 10.1016/j.jcrc.2009.08.008] [Citation(s) in RCA: 10] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/30/2009] [Revised: 07/25/2009] [Accepted: 08/22/2009] [Indexed: 10/20/2022]
Abstract
PURPOSE The aim of this study was to describe the new advancements in Systematized Nomenclature of Medicine-Clinical Terms (SNOMED-CT) terminology and its applicability to critical care documentation. MATERIALS AND METHODS Narrative review of existing literature published in indexed medical and health informatics journals and of gray literature available on the Internet and personal communication with authors and researchers engaged in SNOMED-CT projects related to critical care are conducted. RESULTS Systematized Nomenclature of Medicine-Clinical Terms is a system of comprehensive health and clinical terminology that covers most of the needs of health care documentation. It will potentially become the terminology of clinical enterprise and administrative information systems. Despite a ground swell of international support from health information management experts, the terminology remains unknown to most clinicians. We discuss the reasons why clinical familiarity with SNOMED-CT is an important prerequisite to proceeding with local or national electronic health records or clinical information systems. CONCLUSIONS We propose that SNOMED-CT is suitable for use in critical care; however, work is urgently required to validate the completeness of terminology and to determine clinicians' perceptions on the utility of such a standardized terminology for use in critical care clinical information systems.
Collapse
Affiliation(s)
- Reza Shahpori
- Department of Critical Care Medicine, Alberta Health Services, Calgary, Alberta, Canada.
| | | |
Collapse
|
22
|
Simpson CR, Newton J, Hippisley-Cox J, Sheikh A. Trends in the epidemiology and prescribing of medication for eczema in England. J R Soc Med 2009; 102:108-17. [PMID: 19297652 PMCID: PMC2746851 DOI: 10.1258/jrsm.2009.080211] [Citation(s) in RCA: 50] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022] Open
Abstract
BACKGROUND The prevalence of eczema, particularly in younger children, increased substantially over the second half of the 20th century. Analysis of primary healthcare data-sets offers the possibility to advance understanding about the changing epidemiology of eczema. AIM To investigate recent trends in the recorded incidence, lifetime prevalence, prescribing and consulting behaviour of patients with eczema in England. METHODS QRESEARCH is one of the world's largest national aggregated health databases containing the records of over nine million patients. We extracted data on all patients with a recorded diagnosis of eczema and calculated annual age-sex standardized incidence and lifetime period prevalence rates for each year from 2001-2005. We also analysed the consulting behaviour of these patients when compared with the rest of the QRESEARCH database population. The number of eczema prescriptions issued to people in England was also estimated. RESULTS The age-sex standardized incidence of eczema was 9.58 per 1000 person-years in 2001 and increased to 13.58 per 1000 patients in 2005 (p<0.001). By 2005, eczema affected an estimated 5,773,700 (95% confidence intervals [CI] 5,754,100-5,793,400) individuals in England, who, on average, consulted a general practitioner 4.02 (95% CI 4.01-4.03) times a year. During the study period, the number of eczema related prescriptions increased by 56.6% (95% CI 56.6-56.7), so by 2005 an estimated 13,690,300 (95% CI 13,643,200-13,737,600) prescriptions were issued. CONCLUSIONS Recorded incidence and lifetime prevalence of eczema in England continue to increase. Similar increases have also been observed in the estimated number of eczema prescriptions issued to the English population.
Collapse
Affiliation(s)
- Colin R Simpson
- Allergy & Respiratory Research Group, Centre for Population Health Sciences, University of Edinburgh, 20 West Richmond StreetEdinburgh EH8 9DX, UK
| | - John Newton
- Department of Public Health and Epidemiology, University of Manchester
| | | | - Aziz Sheikh
- Allergy & Respiratory Research Group, Centre for Population Health Sciences, University of Edinburgh, 20 West Richmond StreetEdinburgh EH8 9DX, UK
| |
Collapse
|
23
|
Simpson CR, Newton J, Hippisley-Cox J, Sheikh A. Incidence and prevalence of multiple allergic disorders recorded in a national primary care database. J R Soc Med 2009; 101:558-63. [PMID: 19029357 DOI: 10.1258/jrsm.2008.080196] [Citation(s) in RCA: 54] [Impact Index Per Article: 3.6] [Reference Citation Analysis] [Abstract] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022] Open
Abstract
BACKGROUND The co-existence of allergic conditions, food allergy, eczema, allergic rhinitis, asthma and anaphylaxis is thought to be increasing. Analysis of primary healthcare data-sets offers the possibility to advance understanding about the changing epidemiology of multiple allergic disorders. AIM To investigate recent trends in the recorded incidence, lifetime prevalence and consulting behaviour of patients with multiple allergic disorders in England. METHODS QRESEARCH is one of the world's largest national aggregated health databases containing the records of over nine million patients (including those who have left or died). Data were extracted on all patients with a recorded diagnosis of multiple allergic disorders, and annual age-sex standardized incidence and lifetime period prevalence rates were calculated for each year from 2001 to 2005. We also analysed the consulting behaviour of these patients when compared with the rest of the QRESEARCH database population. RESULTS The age-sex standardized incidence of multiple allergic disorders was 4.72 per 1000 person-years in 2001 and increased by 32.9% to 6.28 per 1000 patients in 2005 (p<0.001). Lifetime age-sex standardized prevalence of a recorded diagnosis of multiple allergic disorders increased by 48.9% from 31.00 per 1000 in 2001 to 46.16 in 2005 (p<0.001). Over this period, the mean consultation rate to general practitioners for these patients increased from 4.68 to 4.90 consultations per person per year. CONCLUSIONS Recorded incidence and lifetime prevalence of multiple allergic disorders in England have increased substantially in recent years.
Collapse
Affiliation(s)
- Colin R Simpson
- Department of General Practice and Primary Care, University of Aberdeen UK.
| | | | | | | |
Collapse
|