{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T12:13:44Z","timestamp":1780402424464,"version":"3.54.1"},"reference-count":83,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T00:00:00Z","timestamp":1715731200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/100000038","name":"Food and Drug Administration","doi-asserted-by":"publisher","award":["75F40119F19002"],"award-info":[{"award-number":["75F40119F19002"]}],"id":[{"id":"10.13039\/100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000038","name":"Food and Drug Administration","doi-asserted-by":"publisher","award":["75F40119D10037"],"award-info":[{"award-number":["75F40119D10037"]}],"id":[{"id":"10.13039\/100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,8,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>To present a general framework providing high-level guidance to developers of computable algorithms for identifying patients with specific clinical conditions (phenotypes) through a variety of approaches, including but not limited to machine learning and natural language processing methods to incorporate rich electronic health record data.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>Drawing on extensive prior phenotyping experiences and insights derived from 3 algorithm development projects conducted specifically for this purpose, our team with expertise in clinical medicine, statistics, informatics, pharmacoepidemiology, and healthcare data science methods conceptualized stages of development and corresponding sets of principles, strategies, and practical guidelines for improving the algorithm development process.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We propose 5 stages of algorithm development and corresponding principles, strategies, and guidelines: (1) assessing fitness-for-purpose, (2) creating gold standard data, (3) feature engineering, (4) model development, and (5) model evaluation.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Discussion and Conclusion<\/jats:title>\n                  <jats:p>This framework is intended to provide practical guidance and serve as a basis for future elaboration and extension.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocae121","type":"journal-article","created":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T20:55:03Z","timestamp":1715720103000},"page":"1785-1796","source":"Crossref","is-referenced-by-count":18,"title":["A general framework for developing computable clinical phenotype algorithms"],"prefix":"10.1093","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8471-0928","authenticated-orcid":false,"given":"David S","family":"Carrell","sequence":"first","affiliation":[{"name":"Kaiser Permanente Washington Health Research Institute , Seattle, WA 98101, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James S","family":"Floyd","sequence":"additional","affiliation":[{"name":"Department of Medicine, School of Medicine, University of Washington , Seattle, WA 98195, United States"},{"name":"Department of Epidemiology, School of Public Health, University of Washington , Seattle, WA 98195, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Susan","family":"Gruber","sequence":"additional","affiliation":[{"name":"Putnam Data Sciences, LLC , Cambridge, MA 02139, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian L","family":"Hazlehurst","sequence":"additional","affiliation":[{"name":"Center for Health Research, Kaiser Permanente Northwest , Portland, OR 97227, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrick J","family":"Heagerty","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, School of Public Health, University of Washington , Seattle, WA 98195, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2968-2661","authenticated-orcid":false,"given":"Jennifer C","family":"Nelson","sequence":"additional","affiliation":[{"name":"Kaiser Permanente Washington Health Research Institute , Seattle, WA 98101, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian D","family":"Williamson","sequence":"additional","affiliation":[{"name":"Kaiser Permanente Washington Health Research Institute , Seattle, WA 98101, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1609-7420","authenticated-orcid":false,"given":"Robert","family":"Ball","sequence":"additional","affiliation":[{"name":"Office of Surveillance and Epidemiology, Center for Drug Evaluation and Research, United States Food and Drug Administration , Silver Spring, MD 