{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T15:32:06Z","timestamp":1768404726531,"version":"3.49.0"},"reference-count":47,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2021,10,19]],"date-time":"2021-10-19T00:00:00Z","timestamp":1634601600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Harold Rogers Prescription Drug Monitoring Program","award":["2016-PM-BX-K002"],"award-info":[{"award-number":["2016-PM-BX-K002"]}]},{"name":"Comprehensive Opioid Abuse Site-based Program","award":["2018-PM-BX-0007"],"award-info":[{"award-number":["2018-PM-BX-0007"]}]},{"DOI":"10.13039\/100005196","name":"Bureau of Justice Assistance","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005196","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Department of Justice\u2019s Office of Justice Programs"},{"DOI":"10.13039\/100013173","name":"Bureau of Justice Statistics","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100013173","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100005289","name":"National Institute of Justice","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005289","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007264","name":"Office of Juvenile Justice and Delinquency Prevention","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007264","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100013138","name":"Office for Victims of Crime","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100013138","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000074","name":"U.S. Department of Justice","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000074","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,28]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Objective<\/jats:title><jats:p>To develop and validate algorithms for predicting 30-day fatal and nonfatal opioid-related overdose using statewide data sources including prescription drug monitoring program data, Hospital Discharge Data System data, and Tennessee (TN) vital records. Current overdose prevention efforts in TN rely on descriptive and retrospective analyses without prognostication.<\/jats:p><\/jats:sec><jats:sec><jats:title>Materials and Methods<\/jats:title><jats:p>Study data included 3 041 668 TN patients with 71 479 191 controlled substance prescriptions from 2012 to 2017. Statewide data and socioeconomic indicators were used to train, ensemble, and calibrate 10 nonparametric \u201cweak learner\u201d models. Validation was performed using area under the receiver operating curve (AUROC), area under the precision recall curve, risk concentration, and Spiegelhalter z-test statistic.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Within 30 days, 2574 fatal overdoses occurred after 4912 prescriptions (0.0069%) and 8455 nonfatal overdoses occurred after 19 460 prescriptions (0.027%). Discrimination and calibration improved after ensembling (AUROC: 0.79\u20130.83; Spiegelhalter P value: 0\u2013.12). Risk concentration captured 47\u201352% of cases in the top quantiles of predicted probabilities.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>Partitioning and ensembling enabled all study data to be used given computational limits and helped mediate case imbalance. Predicting risk at the prescription level can aggregate risk to the patient, provider, pharmacy, county, and regional levels. Implementing these models into Tennessee Department of Health systems might enable more granular risk quantification. Prospective validation with more recent data is needed.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Predicting opioid-related overdose risk at statewide scales remains difficult and models like these, which required a partnership between an academic institution and state health agency to develop, may complement traditional epidemiological methods of risk identification and inform public health decisions.<\/jats:p><\/jats:sec>","DOI":"10.1093\/jamia\/ocab218","type":"journal-article","created":{"date-parts":[[2021,10,9]],"date-time":"2021-10-09T12:01:58Z","timestamp":1633780918000},"page":"22-32","source":"Crossref","is-referenced-by-count":14,"title":["Ensemble learning to predict opioid-related overdose using statewide prescription drug monitoring program and hospital discharge data in the state of Tennessee"],"prefix":"10.1093","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9613-346X","authenticated-orcid":false,"given":"Michael","family":"Ripperger","sequence":"first","affiliation":[{"name":"Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, USA"}]},{"given":"Sarah C","family":"Lotspeich","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Vanderbilt University Medical Center, Nashville, Tennessee, USA"}]},{"given":"Drew","family":"Wilimitis","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, USA"}]},{"given":"Carrie E","family":"Fry","sequence":"additional","affiliation":[{"name":"Department of