{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T13:34:22Z","timestamp":1777124062570,"version":"3.51.4"},"reference-count":86,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T00:00:00Z","timestamp":1736985600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T00:00:00Z","timestamp":1736985600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Machine learning has increasingly been applied to predict opioid-related harms due to its ability to handle complex interactions and generating actionable predictions. This review evaluated the types and quality of ML methods in opioid safety research, identifying 44 studies using supervised ML through searches of Ovid MEDLINE, PubMed and SCOPUS databases. Commonly predicted outcomes included postoperative opioid use (<jats:italic>n<\/jats:italic>\u2009=\u200915, 34%) opioid overdose (<jats:italic>n<\/jats:italic>\u2009=\u20098, 18%), opioid use disorder (<jats:italic>n<\/jats:italic>\u2009=\u20098, 18%) and persistent opioid use (<jats:italic>n<\/jats:italic>\u2009=\u20095, 11%) with varying definitions. Most studies (96%) originated from North America, with only 7% reporting external validation. Model performance was moderate to strong, but calibration was often missing (41%). Transparent reporting of model development was often incomplete, with key aspects such as calibration, imbalance correction, and handling of missing data absent. Infrequent external validation limited the generalizability of current models. Addressing these aspects is critical for transparency, interpretability, and future implementation of the results.<\/jats:p>","DOI":"10.1038\/s41746-024-01312-4","type":"journal-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T10:02:18Z","timestamp":1737021738000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["A systematic review of machine learning applications in predicting opioid associated adverse events"],"prefix":"10.1038","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0611-4389","authenticated-orcid":false,"given":"Carlos R.","family":"Ram\u00edrez Medina","sequence":"first","affiliation":[]},{"given":"Jose","family":"Benitez-Aurioles","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6687-3507","authenticated-orcid":false,"given":"David A.","family":"Jenkins","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1487-277X","authenticated-orcid":false,"given":"Meghna","family":"Jani","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,1,16]]},"reference":[{"key":"1312_CR1","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1146\/annurev-pharmtox-010617-052534","volume":"58","author":"P Skolnick","year":"2018","unstructured":"Skolnick, P. The Opioid Epidemic: Crisis and Solutions. Annu Rev. Pharm. Toxicol. 58, 143\u2013159 (2018).","journal-title":"Annu Rev. Pharm. Toxicol."},{"key":"1312_CR2","unstructured":"NIH National Institute on Drug Abuse. Drug Overdose Deaths: Facts and Figures. https:\/\/nida.nih.gov\/research-topics\/trends-statistics\/overdose-death-rates (2024)."},{"key":"1312_CR3","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1038\/s41380-020-0661-4","volume":"26","author":"ND Volkow","year":"2021","unstructured":"Volkow, N. D. & Blanco, C. The changing opioid crisis: development, challenges and opportunities. Mol. Psychiatry 26, 218\u2013233 (2021).","journal-title":"Mol. Psychiatry"},{"key":"1312_CR4","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1093\/pch\/pxac034","volume":"27","author":"EM Moore","year":"2022","unstructured":"Moore, E. M., Warshawski, T., Jassemi, S., Charles, G. & Vo, D. X. Time to act: Early experience suggests stabilization care offers a feasible approach for adolescents after acute life-threatening opioid toxicity. Paediatr. Child Health 27, 260\u2013264 (2022).","journal-title":"Paediatr. Child Health"},{"key":"1312_CR5","first-page":"43","volume":"34","author":"EA Gardner","year":"2022","unstructured":"Gardner, E. A., McGrath, S. A., Dowling, D. & Bai, D. The Opioid Crisis: Prevalence and Markets of Opioids. Forensic Sci. Rev. 34, 43\u201370 (2022).","journal-title":"Forensic Sci. Rev."