20993, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,5,15]]},"reference":[{"issue":"1","key":"2024071907522224600_ocae121-B1","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1097\/EDE.0000000000001541","article-title":"Validation of acute pancreatitis among adults in an integrated healthcare system","volume":"34","author":"Floyd","year":"2023","journal-title":"Epidemiology"},{"issue":"3-4","key":"2024071907522224600_ocae121-B2","first-page":"84","article-title":"Optimizing identification of people living with HIV from electronic medical records: computable phenotype development and validation","volume":"60","author":"Liu","year":"2021","journal-title":"Methods Inf Med"},{"issue":"2","key":"2024071907522224600_ocae121-B3","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1093\/jamia\/ocx061","article-title":"Development and validation of an electronic medical record (EMR)-based computed phenotype of HIV-1 infection","volume":"25","author":"Paul","year":"2018","journal-title":"J Am Med Inform Assoc"},{"issue":"7","key":"2024071907522224600_ocae121-B4","doi-asserted-by":"crossref","first-page":"626","DOI":"10.1089\/aid.2013.0287","article-title":"Development and validation of an algorithm to identify patients newly diagnosed with HIV infection from electronic health records","volume":"30","author":"Goetz","year":"2014","journal-title":"AIDS Res Hum Retroviruses"},{"issue":"11","key":"2024071907522224600_ocae121-B5","doi-asserted-by":"crossref","first-page":"1205","DOI":"10.1002\/pds.3505","article-title":"Validation of anaphylaxis in the Food and Drug Administration's Mini-Sentinel","volume":"22","author":"Walsh","year":"2013","journal-title":"Pharmacoepidemiol Drug Saf"},{"issue":"10","key":"2024071907522224600_ocae121-B6","doi-asserted-by":"crossref","first-page":"1077","DOI":"10.1002\/pds.4645","article-title":"Evaluating automated approaches to anaphylaxis case classification using unstructured data from the FDA Sentinel System","volume":"27","author":"Ball","year":"2018","journal-title":"Pharmacoepidemiol Drug Saf"},{"issue":"2","key":"2024071907522224600_ocae121-B7","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1016\/j.jaci.2005.12.1303","article-title":"Second symposium on the definition and management of anaphylaxis: summary report\u2014Second National Institute of Allergy and Infectious Disease\/Food Allergy and Anaphylaxis Network symposium","volume":"117","author":"Sampson","year":"2006","journal-title":"J Allergy Clin Immunol"},{"key":"2024071907522224600_ocae121-B8","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.jbi.2017.07.012","article-title":"Natural language processing systems for capturing and standardizing unstructured clinical information: a systematic review","volume":"73","author":"Kreimeyer","year":"2017","journal-title":"J Biomed Inform"},{"issue":"12","key":"2024071907522224600_ocae121-B9","doi-asserted-by":"crossref","first-page":"3426","DOI":"10.1038\/s41596-019-0227-6","article-title":"High-throughput phenotyping with electronic medical record data using a common semi-supervised approach (PheCAP)","volume":"14","author":"Zhang","year":"2019","journal-title":"Nat Protoc"},{"issue":"5","key":"2024071907522224600_ocae121-B10","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1007\/s40264-022-01158-3","article-title":"Applying machine learning in distributed data networks for pharmacoepidemiologic and pharmacovigilance studies: opportunities, challenges, and considerations","volume":"45","author":"Wong","year":"2022","journal-title":"Drug Saf"},{"key":"2024071907522224600_ocae121-B11","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1016\/j.jbi.2014.06.007","article-title":"Design patterns for the development of electronic health record-driven phenotype extraction algorithms","volume":"51","author":"Rasmussen","year":"2014","journal-title":"J Biomed Inform"},{"issue":"6","key":"2024071907522224600_ocae121-B12","doi-asserted-by":"crossref","first-page":"1251","DOI":"10.1093\/jamia\/ocv070","article-title":"Review and evaluation of electronic health records-driven phenotype algorithm authoring tools for clinical and translational research","volume":"22","author":"Xu","year":"2015","journal-title":"J Am Med Inform Assoc"},{"issue":"2","key":"2024071907522224600_ocae121-B13","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1136\/amiajnl-2011-000456","article-title":"Importance of multi-modal approaches to effectively identify cataract cases from electronic health records","volume":"19","author":"Peissig","year":"2012","journal-title":"J