{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T09:47:06Z","timestamp":1778320026731,"version":"3.51.4"},"reference-count":33,"publisher":"Oxford University Press (OUP)","issue":"7","license":[{"start":{"date-parts":[[2021,3,13]],"date-time":"2021-03-13T00:00:00Z","timestamp":1615593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100000038","name":"Food and Drug Administration","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000016","name":"Department of Health and Human Services","doi-asserted-by":"publisher","award":["HHSF223201400030I"],"award-info":[{"award-number":["HHSF223201400030I"]}],"id":[{"id":"10.13039\/100000016","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000038","name":"Food and Drug Administration","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000038","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Department of Health and Human Services Mini-Sentinel","award":["HHSF22301007T"],"award-info":[{"award-number":["HHSF22301007T"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,14]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>Claims-based algorithms are used in the Food and Drug Administration Sentinel Active Risk Identification and Analysis System to identify occurrences of health outcomes of interest (HOIs) for medical product safety assessment. This project aimed to apply machine learning classification techniques to demonstrate the feasibility of developing a claims-based algorithm to predict an HOI in structured electronic health record (EHR) data.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>We used the 2015-2019 IBM MarketScan Explorys Claims-EMR Data Set, linking administrative claims and EHR data at the patient level. We focused on a single HOI, rhabdomyolysis, defined by EHR laboratory test results. Using claims-based predictors, we applied machine learning techniques to predict the HOI: logistic regression, LASSO (least absolute shrinkage and selection operator), random forests, support vector machines, artificial neural nets, and an ensemble method (Super Learner).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>The study cohort included 32 956 patients and 39 499 encounters. Model performance (positive predictive value [PPV], sensitivity, specificity, area under the receiver-operating characteristic curve) varied considerably across techniques. The area under the receiver-operating characteristic curve exceeded 0.80 in most model variations.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Discussion<\/jats:title>\n                  <jats:p>For the main Food and Drug Administration use case of assessing risk of rhabdomyolysis after drug use, a model with a high PPV is typically preferred. The Super Learner ensemble model without adjustment for class imbalance achieved a PPV of 75.6%, substantially better than a previously used human expert-developed model (PPV = 44.0%).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>It is feasible to use machine learning methods to predict an EHR-derived HOI with claims-based predictors. Modeling strategies can be adapted for intended uses, including surveillance, identification of cases for chart review, and outcomes research.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocab036","type":"journal-article","created":{"date-parts":[[2021,2,19]],"date-time":"2021-02-19T20:58:34Z","timestamp":1613768314000},"page":"1507-1517","source":"Crossref","is-referenced-by-count":20,"title":["Electronic phenotyping of health outcomes of interest using a linked claims-electronic health record database: Findings from a machine learning pilot project"],"prefix":"10.1093","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5853-7447","authenticated-orcid":false,"given":"Teresa B","family":"Gibson","sequence":"first","affiliation":[{"name":"Government Health and Human Services, IBM Watson Health, Bethesda, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael D","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Food and Drug Administration, Silver Spring, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Timothy","family":"Burrell","sequence":"additional","affiliation":[{"name":"Government Health and Human Services, IBM Watson Health, Bethesda, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frank","family":"Yoon","sequence":"additional","affiliation":[{"name":"Government Health and Human Services, IBM Watson Health, Bethesda, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jenna","family":"Wong","sequence":"additional","affiliation":[{"name":"Harvard\u00a0Medical School and Harvard Pilgrim Health Care Institute, Harvard Medical School, Boston, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sai","family":"Dharmarajan","sequence":"additional","affiliation":[{"name":"Office of Biostatistics, Center for Drug Evaluation and Research, Food and Drug Administration, Silver Spring, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rita","family":"Ouellet-Hellstrom","sequence":"additional","affiliation":[{"name":"Division of Epidemiology II, Office of Pharmacovigilance and Epidemiology, Office of Surveillance and Epidemiology, Center for Drug Evaluation and Research, Food and Drug Administration, Silver Spring, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Hua","sequence":"additional","affiliation":[{"name":"Food and Drug Administration, Silver Spring, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Ma","sequence":"additional","affiliation":[{"name":"Center for Drug Evaluation and