},{"key":"1312_CR6","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1007\/s11096-020-01205-y","volume":"43","author":"A Alenezi","year":"2021","unstructured":"Alenezi, A., Yahyouche, A. & Paudyal, V. Current status of opioid epidemic in the United Kingdom and strategies for treatment optimisation in chronic pain. Int J. Clin. Pharm. 43, 318\u2013322 (2021).","journal-title":"Int J. Clin. Pharm."},{"key":"1312_CR7","doi-asserted-by":"publisher","first-page":"e1003270","DOI":"10.1371\/journal.pmed.1003270","volume":"17","author":"M Jani","year":"2020","unstructured":"Jani, M., Birlie Yimer, B., Sheppard, T., Lunt, M. & Dixon, W. G. Time trends and prescribing patterns of opioid drugs in UK primary care patients with non-cancer pain: A retrospective cohort study. PLOS Med. 17, e1003270 (2020).","journal-title":"PLOS Med."},{"key":"1312_CR8","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1016\/S0140-6736(21)02252-2","volume":"399","author":"K Humphreys","year":"2022","unstructured":"Humphreys, K. et al. Responding to the opioid crisis in North America and beyond: recommendations of the Stanford-Lancet Commission. Lancet 399, 555\u2013604 (2022).","journal-title":"Lancet"},{"key":"1312_CR9","doi-asserted-by":"publisher","first-page":"e13","DOI":"10.2196\/jmir.5876","volume":"19","author":"A Roehrs","year":"2017","unstructured":"Roehrs, A., da Costa, C. A., Righi, R. D. & de Oliveira, K. S. Personal Health Records: A Systematic Literature Review. J. Med Internet Res 19, e13 (2017).","journal-title":"J. Med Internet Res"},{"key":"1312_CR10","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-022-01577-x","volume":"22","author":"P Dhiman","year":"2022","unstructured":"Dhiman, P. et al. Methodological conduct of prognostic prediction models developed using machine learning in oncology: a systematic review. BMC Med. Res. Methodol. 22, 101 (2022).","journal-title":"BMC Med. Res. Methodol."},{"key":"1312_CR11","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-019-1426-2","volume":"17","author":"CJ Kelly","year":"2019","unstructured":"Kelly, C. J., Karthikesalingam, A., Suleyman, M., Corrado, G. & King, D. Key challenges for delivering clinical impact with artificial intelligence. BMC Med. 17, 195 (2019).","journal-title":"BMC Med."},{"key":"1312_CR12","doi-asserted-by":"publisher","first-page":"m1328","DOI":"10.1136\/bmj.m1328","volume":"369","author":"L Wynants","year":"2020","unstructured":"Wynants, L. et al. Prediction models for diagnosis and prognosis of covid-19: systematic review and critical appraisal. BMJ 369, m1328 (2020).","journal-title":"BMJ"},{"key":"1312_CR13","doi-asserted-by":"publisher","first-page":"59","DOI":"10.7326\/M19-2548","volume":"172","author":"F Wang","year":"2020","unstructured":"Wang, F., Kaushal, R. & Khullar, D. Should Health Care Demand Interpretable Artificial Intelligence or Accept \u201cBlack Box\u201d Medicine? Ann. Intern Med. 172, 59\u201360 (2020).","journal-title":"Ann. Intern Med."},{"key":"1312_CR14","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1145\/3233231","volume":"61","author":"Z Lipton","year":"2018","unstructured":"Lipton, Z. The mythos of model interpretability. Commun. ACM 61, 36\u201343 (2018).","journal-title":"Commun. ACM"},{"key":"1312_CR15","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1007\/s00701-024-05892-8","volume":"166","author":"O Ciobanu-Caraus","year":"2024","unstructured":"Ciobanu-Caraus, O. et al. A critical moment in machine learning in medicine: on reproducible and interpretable learning. Acta Neurochirurgica 166, 14 (2024).","journal-title":"Acta Neurochirurgica"},{"key":"1312_CR16","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1038\/s41746-022-00592-y","volume":"5","author":"G Varoquaux","year":"2022","unstructured":"Varoquaux, G. & Cheplygina, V. Machine learning for medical imaging: methodological failures and recommendations for the future. NPJ Digit Med. 5, 48 (2022).","journal-title":"NPJ Digit Med."