Am Med Inform Assoc"},{"issue":"1","key":"2024071907522224600_ocae121-B14","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1186\/s12911-022-01759-z","article-title":"Under-specification as the source of ambiguity and vagueness in narrative phenotype algorithm definitions","volume":"22","author":"Yu","year":"2022","journal-title":"BMC Med Inform Decis Mak"},{"issue":"10","key":"2024071907522224600_ocae121-B15","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1038\/gim.2013.72","article-title":"The Electronic Medical Records and Genomics (eMERGE) Network: past, present, and future","volume":"15","author":"Gottesman","year":"2013","journal-title":"Genet Med"},{"issue":"4","key":"2024071907522224600_ocae121-B16","doi-asserted-by":"crossref","first-page":"763","DOI":"10.1016\/j.jbi.2012.01.009","article-title":"Building a robust, scalable and standards-driven infrastructure for secondary use of EHR data: the SHARPn project","volume":"45","author":"Rea","year":"2012","journal-title":"J Biomed Inform"},{"key":"2024071907522224600_ocae121-B17","author":"Office of the National Coordinator for Health Information Technology","year":"2011"},{"issue":"1","key":"2024071907522224600_ocae121-B18","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1186\/s12874-017-0420-7","article-title":"Pragmatic clinical trials embedded in healthcare systems: generalizable lessons from the NIH Collaboratory","volume":"17","author":"Weinfurt","year":"2017","journal-title":"BMC Med Res Methodol"},{"key":"2024071907522224600_ocae121-B19","author":"Mental Health Research Network"},{"key":"2024071907522224600_ocae121-B20","author":"HCSRN"},{"key":"2024071907522224600_ocae121-B21","doi-asserted-by":"crossref","first-page":"S45","DOI":"10.1542\/peds.2010-1722H","article-title":"The Vaccine Safety Datalink: a model for monitoring immunization safety","volume":"127 Suppl 1","author":"Baggs","year":"2011","journal-title":"Pediatrics"},{"issue":"6","key":"2024071907522224600_ocae121-B22","doi-asserted-by":"crossref","first-page":"498","DOI":"10.1056\/NEJMp1014427","article-title":"Developing the Sentinel System\u2014a national resource for evidence development","volume":"364","author":"Behrman","year":"2011","journal-title":"N Engl J Med"},{"issue":"3","key":"2024071907522224600_ocae121-B23","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1002\/cpt.320","article-title":"The FDA's Sentinel Initiative\u2014a comprehensive approach to medical product surveillance","volume":"99","author":"Ball","year":"2016","journal-title":"Clin Pharmacol Ther"},{"issue":"22","key":"2024071907522224600_ocae121-B24","doi-asserted-by":"crossref","first-page":"2091","DOI":"10.1056\/NEJMp1809643","article-title":"The FDA Sentinel Initiative\u2014an evolving national resource","volume":"379","author":"Platt","year":"2018","journal-title":"N Engl J Med"},{"key":"2024071907522224600_ocae121-B25","author":"Food and Drug Administration"},{"issue":"2","key":"2024071907522224600_ocae121-B26","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1093\/aje\/kwac182","article-title":"Improving methods of identifying anaphylaxis for medical product safety surveillance using natural language processing and machine learning","volume":"192","author":"Carrell","year":"2023","journal-title":"Am J Epidemiol"},{"key":"2024071907522224600_ocae121-B27","author":"Sentinel"},{"issue":"3","key":"2024071907522224600_ocae121-B28","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1093\/jamia\/ocad241","article-title":"Data-driven automated classification algorithms for acute health conditions: applying PheNorm to COVID-19 disease","volume":"31","author":"Smith","year":"2024","journal-title":"J Am Med Inform Assoc"},{"issue":"5","key":"2024071907522224600_ocae121-B29","doi-asserted-by":"crossref","first-page":"793","DOI":"10.1093\/jamia\/ocaa028","article-title":"Using and improving distributed data networks to generate actionable evidence: the case of real-world outcomes in the Food and Drug Administration's Sentinel system","volume":"27","author":"Brown","year":"2020","journal-title":"J Am Med Inform Assoc"},{"key":"2024071907522224600_ocae121-B30","author":"Sentinel"},{"key":"2024071907522224600_ocae121-B31","author":"Sentinel"},{"key":"2024071907522224600_ocae121-B32","author":"Klein","year":"2007"},{"key":"2024071907522224600_ocae121-B33","doi-asserted-by":"crossref","first-page":"e076460","DOI":"10.1136\/bmj-2023-076460","article-title":"Process guide for inferential studies using healthcare data from routine