Health Policy, Vanderbilt University Medical Center, Nashville, Tennessee, USA"}]},{"given":"Allison","family":"Roberts","sequence":"additional","affiliation":[{"name":"Office of Informatics and Analytics, Tennessee Department of Health, Nashville, Tennessee, USA"}]},{"given":"Matthew","family":"Lenert","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, USA"}]},{"given":"Charlotte","family":"Cherry","sequence":"additional","affiliation":[{"name":"Office of Informatics and Analytics, Tennessee Department of Health, Nashville, Tennessee, USA"}]},{"given":"Sanura","family":"Latham","sequence":"additional","affiliation":[{"name":"Office of Informatics and Analytics, Tennessee Department of Health, Nashville, Tennessee, USA"}]},{"given":"Katelyn","family":"Robinson","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, USA"}]},{"given":"Qingxia","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, USA"},{"name":"Department of Biostatistics, Vanderbilt University Medical Center, Nashville, Tennessee, USA"}]},{"given":"Melissa L","family":"McPheeters","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, USA"},{"name":"Department of Health Policy, Vanderbilt University Medical Center, Nashville, Tennessee, USA"}]},{"given":"Ben","family":"Tyndall","sequence":"additional","affiliation":[{"name":"Office of Informatics and Analytics, Tennessee Department of Health, Nashville, Tennessee, USA"}]},{"given":"Colin G","family":"Walsh","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, USA"},{"name":"Department of Medicine, Vanderbilt University Medical Center, Nashville, Tennessee, USA"},{"name":"Department of Psychiatry, Vanderbilt University Medical Center, Nashville, Tennessee, USA"}]}],"member":"286","published-online":{"date-parts":[[2021,10,19]]},"reference":[{"key":"2021122823080653400_ocab218-B1","year":"2020"},{"issue":"5","key":"2021122823080653400_ocab218-B2","doi-asserted-by":"crossref","first-page":"422","DOI":"10.5811\/westjem.2012.7.12936","article-title":"Prescription drug monitoring programs and other interventions to combat prescription opioid abuse","volume":"13","author":"Chakravarthy","year":"2012","journal-title":"West J Emerg Med"},{"issue":"9","key":"2021122823080653400_ocab218-B3","doi-asserted-by":"crossref","first-page":"1214","DOI":"10.2105\/AJPH.2018.304532","article-title":"Opioid prescribing rates by congressional districts, United States, 2016","volume":"108","author":"Rolheiser","year":"2018","journal-title":"Am J Public Health"},{"key":"2021122823080653400_ocab218-B4","year":"2020"},{"key":"2021122823080653400_ocab218-B5","year":"2021"},{"key":"2021122823080653400_ocab218-B6","year":"2020"},{"issue":"7","key":"2021122823080653400_ocab218-B7","doi-asserted-by":"crossref","first-page":"1324","DOI":"10.1377\/hlthaff.2015.1496","article-title":"Implementation of prescription drug monitoring programs associated with reductions in opioid-related death rates","volume":"35","author":"Patrick","year":"2016","journal-title":"Health Aff (Millwood)"},{"issue":"2","key":"2021122823080653400_ocab218-B8","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1111\/add.13620","article-title":"Physician attitudes and experiences with Maryland\u2019s prescription drug monitoring program (PDMP)","volume":"112","author":"Lin","year":"2017","journal-title":"Addiction"},{"key":"2021122823080653400_ocab218-B9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.drugalcdep.2019.02.010","article-title":"Effects of mandatory prescription drug monitoring program (PDMP) use laws on prescriber registration and use and on risky prescribing","volume":"199","author":"Strickler","year":"2019","journal-title":"Drug Alcohol Depend"},{"key":"2021122823080653400_ocab218-B10","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1016\/j.drugpo.2019.10.001","article-title":"Prescription drug monitoring programs operational characteristics and fatal heroin poisoning","volume":"74","author":"Martins","year":"2019","journal-title":"Int J Drug Policy"},{"issue":"1","key":"2021122823080653400_ocab218-B11","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1097\/j.pain.0000000000001078","article-title":"High risk prescribing and opioid overdose: prospects for prescription drug monitoring program based proactive alerts","volume":"159","author":"Geissert","year":"2018","journal-title":"Pain"},{"key":"2021122823080653400_ocab218-B12","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.drugalcdep.2019.04.016","article-title":"A predictive risk model for nonfatal opioid overdose in a statewide population of buprenorphine patients","volume":"201","author":"Chang","year":"2019","journal-title":"Drug Alcohol Depend"},{"issue":"4","key":"2021122823080653400_ocab218-B13","doi-asserted-by":"crossref","first-page":"1917","DOI":"10.1073\/pnas.1905355117","article-title":"Predicting high-risk opioid prescriptions before they are