},{"key":"1312_CR17","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.jclinepi.2019.02.004","volume":"110","author":"E Christodoulou","year":"2019","unstructured":"Christodoulou, E. et al. A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models. J. Clin. Epidemiol. 110, 12\u201322 (2019).","journal-title":"J. Clin. Epidemiol."},{"key":"1312_CR18","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1186\/s12911-020-1099-y","volume":"20","author":"B Sharma","year":"2020","unstructured":"Sharma, B. et al. Publicly available machine learning models for identifying opioid misuse from the clinical notes of hospitalized patients. BMC Med. Inform. Decision Making 20, 79 (2020).","journal-title":"BMC Med. Inform. Decision Making"},{"key":"1312_CR19","doi-asserted-by":"publisher","first-page":"e043964","DOI":"10.1136\/bmjopen-2020-043964","volume":"11","author":"V Sharma","year":"2021","unstructured":"Sharma, V., Kulkarni, V., Eurich, D. T., Kumar, L. & Samanani, S. Safe opioid prescribing: a prognostic machine learning approach to predicting 30-day risk after an opioid dispensation in Alberta, Canada. BMJ open 11, e043964 (2021).","journal-title":"BMJ open"},{"key":"1312_CR20","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1177\/07067437221114094","volume":"68","author":"YS Liu","year":"2023","unstructured":"Liu, Y. S. et al. Individualized prospective prediction of opioid use disorder. Can. J. Psychiatry 68, 54\u201363 (2023).","journal-title":"Can. J. Psychiatry"},{"key":"1312_CR21","doi-asserted-by":"publisher","first-page":"1225","DOI":"10.1177\/0960327121991910","volume":"40","author":"B Behnoush","year":"2021","unstructured":"Behnoush, B. et al. Machine learning algorithms to predict seizure due to acute tramadol poisoning. Hum. Exp. Toxicol. 40, 1225\u20131233 (2021).","journal-title":"Hum. Exp. Toxicol."},{"key":"1312_CR22","first-page":"44","volume":"165","author":"U Held","year":"2024","unstructured":"Held, U. et al. Development and internal validation of a prediction model for long-term opioid use-an analysis of insurance claims data. Pain 165, 44\u201353 (2024).","journal-title":"Pain"},{"key":"1312_CR23","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1016\/j.spinee.2019.12.019","volume":"20","author":"AV Karhade","year":"2020","unstructured":"Karhade, A. V. et al. Predicting prolonged opioid prescriptions in opioid-na\u00efve lumbar spine surgery patients. Spine J. 20, 888\u2013895 (2020).","journal-title":"Spine J."},{"key":"1312_CR24","doi-asserted-by":"publisher","first-page":"1764","DOI":"10.1016\/j.spinee.2019.06.002","volume":"19","author":"AV Karhade","year":"2019","unstructured":"Karhade, A. V. et al. Development of machine learning algorithms for prediction of prolonged opioid prescription after surgery for lumbar disc herniation. Spine J. 19, 1764\u20131771 (2019).","journal-title":"Spine J."},{"key":"1312_CR25","doi-asserted-by":"publisher","first-page":"898","DOI":"10.1007\/s11606-018-4335-8","volume":"33","author":"SL Calcaterra","year":"2018","unstructured":"Calcaterra, S. L. et al. Prediction of Future Chronic Opioid Use Among Hospitalized Patients. J. Gen. Intern. Med. 33, 898\u2013905 (2018).","journal-title":"J. Gen. Intern. Med."},{"key":"1312_CR26","doi-asserted-by":"publisher","first-page":"e455","DOI":"10.1016\/S2589-7500(22)00062-0","volume":"4","author":"W-H Lo-Ciganic","year":"2022","unstructured":"Lo-Ciganic, W.