clinical practice to evaluate causal effects of drugs (PRINCIPLED): considerations from the FDA Sentinel Innovation Center","volume":"384","author":"Desai","year":"2024","journal-title":"BMJ"},{"key":"2024071907522224600_ocae121-B34","author":"Fang"},{"issue":"4","key":"2024071907522224600_ocae121-B35","doi-asserted-by":"crossref","first-page":"1219","DOI":"10.3390\/jcm9041219","article-title":"Diagnostic criteria for fibromyalgia: critical review and future perspectives","volume":"9","author":"Galvez-S\u00e1nchez","year":"2020","journal-title":"J Clin Med"},{"issue":"3","key":"2024071907522224600_ocae121-B36","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1097\/EDE.0000000000001330","article-title":"Identification and validation of anaphylaxis using electronic health data in a population-based setting","volume":"32","author":"Bann","year":"2021","journal-title":"Epidemiology"},{"issue":"3","key":"2024071907522224600_ocae121-B37","first-page":"86","article-title":"Impact of COVID-19 pandemic on chronic diseases care follow-up and current perspectives in low resource settings: a narrative review","volume":"13","author":"Fekadu","year":"2021","journal-title":"Int J Physiol Pathophysiol Pharmacol"},{"issue":"2","key":"2024071907522224600_ocae121-B38","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1097\/01.NPR.0000731572.91985.98","article-title":"Risk of misdiagnosis and delayed diagnosis with COVID-19: a syndemic approach","volume":"46","author":"Muhrer","year":"2021","journal-title":"Nurse Pract"},{"issue":"7","key":"2024071907522224600_ocae121-B39","doi-asserted-by":"crossref","first-page":"e0271049","DOI":"10.1371\/journal.pone.0271049","article-title":"The impact of the Covid-19 pandemic on the incidence of diseases and the provision of primary care: a registry-based study","volume":"17","author":"Van den Bulck","year":"2022","journal-title":"PLoS One"},{"key":"2024071907522224600_ocae121-B40","author":"Shi","year":"2024"},{"issue":"3","key":"2024071907522224600_ocae121-B41","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1111\/hsc.12198","article-title":"General practitioners' perspectives on primary care consultations for suicidal patients","volume":"24","author":"Saini","year":"2016","journal-title":"Health Soc Care Community"},{"issue":"4","key":"2024071907522224600_ocae121-B42","first-page":"229","article-title":"Screening for suicidal thoughts in primary care: the views of patients and general practitioners","volume":"5","author":"Bajaj","year":"2008","journal-title":"Ment Health Fam Med"},{"issue":"5","key":"2024071907522224600_ocae121-B43","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1016\/j.genhosppsych.2004.06.007","article-title":"Preventing suicide in primary care patients: the primary care physician's role","volume":"26","author":"Schulberg","year":"2004","journal-title":"Gen Hosp Psychiatry"},{"issue":"89","key":"2024071907522224600_ocae121-B44","first-page":"25049","article-title":"Guidance for industry: for the submission of chemistry, manufacturing and controls and establishment description information for human blood and blood components intended for transfusion or for further manufacture and for the completion of the form FDA 356h, \u201cApplication to market a new drug, biologic or an antibiotic drug for human use\u201d. Notice","volume":"64","author":"Food and Drug Administration, HHS","year":"1999","journal-title":"Fed Regist"},{"issue":"5","key":"2024071907522224600_ocae121-B45","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1097\/YCO.0000000000000351","article-title":"Stigma and substance use disorders: an international phenomenon","volume":"30","author":"Yang","year":"2017","journal-title":"Curr Opin Psychiatry"},{"issue":"1","key":"2024071907522224600_ocae121-B46","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1186\/s12913-018-3148-0","article-title":"Identifying diabetes cases from administrative data: a population-based validation study","volume":"18","author":"Lipscombe","year":"2018","journal-title":"BMC Health Serv Res"},{"issue":"4","key":"2024071907522224600_ocae121-B47","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1016\/1047-2797(94)00093-9","article-title":"Surveillance and ascertainment of cardiovascular events. The Cardiovascular Health Study","volume":"5","author":"Ives","year":"1995","journal-title":"Ann Epidemiol"},{"key":"2024071907522224600_ocae121-B48","author":"Brighton