Research, Food and Drug Administration, Silver Spring, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elande","family":"Baro","sequence":"additional","affiliation":[{"name":"Department of Population Medicine, Harvard Medical School and Harvard Pilgrim Health Care Institute, Boston, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sarah","family":"Bloemers","sequence":"additional","affiliation":[{"name":"Government Health and Human Services, IBM Watson Health, Bethesda, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cory","family":"Pack","sequence":"additional","affiliation":[{"name":"Government Health and Human Services, IBM Watson Health, Bethesda, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adee","family":"Kennedy","sequence":"additional","affiliation":[{"name":"Harvard\u00a0Medical School and Harvard Pilgrim Health Care Institute, Harvard Medical School, Boston, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sengwee","family":"Toh","sequence":"additional","affiliation":[{"name":"Harvard\u00a0Medical School and Harvard Pilgrim Health Care Institute, Harvard Medical School, Boston, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Ball","sequence":"additional","affiliation":[{"name":"Office of Surveillance and Epidemiology Center for Drug Evaluation and Research U.S. Food and Drug Administration, Silver Spring, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2021,3,13]]},"reference":[{"key":"2021071421225996100_ocab036-B1","doi-asserted-by":"crossref","first-page":"2091","DOI":"10.1056\/NEJMp1809643","article-title":"The FDA sentinel initiative \u2014 an evolving national resource","volume":"379","author":"Platt","year":"2018","journal-title":"N Engl J Med"},{"key":"2021071421225996100_ocab036-B2"},{"key":"2021071421225996100_ocab036-B3","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4614-7138-7","volume-title":"Introduction to Statistical Learning with Applications in R","author":"James","year":"2013"},{"issue":"10","key":"2021071421225996100_ocab036-B4","doi-asserted-by":"crossref","first-page":"e1915997","DOI":"10.1001\/jamanetworkopen.2019.15997","article-title":"Machine learning approaches to predict 6-month mortality among patients with cancer","volume":"2","author":"Parikh","year":"2019","journal-title":"JAMA Netw Open"},{"key":"2021071421225996100_ocab036-B5","doi-asserted-by":"crossref","first-page":"103363","DOI":"10.1016\/j.jbi.2019.103363","article-title":"Adapting electronic health records-derived phenotypes to claims data: Lessons learned in using limited clinical data for phenotyping","volume":"102","author":"Ostropolets","year":"2020","journal-title":"J Biomed Inform"},{"key":"2021071421225996100_ocab036-B6","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1007\/s40279-017-0689-z","article-title":"Perspectives on exertional rhabdomyolysis","volume":"47 (Suppl 1","author":"Rawson","year":"2017","journal-title":"Sports Med"},{"issue":"4","key":"2021071421225996100_ocab036-B7","doi-asserted-by":"crossref","first-page":"161","DOI":"10.5409\/wjcp.v6.i4.161","article-title":"Rhabdomyolysis with different etiologies in childhood","volume":"6","author":"Alaygut","year":"2017","journal-title":"World J Clin Pediatr"},{"issue":"8","key":"2021071421225996100_ocab036-B8","doi-asserted-by":"crossref","first-page":"845","DOI":"10.2169\/internalmedicine.50.4484","article-title":"Characteristics of drug-associated rhabdomyolysis: analysis of 8,610 cases reported to the U.S. Food and Drug Administration","volume":"50","author":"Ohima","year":"2011","journal-title":"Intern Med"},{"issue":"2","key":"2021071421225996100_ocab036-B9","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1186\/cc2978","article-title":"Bench-to-bedside review: rhabdomyolysis\u2014an overview for clinicians","volume":"9","author":"Huerta-Alard\u00edn","year":"2004","journal-title":"Crit Care"},{"issue":"3","key":"2021071421225996100_ocab036-B10","doi-asserted-by":"crossref","first-page":"S58","DOI":"10.1016\/j.jacl.2014.03.004","article-title":"An assessment by the Statin Muscle Task Force: 2014 update","volume":"8","author":"Rosenson","year":"2014","journal-title":"J Clin Lipidol"},{"issue":"6","key":"2021071421225996100_ocab036-B11","doi-asserted-by":"crossref","first-page":"743","DOI":"10.3892\/br.2015.500","article-title":"Diagnostic markers of acute myocardial infarction","volume":"3","author":"Mythili","year":"2015","journal-title":"Biomed Rep"},{"issue":"4","key":"2021071421225996100_ocab036-B12","doi-asserted-by":"crossref","first-page":"470","DOI":"10.1038\/clpt.2014.121","article-title":"Phenotype standardization for statin-induced myotoxicity","volume":"96","author":"Alfirevic","year":"2014","journal-title":"Clin Pharmacol Ther"},{"issue":"1","key":"2021071421225996100_ocab036-B13","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1186\/2110-5820-3-8","article-title":"An observational study on rhabdomyolysis in the intensive care unit. Exploring its risk factors and main complication: acute kidney injury","volume":"3","author":"El-Abdellati","year":"2013","journal-title":"Ann Intensive Care"},{"issue":"15","key":"2021071421225996100_ocab036-B14","doi-asserted-by":"crossref","first-page":"1580","DOI":"10.1001\/jama.2012.489","article-title":"Use of administrative data to estimate the incidence of statin-related rhabdomyolysis","volume":"307","author":"Floyd","year":"2012","journal-title":"JAMA"},{"issue":"4","key":"2021071421225996100_ocab036-B15","doi-asserted-by":"crossref","first-page":"303","DOI":"10.32098\/mltj.04.2013.11","article-title":"Rhabdomyolysis: the role of diagnostic and prognostic factors","volume":"3","author":"Keltz","year":"2014","journal-title":"Muscles Ligaments Tendons J"},{"issue":"1","key":"2021071421225996100_ocab036-B16","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1186\/s13054-016-1314-5","article-title":"Beyond muscle destruction: a systematic review of rhabdomyolysis for clinical practice","volume":"20","author":"Chavez","year":"2016","journal-title":"Crit Care"},{"key":"2021071421225996100_ocab036-B17","first-page":"272","article-title":"Rhabdomyolysis: a review of the literature","volume":"67","author":"Khan","year":"2009","journal-title":"Neth J Med"},{"issue":"6","key":"2021071421225996100_ocab036-B18","doi-asserted-by":"crossref","first-page":"793","DOI":"10.1002\/mus.24606","article-title":"Diagnostic evaluation of rhabdomyolysis","volume":"51","author":"Nance","year":"2015","journal-title":"Muscle Nerve"},{"issue":"1","key":"2021071421225996100_ocab036-B19","first-page":"58","article-title":"Rhabdomyolysis: pathogenesis, diagnosis, and treatment","volume":"15","author":"Torres","year":"2015","journal-title":"Ochsner J"},{"issue":"4","key":"2021071421225996100_ocab036-B20","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1071\/HC17051","article-title":"Association of aspartate aminotransferase in statin-induced rhabdomyolysis","volume":"9","author":"Ruan","year":"2017","journal-title":"J Prim Healthcare"},{"issue":"1","key":"2021071421225996100_ocab036-B21","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1136\/practneurol-2018-002008","article-title":"How to do it: investigate exertional rhabdomyolysis (or not)","volume":"19","author":"Fernandes","year":"2019","journal-title":"Pract Neurol"},{"issue":"1","key":"2021071421225996100_ocab036-B22","doi-asserted-by":"crossref","first-page":"86","DOI":"10.4103\/2249-4863.109962","article-title":"Acute renal failure due to rhabdomyolysis following a seizure","volume":"2","author":"Mishra","year":"2013","journal-title":"J Family Med Prim Care"},{"issue":"3","key":"2021071421225996100_ocab036-B23","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1186\/cc13897","article-title":"Acute kidney injury due to rhabdomyolysis and renal replacement therapy: a critical review","volume":"18","author":"Petejova","year":"2014","journal-title":"Crit Care"},{"issue":"6","key":"2021071421225996100_ocab036-B24","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1093\/ndt\/9.6.637","article-title":"Relationship between elevated creatine phosphokinase and the clinical spectrum of rhabdomyolysis","volume":"9","author":"Veenstra","year":"1994","journal-title":"Nephrol Dial Transplant"},{"issue":"3","key":"2021071421225996100_ocab036-B25","doi-asserted-by":"crossref","first-page":"215","DOI":"10.31486\/toj.17.0112","article-title":"Rhabdomyolysis: patterns, circumstances, and outcomes of patients presenting to the emergency department","volume":"18","author":"Knafl","year":"2018","journal-title":"Ochsner J"},{"issue":"6","key":"2021071421225996100_ocab036-B26","doi-asserted-by":"crossref","first-page":"763","DOI":"10.1093\/oxfordjournals.bja.a013590","article-title":"Serum myoglobin and creatine kinase following surgery","volume":"84","author":"Laurence","year":"2000","journal-title":"Br J Anaesth"},{"issue":"21","key":"2021071421225996100_ocab036-B27","doi-asserted-by":"crossref","first-page":"2585","DOI":"10.1001\/jama.292.21.2585","article-title":"Incidence of hospitalized rhabdomyolysis in patients treated with lipid-lowering drugs","volume":"292","author":"Graham","year":"2004","journal-title":"JAMA"},{"key":"2021071421225996100_ocab036-B28"},{"key":"2021071421225996100_ocab036-B29","article-title":"Sentinel Common Data Model"},{"key":"2021071421225996100_ocab036-B30","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"},{"issue":"9","key":"2021071421225996100_ocab036-B31","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","article-title":"Learning from imbalanced data","volume":"21","author":"He","year":"2009","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"4","key":"2021071421225996100_ocab036-B32","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1097\/EDE.0000000000001027","article-title":"Can hyperparameter tuning improve the performance of a Super Learner?: a case study","volume":"30","author":"Wong","year":"2019","journal-title":"Epidemiology"},{"key":"2021071421225996100_ocab036-B33","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1146\/annurev-biodatasci-080917-013315","article-title":"Advances in electronic phenotyping: from rule-based definitions to machine learning models","volume":"1","author":"Banda","year":"2018","journal-title":"Ann Rev Biomed Data Sci"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/28\/7\/1507\/38983326\/ocab036.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/28\/7\/1507\/38983326\/ocab036.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,14]],"date-time":"2021-07-14T21:24:36Z","timestamp":1626297876000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/28\/7\/1507\/6169465"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,13]]},"references-count":33,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2021,3,13]]},"published-print":{"date-parts":[[2021,7,14]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocab036","relation":{},"ISSN":["1527-974X"],"issn-type":[{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,7,1]]},"published":{"date-parts":[[2021,3,13]]}}}