-H. et al. Developing and validating a machine-learning algorithm to predict opioid overdose in Medicaid beneficiaries in two US states: a prognostic modelling study. Lancet Digi. Health 4, e455\u2013e465 (2022).","journal-title":"Lancet Digi. Health"},{"key":"1312_CR27","doi-asserted-by":"publisher","first-page":"3589","DOI":"10.1109\/JBHI.2023.3265920","volume":"27","author":"S Fouladvand","year":"2023","unstructured":"Fouladvand, S. et al. A Comparative Effectiveness Study on Opioid Use Disorder Prediction Using Artificial Intelligence and Existing Risk Models. IEEE J. Biomed. Health Inform. 27, 3589\u20133598 (2023).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"1312_CR28","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1016\/j.amjsurg.2021.03.058","volume":"222","author":"J Hur","year":"2021","unstructured":"Hur, J. et al. Predicting postoperative opioid use with machine learning and insurance claims in opioid-na\u00efve patients. Am. J. Surg. 222, 659\u2013665 (2021).","journal-title":"Am. J. Surg."},{"key":"1312_CR29","doi-asserted-by":"publisher","DOI":"10.1002\/prp2.669","volume":"8","author":"Z Segal","year":"2020","unstructured":"Segal, Z. et al. Development of a machine learning algorithm for early detection of opioid use disorder. Pharmacol. Res. Perspect. 8, e00669 (2020).","journal-title":"Pharmacol. Res. Perspect."},{"key":"1312_CR30","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1016\/j.jclinepi.2021.01.009","volume":"132","author":"M van Smeden","year":"2021","unstructured":"van Smeden, M., Reitsma, J. B., Riley, R. D., Collins, G. S. & Moons, K. G. Clinical prediction models: diagnosis versus prognosis. J. Clin. Epidemiol. 132, 142\u2013145 (2021).","journal-title":"J. Clin. Epidemiol."},{"key":"1312_CR31","doi-asserted-by":"publisher","first-page":"762","DOI":"10.1007\/s00167-020-06421-7","volume":"30","author":"Y Lu","year":"2022","unstructured":"Lu, Y. et al. Machine-learning model successfully predicts patients at risk for prolonged postoperative opioid use following elective knee arthroscopy. Knee Surg. Sports Traumatol. Arthrosc. 30, 762\u2013772 (2022).","journal-title":"Knee Surg. Sports Traumatol. Arthrosc."},{"key":"1312_CR32","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/j.jor.2020.03.052","volume":"22","author":"A Katakam","year":"2020","unstructured":"Katakam, A., Karhade, A. V., Schwab, J. H., Chen, A. F. & Bedair, H. S. Development and validation of machine learning algorithms for postoperative opioid prescriptions after TKA. J. Orthop. 22, 95\u201399 (2020).","journal-title":"J. Orthop."},{"key":"1312_CR33","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1136\/rapm-2021-103299","volume":"47","author":"RA Gabriel","year":"2022","unstructured":"Gabriel, R. A. et al. Machine learning approach to predicting persistent opioid use following lower extremity joint arthroplasty. Reg. Anesthesia pain. Med. 47, 313\u2013319 (2022).","journal-title":"Reg. Anesthesia pain. Med."},{"key":"1312_CR34","doi-asserted-by":"publisher","first-page":"2573","DOI":"10.1007\/s00167-021-06812-4","volume":"30","author":"C Klemt","year":"2022","unstructured":"Klemt, C. et al. Machine learning algorithms predict extended postoperative opioid use in primary total knee arthroplasty. Knee Surg., Sports Traumatol., Arthrosc. 30, 2573\u20132581 (2022).","journal-title":"Knee Surg., Sports Traumatol., Arthrosc."},{"key":"1312_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2021.103725","volume":"116","author":"X Dong","year":"2021","unstructured":"Dong, X. et al. Predicting opioid overdose risk of patients with opioid prescriptions using electronic health records based on temporal deep learning. J. Biomed. Inform. 116, 103725 (2021).","journal-title":"J. Biomed. Inform."},{"key":"1312_CR36","first-page":"389","volume":"2019","author":"X Dong","year":"2019","unstructured":"Dong, X. et al. Machine Learning Based Opioid Overdose Prediction Using Electronic Health Records. AMIA Annu. Symp. Proc. 2019, 389\u2013398 (2019).","journal-title":"AMIA Annu. Symp. Proc."