Collaboration"},{"issue":"6","key":"2024071907522224600_ocae121-B49","doi-asserted-by":"crossref","first-page":"710","DOI":"10.1093\/aje\/kwk052","article-title":"Relaxing the rule of ten events per variable in logistic and Cox regression","volume":"165","author":"Vittinghoff","year":"2007","journal-title":"Am J Epidemiol"},{"issue":"1","key":"2024071907522224600_ocae121-B50","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1136\/gutjnl-2012-302779","article-title":"Classification of acute pancreatitis\u20142012: revision of the Atlanta classification and definitions by international consensus","volume":"62","author":"Banks","year":"2013","journal-title":"Gut"},{"issue":"1","key":"2024071907522224600_ocae121-B51","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.jclinepi.2010.03.002","article-title":"Guidelines for Reporting Reliability and Agreement Studies (GRRAS) were proposed","volume":"64","author":"Kottner","year":"2011","journal-title":"J Clin Epidemiol"},{"issue":"2","key":"2024071907522224600_ocae121-B52","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1016\/j.jbi.2008.08.010","article-title":"Research electronic data capture (REDCap)\u2014a metadata-driven methodology and workflow process for providing translational research informatics support","volume":"42","author":"Harris","year":"2009","journal-title":"J Biomed Inform"},{"issue":"1","key":"2024071907522224600_ocae121-B53","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1093\/eurjcn\/zvab104","article-title":"Research Electronic Data Capture (REDCap): tackling data collection, management, storage, and privacy challenges","volume":"21","author":"Van Bulck","year":"2022","journal-title":"Eur J Cardiovasc Nurs"},{"key":"2024071907522224600_ocae121-B54","author":"Github"},{"issue":"5","key":"2024071907522224600_ocae121-B55","doi-asserted-by":"crossref","first-page":"429","DOI":"10.3233\/IDA-2002-6504","article-title":"The class imbalance problem: a systematic study","volume":"6","author":"Japkowicz","year":"2002","journal-title":"IDA"},{"issue":"e1","key":"2024071907522224600_ocae121-B56","doi-asserted-by":"crossref","first-page":"e147","DOI":"10.1136\/amiajnl-2012-000896","article-title":"Validation of electronic medical record-based phenotyping algorithms: results and lessons learned from the eMERGE network","volume":"20","author":"Newton","year":"2013","journal-title":"J Am Med Inform Assoc"},{"issue":"4","key":"2024071907522224600_ocae121-B57","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1016\/j.ijmedinf.2007.04.008","article-title":"Distributed cognition: an alternative model of cognition for medical informatics","volume":"77","author":"Hazlehurst","year":"2008","journal-title":"Int J Med Inform"},{"key":"2024071907522224600_ocae121-B58","first-page":"284","article-title":"How the ICU follows orders: care delivery as a complex activity system","volume":"2003","author":"Hazlehurst","year":"2003","journal-title":"AMIA Annu Symp Proc"},{"issue":"5","key":"2024071907522224600_ocae121-B59","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1016\/j.jbi.2007.02.001","article-title":"Distributed cognition in the heart room: how situation awareness arises from coordinated communications during cardiac surgery","volume":"40","author":"Hazlehurst","year":"2007","journal-title":"J Biomed Inform"},{"key":"2024071907522224600_ocae121-B60","author":"Shekhar","year":"2018"},{"issue":"1","key":"2024071907522224600_ocae121-B61","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1093\/jamia\/ocx111","article-title":"Enabling phenotypic big data with PheNorm","volume":"25","author":"Yu","year":"2018","journal-title":"J Am Med Inform Assoc"},{"key":"2024071907522224600_ocae121-B62","author":"Press","year":"2016"},{"issue":"5","key":"2024071907522224600_ocae121-B63","doi-asserted-by":"crossref","first-page":"993","DOI":"10.1093\/jamia\/ocv034","article-title":"Toward high-throughput phenotyping: unbiased automated feature extraction and selection from knowledge sources","volume":"22","author":"Yu","year":"2015","journal-title":"J Am Med Inform Assoc"},{"issue":"1","key":"2024071907522224600_ocae121-B64","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1177\/0272989X11400418","article-title":"Natural language processing improves identification of colorectal cancer testing in the electronic medical record","volume":"32","author":"Denny","year":"2012","journal-title":"Med Decis Making"},{"key":"2024071907522224600_ocae121-B65","author":"Kaiser Permanente Washington Health Research