given","volume":"117","author":"Hastings","year":"2020","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"11","key":"2021122823080653400_ocab218-B14","doi-asserted-by":"crossref","first-page":"1155","DOI":"10.1001\/jamapsychiatry.2020.1689","article-title":"Predictive modeling of opioid overdose using linked statewide medical and criminal justice data","volume":"77","author":"Saloner","year":"2020","journal-title":"JAMA Psychiatry"},{"key":"2021122823080653400_ocab218-B15","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1016\/j.drugalcdep.2018.05.004","article-title":"Sociodemographic factors, prescription history and opioid overdose deaths: a statewide analysis using linked PDMP and mortality data","volume":"190","author":"Nechuta","year":"2018","journal-title":"Drug Alcohol Depend"},{"key":"2021122823080653400_ocab218-B16","doi-asserted-by":"crossref","first-page":"105883","DOI":"10.1016\/j.ypmed.2019.105883","article-title":"Prescribing patterns before and after a non-fatal drug overdose using Tennessee\u2019s Controlled Substance Monitoring Database linked to hospital discharge data","volume":"130","author":"Krishnaswami","year":"2020","journal-title":"Prev Med"},{"key":"2021122823080653400_ocab218-B17","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.drugpo.2017.05.039","article-title":"Fatal and non-fatal opioid overdose in opioid dependent patients treated with methadone, buprenorphine or implant naltrexone","volume":"46","author":"Kelty","year":"2017","journal-title":"Int J Drug Policy"},{"issue":"6","key":"2021122823080653400_ocab218-B18","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1097\/ADM.0000000000000245","article-title":"Understanding risk factors for opioid overdose in clinical populations to inform treatment and policy","volume":"10","author":"Park","year":"2016","journal-title":"J Addict Med"},{"issue":"3","key":"2021122823080653400_ocab218-B19","doi-asserted-by":"crossref","first-page":"e190968","DOI":"10.1001\/jamanetworkopen.2019.0968","article-title":"Evaluation of machine-learning algorithms for predicting opioid overdose risk among medicare beneficiaries with opioid prescriptions","volume":"2","author":"Lo-Ciganic","year":"2019","journal-title":"JAMA Netw Open"},{"key":"2021122823080653400_ocab218-B20","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/j.drugalcdep.2015.05.035","article-title":"Drug use patterns predict risk of non-fatal overdose among street-involved youth in a Canadian setting","volume":"153","author":"Mitra","year":"2015","journal-title":"Drug Alcohol Depend"},{"key":"2021122823080653400_ocab218-B21","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1016\/j.addbeh.2018.03.010","article-title":"Fentanyl related overdose in Indianapolis: estimating trends using multilevel Bayesian models","volume":"86","author":"Phalen","year":"2018","journal-title":"Addict Behav"},{"key":"2021122823080653400_ocab218-B22","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1186\/s13040-019-0193-0","article-title":"Predicting opioid dependence from electronic health records with machine learning","volume":"12","author":"Ellis","year":"2019","journal-title":"BioData Min"},{"issue":"10","key":"2021122823080653400_ocab218-B23","doi-asserted-by":"crossref","first-page":"1646","DOI":"10.1007\/s11606-017-4288-3","article-title":"Prediction model for two-year risk of opioid overdose among patients prescribed chronic opioid therapy","volume":"33","author":"Glanz","year":"2018","journal-title":"J Gen Intern Med"},{"issue":"8","key":"2021122823080653400_ocab218-B24","doi-asserted-by":"crossref","first-page":"1566","DOI":"10.1111\/pme.12777","article-title":"Development of a risk index for serious prescription opioid-induced respiratory depression or overdose in Veterans\u2019 Health Administration Patients","volume":"16","author":"Zedler","year":"2015","journal-title":"Pain Med"},{"issue":"1","key":"2021122823080653400_ocab218-B25","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1093\/pm\/pnx009","article-title":"Validation of a screening risk index for serious prescription opioid-induced respiratory depression or overdose in a US Commercial Health Plan Claims Database","volume":"19","author":"Zedler","year":"2018","journal-title":"Pain Med"},{"issue":"3\u20134","key":"2021122823080653400_ocab218-B26","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1159\/000484667","article-title":"Using controlled substance receipt patterns to predict prescription overdose death","volume":"101","author":"Holt","year":"2018","journal-title":"Pharmacology"},{"issue":"6","key":"2021122823080653400_ocab218-B27","doi-asserted-by":"crossref","first-page":"e211","DOI":"10.1016\/j.amepre.2019.07.026","article-title":"Predicting opioid overdose deaths using prescription drug monitoring program data","volume":"57","author":"Ferris","year":"2019","journal-title":"Am J Prev