},{"key":"1312_CR37","doi-asserted-by":"publisher","DOI":"10.1016\/j.drugalcdep.2023.109856","volume":"246","author":"WF Gellad","year":"2023","unstructured":"Gellad, W. F. et al. Development and validation of an overdose risk prediction tool using prescription drug monitoring program data. Drug Alcohol Depend. 246, 109856 (2023).","journal-title":"Drug Alcohol Depend."},{"key":"1312_CR38","doi-asserted-by":"publisher","first-page":"e0248360","DOI":"10.1371\/journal.pone.0248360","volume":"16","author":"W-H Lo-Ciganic","year":"2021","unstructured":"Lo-Ciganic, W.-H. et al. Integrating human services and criminal justice data with claims data to predict risk of opioid overdose among Medicaid beneficiaries: A machine-learning approach. PloS one 16, e0248360 (2021).","journal-title":"PloS one"},{"key":"1312_CR39","doi-asserted-by":"publisher","first-page":"e190968","DOI":"10.1001\/jamanetworkopen.2019.0968","volume":"2","author":"W-H Lo-Ciganic","year":"2019","unstructured":"Lo-Ciganic, W.-H. et al. Evaluation of Machine-Learning Algorithms for Predicting Opioid Overdose Risk Among Medicare Beneficiaries With Opioid Prescriptions. JAMA Netw. Open 2, e190968 (2019).","journal-title":"JAMA Netw. Open"},{"key":"1312_CR40","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1093\/jamia\/ocab218","volume":"29","author":"M Ripperger","year":"2021","unstructured":"Ripperger, M. et al. Ensemble learning to predict opioid-related overdose using statewide prescription drug monitoring program and hospital discharge data in the state of Tennessee. J. Am. Med. Inform. Assoc.: JAMIA 29, 22\u201332 (2021).","journal-title":"J. Am. Med. Inform. Assoc.: JAMIA"},{"key":"1312_CR41","doi-asserted-by":"publisher","first-page":"e0241083","DOI":"10.1371\/journal.pone.0241083","volume":"15","author":"JW Sun","year":"2020","unstructured":"Sun, J. W. et al. Predicting overdose among individuals prescribed opioids using routinely collected healthcare utilization data. PloS one 15, e0241083 (2020).","journal-title":"PloS one"},{"key":"1312_CR42","doi-asserted-by":"publisher","first-page":"e059414","DOI":"10.1136\/bmjopen-2021-059414","volume":"12","author":"IE Annis","year":"2022","unstructured":"Annis, I. E., Jordan, R. & Thomas, K. C. Quickly identifying people at risk of opioid use disorder in emergency departments: trade-offs between a machine learning approach and a simple EHR flag strategy. BMJ open 12, e059414 (2022).","journal-title":"BMJ open"},{"key":"1312_CR43","doi-asserted-by":"publisher","DOI":"10.1177\/14604582231168826","volume":"29","author":"TJ Banks","year":"2023","unstructured":"Banks, T. J., Nguyen, T. D., Uhlmann, J. K., Nair, S. S. & Scherrer, J. F. Predicting opioid use disorder before and after the opioid prescribing peak in the United States: A machine learning tool using electronic healthcare records. Health Inform. J. 29, 14604582231168826 (2023).","journal-title":"Health Inform. J."},{"key":"1312_CR44","doi-asserted-by":"publisher","first-page":"1683","DOI":"10.1093\/jamia\/ocab043","volume":"28","author":"X Dong","year":"2021","unstructured":"Dong, X. et al. Identifying risk of opioid use disorder for patients taking opioid medications with deep learning. J. Am. Med. Inform. Assoc. : JAMIA 28, 1683\u20131693 (2021).","journal-title":"J. Am. Med. Inform. Assoc. : JAMIA"},{"key":"1312_CR45","first-page":"00093","volume":"5","author":"KN Kunze","year":"2021","unstructured":"Kunze, K. N., Polce, E. M., Alter, T. D. & Nho, S. J. Machine Learning Algorithms Predict Prolonged Opioid Use in Opioid-Na\u00efve Primary Hip Arthroscopy Patients. J. Am. Acad. Orthop. Surg. Glob. Res. Rev. 5, 00093\u201300098 (2021).","journal-title":"J. Am. Acad. Orthop. Surg. Glob. Res. Rev."