Institute","year":"2024"},{"key":"2024071907522224600_ocae121-B66","author":"MedlinePlus","year":"2022"},{"key":"2024071907522224600_ocae121-B67","author":"Fernandez","year":"2022"},{"issue":"2","key":"2024071907522224600_ocae121-B68","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1002\/pds.4919","article-title":"The use of natural language processing to identify vaccine-related anaphylaxis at five health care systems in the Vaccine Safety Datalink","volume":"29","author":"Yu","year":"2020","journal-title":"Pharmacoepidemiol Drug Saf"},{"issue":"10","key":"2024071907522224600_ocae121-B69","doi-asserted-by":"crossref","first-page":"1359","DOI":"10.1093\/jamia\/ocy056","article-title":"PheProb: probabilistic phenotyping using diagnosis codes to improve power for genetic association studies","volume":"25","author":"Sinnott","year":"2018","journal-title":"J Am Med Inform Assoc"},{"issue":"11","key":"2024071907522224600_ocae121-B70","doi-asserted-by":"crossref","first-page":"1255","DOI":"10.1093\/jamia\/ocz066","article-title":"High-throughput multimodal automated phenotyping (MAP) with application to PheWAS","volume":"26","author":"Liao","year":"2019","journal-title":"J Am Med Inform Assoc"},{"issue":"3","key":"2024071907522224600_ocae121-B71","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1093\/jamia\/ocad241","article-title":"Data-driven automated classification algorithms for acute health conditions: applying PheNorm to COVID-19 disease","volume":"31","author":"Smith","year":"2024","journal-title":"J Am Med Inform Assoc"},{"key":"2024071907522224600_ocae121-B72","author":"Github"},{"key":"2024071907522224600_ocae121-B73","author":"Github"},{"key":"2024071907522224600_ocae121-B74","author":"Github"},{"key":"2024071907522224600_ocae121-B75","first-page":"1276"},{"key":"2024071907522224600_ocae121-B76","doi-asserted-by":"crossref","first-page":"Article25","DOI":"10.2202\/1544-6115.1309","article-title":"Super learner","volume":"6","author":"van der Laan","year":"2007","journal-title":"Stat Appl Genet Mol Biol"},{"key":"2024071907522224600_ocae121-B77","author":"van der Laan","year":"2004"},{"key":"2024071907522224600_ocae121-B78","author":"Davis","year":"2006"},{"issue":"1","key":"2024071907522224600_ocae121-B79","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1097\/EDE.0b013e3181c30fb2","article-title":"Assessing the performance of prediction models: a framework for traditional and novel measures","volume":"21","author":"Steyerberg","year":"2010","journal-title":"Epidemiology"},{"key":"2024071907522224600_ocae121-B80","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1007\/978-3-662-44851-9_15","article-title":"Optimal thresholding of classifiers to maximize F1 measure","volume":"8725","author":"Lipton","year":"2014","journal-title":"Mach Learn Knowl Discov Databases"},{"issue":"6","key":"2024071907522224600_ocae121-B81","doi-asserted-by":"crossref","first-page":"515","DOI":"10.7326\/0003-4819-130-6-199903160-00016","article-title":"Assessing the generalizability of prognostic information","volume":"130","author":"Justice","year":"1999","journal-title":"Ann Intern Med"},{"issue":"4","key":"2024071907522224600_ocae121-B82","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1007\/s40471-014-0027-z","article-title":"Misclassification in administrative claims data: quantifying the impact on treatment effect estimates","volume":"1","author":"Funk","year":"2014","journal-title":"Curr Epidemiol Rep"},{"issue":"4","key":"2024071907522224600_ocae121-B83","doi-asserted-by":"crossref","first-page":"843","DOI":"10.1093\/biomet\/86.4.843","article-title":"Bias and efficiency loss due to misclassified responses in binary regression","volume":"86","author":"Neuhaus","year":"1999","journal-title":"Biometrika"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/advance-article-pdf\/doi\/10.1093\/jamia\/ocae121\/57687277\/ocae121.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/31\/8\/1785\/58591200\/ocae121.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/31\/8\/1785\/58591200\/ocae121.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T07:52:56Z","timestamp":1721375576000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/31\/8\/1785\/7674873"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,15]]},"references-count":83,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2024,5,15]]},"published-print":{"date-parts":[[2024,8,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocae121","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,8]]},"published":{"date-parts":[[2024,5,15]]}}}