Med"},{"issue":"7","key":"2021122823080653400_ocab218-B28","doi-asserted-by":"crossref","first-page":"980","DOI":"10.1001\/jamainternmed.2018.8757","article-title":"Use of opioid overdose deaths reported in one state\u2019s criminal justice, hospital, and prescription databases to identify risk of opioid fatalities","volume":"179","author":"Eisenberg","year":"2019","journal-title":"JAMA Intern Med"},{"key":"2021122823080653400_ocab218-B29","author":"Johnson","year":"2019"},{"issue":"12","key":"2021122823080653400_ocab218-B30","doi-asserted-by":"crossref","first-page":"2252","DOI":"10.2105\/AJPH.2013.301347","article-title":"Revisiting the role of the urban environment in substance use: the case of analgesic overdose fatalities","volume":"103","author":"Cerd\u00e1","year":"2013","journal-title":"Am J Public Health"},{"issue":"11","key":"2021122823080653400_ocab218-B31","doi-asserted-by":"crossref","first-page":"765","DOI":"10.7326\/M13-2946","article-title":"Neighborhood socioeconomic disadvantage and 30 day rehospitalizations: an analysis of Medicare data","volume":"161","author":"Kind","year":"2014","journal-title":"Ann Intern Med"},{"key":"2021122823080653400_ocab218-B32","year":"2021"},{"issue":"11","key":"2021122823080653400_ocab218-B33","doi-asserted-by":"crossref","first-page":"1722","DOI":"10.1093\/cid\/cix1079","article-title":"Tennessee\u2019s in-state vulnerability assessment for a \u201crapid dissemination of human immunodeficiency virus or hepatitis C virus infection\u201d event utilizing data about the opioid epidemic","volume":"66","author":"Rickles","year":"2018","journal-title":"Clin Infect Dis"},{"key":"2021122823080653400_ocab218-B34","year":"2016"},{"key":"2021122823080653400_ocab218-B35","year":"2020"},{"key":"2021122823080653400_ocab218-B36","first-page":"1","article-title":"A social vulnerability index for disaster management","volume":"8","author":"Flanagan","year":"2011","journal-title":"J Homel Secur Emerg Manag"},{"key":"2021122823080653400_ocab218-B37","author":"McPheeters","year":"2018"},{"key":"2021122823080653400_ocab218-B38","year":"2004"},{"issue":"1","key":"2021122823080653400_ocab218-B39","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1097\/EDE.0000000000001110","article-title":"Record linkage approaches using prescription drug monitoring program and mortality data for public health analyses and epidemiologic studies","volume":"31","author":"Nechuta","year":"2020","journal-title":"Epidemiology"},{"issue":"Pt 1","key":"2021122823080653400_ocab218-B40","first-page":"477","article-title":"VA National Drug File Reference Terminology: a cross-institutional content coverage study","volume":"107","author":"Brown","year":"2004","journal-title":"Stud Health Technol Inform"},{"key":"2021122823080653400_ocab218-B41","year":"2015"},{"key":"2021122823080653400_ocab218-B42","year":"2018"},{"key":"2021122823080653400_ocab218-B43","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v077.i01","article-title":"ranger: a fast implementation of random forests for high dimensional data in C++ and R","volume":"77","author":"Wright","year":"2017","journal-title":"J Stat Softw"},{"key":"2021122823080653400_ocab218-B44","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.jbi.2017.10.008","article-title":"Beyond discrimination: a comparison of calibration methods and clinical usefulness of predictive models of readmission risk","volume":"76","author":"Walsh","year":"2017","journal-title":"J Biomed Inform"},{"issue":"16","key":"2021122823080653400_ocab218-B45","doi-asserted-by":"crossref","first-page":"2567","DOI":"10.1002\/sim.1844","article-title":"Validation and updating of predictive logistic regression models: a study on sample size and shrinkage","volume":"23","author":"Steyerberg","year":"2004","journal-title":"Statist Med"},{"issue":"1","key":"2021122823080653400_ocab218-B46","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J R Stat Soc Ser B Methodol"},{"key":"2021122823080653400_ocab218-B47","doi-asserted-by":"crossref","first-page":"h2698","DOI":"10.1136\/bmj.h2698","article-title":"Benzodiazepine prescribing patterns and deaths from drug overdose among US veterans receiving opioid analgesics: case-cohort study","volume":"350","author":"Park","year":"2015","journal-title":"BMJ"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/29\/1\/22\/41955611\/ocab218.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/29\/1\/22\/41955611\/ocab218.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T16:30:24Z","timestamp":1725899424000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/29\/1\/22\/6400317"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,19]]},"references-count":47,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,10,19]]},"published-print":{"date-parts":[[2021,12,28]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocab218","relation":{},"ISSN":["1527-974X"],"issn-type":[{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,1,1]]},"published":{"date-parts":[[2021,10,19]]}}}