},{"key":"1312_CR46","doi-asserted-by":"publisher","first-page":"839","DOI":"10.1016\/j.arthro.2021.08.009","volume":"38","author":"CF Grazal","year":"2022","unstructured":"Grazal, C. F. et al. A machine-learning algorithm to predict the likelihood of prolonged opioid use following arthroscopic hip surgery. Arthrosc. 38, 839\u2013847.e832 (2022).","journal-title":"Arthrosc."},{"key":"1312_CR47","doi-asserted-by":"publisher","first-page":"148","DOI":"10.37765\/ajmc.2021.88617","volume":"27","author":"W Gao","year":"2021","unstructured":"Gao, W., Leighton, C., Chen, Y., Jones, J. & Mistry, P. Predicting opioid use disorder and associated risk factors in a medicaid managed care population. Am. J. Managed Care 27, 148\u2013154 (2021).","journal-title":"Am. J. Managed Care"},{"key":"1312_CR48","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2022.104979","volume":"171","author":"A Kashyap","year":"2023","unstructured":"Kashyap, A., Callison-Burch, C. & Boland, M. R. A deep learning method to detect opioid prescription and opioid use disorder from electronic health records. Int. J. Med. Inform. 171, 104979 (2023).","journal-title":"Int. J. Med. Inform."},{"key":"1312_CR49","doi-asserted-by":"publisher","first-page":"e0235981","DOI":"10.1371\/journal.pone.0235981","volume":"15","author":"W-H Lo-Ciganic","year":"2020","unstructured":"Lo-Ciganic, W.-H. et al. Using machine learning to predict risk of incident opioid use disorder among fee-for-service Medicare beneficiaries: A prognostic study. PloS one 15, e0235981 (2020).","journal-title":"PloS one"},{"key":"1312_CR50","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/s10729-022-09605-4","volume":"25","author":"MV Bjarnadottir","year":"2022","unstructured":"Bjarnadottir, M. V., Anderson, D. B., Agarwal, R. & Nelson, D. A. Aiding the prescriber: developing a machine learning approach to personalized risk modeling for chronic opioid therapy amongst US Army soldiers. Health Care Manag. Sci. 25, 649\u2013665 (2022).","journal-title":"Health Care Manag. Sci."},{"key":"1312_CR51","doi-asserted-by":"publisher","unstructured":"Johnson, D. G. et al. Prescription quantity and duration predict progression from acute to chronic opioid use in opioid-naive Medicaid patients. PLOS Digit. Health 1, https:\/\/doi.org\/10.1371\/journal.pdig.0000075 (2022).","DOI":"10.1371\/journal.pdig.0000075"},{"key":"1312_CR52","doi-asserted-by":"publisher","first-page":"1511","DOI":"10.1002\/acr.25013","volume":"75","author":"JT Mohl","year":"2023","unstructured":"Mohl, J. T. et al. Predicting Chronic Opioid Use Among Patients With Osteoarthritis Using Electronic Health Record Data. Arthritis Care Res. 75, 1511\u20131518 (2023).","journal-title":"Arthritis Care Res."},{"key":"1312_CR53","doi-asserted-by":"publisher","first-page":"e2248559","DOI":"10.1001\/jamanetworkopen.2022.48559","volume":"5","author":"V Sharma","year":"2022","unstructured":"Sharma, V. et al. Development and Validation of a Machine Learning Model to Estimate Risk of Adverse Outcomes Within 30 Days of Opioid Dispensation. JAMA Netw. Open 5, e2248559 (2022).","journal-title":"JAMA Netw. Open"},{"key":"1312_CR54","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2021.742723","volume":"4","author":"R Vunikili","year":"2021","unstructured":"Vunikili, R. et al. Predictive modelling of susceptibility to substance abuse, mortality and drug-drug interactions in opioid patients. Front. Artif. Intell. 4, 742723 (2021).","journal-title":"Front. Artif. Intell."},{"key":"1312_CR55","first-page":"525","volume":"2017","author":"Z Che","year":"2017","unstructured":"Che, Z., St Sauver, J., Liu, H. & Liu, Y. Deep Learning Solutions for Classifying Patients on Opioid Use. AMIA \u2026 Annu. Symp. Proc. AMIA Symp. 2017, 525\u2013534 (2017).","journal-title":"AMIA \u2026 Annu. Symp. Proc. AMIA Symp."},{"key":"1312_CR56","doi-asserted-by":"publisher","DOI":"10.1186\/s13040-019-0193-0","volume":"12","author":"RJ Ellis","year":"2019","unstructured":"Ellis, R. J., Wang, Z., Genes, N. & Ma\u2019ayan, A. Predicting opioid dependence from electronic health records with machine learning. BioData Min. 12, 3 (2019).","journal-title":"BioData Min."},{"key":"1312_CR57","doi-asserted-by":"publisher","first-page":"908","DOI":"10.1007\/s11606-020-06405-w","volume":"36","author":"J Guo","year":"2021","unstructured":"Guo, J. et al. Predicting Mortality Risk After a Hospital or Emergency Department Visit for Nonfatal Opioid Overdose. J. Gen. Intern. Med. 36, 908\u2013915 (2021).","journal-title":"J. Gen. Intern. Med."},{"key":"1312_CR58","doi-asserted-by":"publisher","first-page":"00","DOI":"10.1097\/CORR.0000000000001251","volume":"478","author":"AB Anderson","year":"2020","unstructured":"Anderson, A. B. et al. Can Predictive Modeling Tools Identify Patients at High Risk of Prolonged Opioid Use after ACL Reconstruction? Clin. Orthop. Relat. Res. 478, 00\u20131618 (2020).","journal-title":"Clin. Orthop. Relat. Res."},{"key":"1312_CR59","doi-asserted-by":"publisher","first-page":"2272","DOI":"10.1016\/j.arth.2019.06.013","volume":"34","author":"AV Karhade","year":"2019","unstructured":"Karhade, A. V., Schwab, J. H. & Bedair, H. S. Development of Machine Learning Algorithms for Prediction of Sustained Postoperative Opioid Prescriptions After Total Hip Arthroplasty. J. Arthroplast. 34, 2272\u20132277.e2271 (2019).","journal-title":"J. Arthroplast."},{"key":"1312_CR60","doi-asserted-by":"publisher","first-page":"976","DOI":"10.1016\/j.spinee.2019.01.009","volume":"19","author":"AV Karhade","year":"2019","unstructured":"Karhade, A. V. et al. Machine learning for prediction of sustained opioid prescription after anterior cervical discectomy and fusion. Spine J. 19, 976\u2013983 (2019).","journal-title":"Spine J."},{"key":"1312_CR61","doi-asserted-by":"publisher","first-page":"1184","DOI":"10.1016\/j.spinee.2020.05.098","volume":"20","author":"Y Zhang","year":"2020","unstructured":"Zhang, Y. et al. A predictive-modeling based screening tool for prolonged opioid use after surgical management of low back and lower extremity pain. Spine J. 20, 1184\u20131195 (2020).","journal-title":"Spine J."},{"key":"1312_CR62","first-page":"358e","volume":"152","author":"AM Giladi","year":"2023","unstructured":"Giladi, A. M. et al. Patient-Reported Data Augment Prediction Models of Persistent Opioid Use after Elective Upper Extremity Surgery. Plast. Reconstruct. Surg. 152, 358e\u2013366e (2023).","journal-title":"Plast. Reconstruct. Surg."},{"key":"1312_CR63","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1097\/PRS.0000000000011099","volume":"54","author":"NB Baxter","year":"2024","unstructured":"Baxter, N. B. et al. Predicting persistent opioid use after hand surgery: a machine learning approach. Plast. Reconstr. Surg. 54, 573\u2013580 (2024).","journal-title":"Plast. Reconstr. Surg."},{"key":"1312_CR64","doi-asserted-by":"publisher","first-page":"1116","DOI":"10.1136\/ard-2023-224118","volume":"82","author":"Y-T Huang","year":"2023","unstructured":"Huang, Y.-T., Jenkins, D. A., Peek, N., Dixon, W. G. & Jani, M. High frequency of long-term opioid use among patients with rheumatic and musculoskeletal diseases initiating opioids for the first time. Ann. Rheumatic Dis. 82, 1116\u20131117 (2023).","journal-title":"Ann. Rheumatic Dis."},{"key":"1312_CR65","doi-asserted-by":"publisher","unstructured":"Chen, S.-F. et al. External validation of machine learning algorithm predicting prolonged opioid prescriptions in opioid-naive lumbar spine surgery patients using a Taiwanese cohort. J. Formosan Med. Associat. https:\/\/doi.org\/10.1016\/j.jfma.2023.06.027 (2023).","DOI":"10.1016\/j.jfma.2023.06.027"},{"key":"1312_CR66","doi-asserted-by":"publisher","first-page":"1119","DOI":"10.1016\/j.spinee.2022.02.009","volume":"22","author":"H-K Yen","year":"2022","unstructured":"Yen, H.-K. et al. A machine learning algorithm for predicting prolonged postoperative opioid prescription after lumbar disc herniation surgery. An external validation study using 1,316 patients from a Taiwanese cohort. Spine J. 22, 1119\u20131130 (2022).","journal-title":"Spine J."},{"key":"1312_CR67","doi-asserted-by":"publisher","first-page":"25","DOI":"10.4097\/kja.21209","volume":"75","author":"FS Nahm","year":"2022","unstructured":"Nahm, F. S. Receiver operating characteristic curve: overview and practical use for clinicians. Korean J. Anesthesiol. 75, 25\u201336 (2022).","journal-title":"Korean J. Anesthesiol."},{"key":"1312_CR68","doi-asserted-by":"publisher","unstructured":"Monaghan, T. F. et al. Foundational statistical principles in medical research: sensitivity, specificity, positive predictive value, and negative predictive value. Medicina (Kaunas) 57, https:\/\/doi.org\/10.3390\/medicina57050503 (2021).","DOI":"10.3390\/medicina57050503"},{"key":"1312_CR69","doi-asserted-by":"publisher","first-page":"1433","DOI":"10.1016\/j.jtcvs.2021.07.041","volume":"165","author":"F Movahedi","year":"2023","unstructured":"Movahedi, F., Padman, R. & Antaki, J. F. Limitations of receiver operating characteristic curve on imbalanced data: Assist device mortality risk scores. J. Thorac. Cardiovasc Surg. 165, 1433\u20131442.e1432 (2023).","journal-title":"J. Thorac. Cardiovasc Surg."},{"key":"1312_CR70","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1007\/s13534-023-00291-x","volume":"13","author":"J Shin","year":"2023","unstructured":"Shin, J. Feasibility of local interpretable model-agnostic explanations (LIME) algorithm as an effective and interpretable feature selection method: comparative fNIRS study. Biomed. Eng. Lett. 13, 689\u2013703 (2023).","journal-title":"Biomed. Eng. Lett."},{"key":"1312_CR71","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.1007\/s10822-020-00314-0","volume":"34","author":"R Rodr\u00edguez-P\u00e9rez","year":"2020","unstructured":"Rodr\u00edguez-P\u00e9rez, R. & Bajorath, J. Interpretation of machine learning models using shapley values: application to compound potency and multi-target activity predictions. J. Comput Aided Mol. Des. 34, 1013\u20131026 (2020).","journal-title":"J. Comput Aided Mol. Des."},{"key":"1312_CR72","unstructured":"Durgia, C. Using SHAP for Explainability \u2014 Understand these Limitations First, https:\/\/towardsdatascience.com\/using-shap-for-explainability-understand-these-limitations-first-1bed91c9d21 (2021)."},{"key":"1312_CR73","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijar.2023.109112","volume":"171","author":"X Huang","year":"2024","unstructured":"Huang, X. & Marques-Silva, J. On the failings of Shapley values for explainability. Int. J. Approx. Reason. 171, 109112 (2024).","journal-title":"Int. J. Approx. Reason."},{"key":"1312_CR74","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1126\/science.aax2342","volume":"366","author":"Z Obermeyer","year":"2019","unstructured":"Obermeyer, Z., Powers, B., Vogeli, C. & Mullainathan, S. Dissecting racial bias in an algorithm used to manage the health of populations. Science 366, 447\u2013453 (2019).","journal-title":"Science"},{"key":"1312_CR75","doi-asserted-by":"publisher","first-page":"1259","DOI":"10.1097\/j.pain.0000000000000516","volume":"157","author":"J Goesling","year":"2016","unstructured":"Goesling, J. et al. Trends and predictors of opioid use after total knee and total hip arthroplasty. Pain 157, 1259\u20131265 (2016).","journal-title":"Pain"},{"key":"1312_CR76","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1002\/pds.5595","volume":"32","author":"M Jani","year":"2023","unstructured":"Jani, M. et al. Take up to eight tablets per day\u201d: Incorporating free-text medication instructions into a transparent and reproducible process for preparing drug exposure data for pharmacoepidemiology. Pharmacoepidemiol Drug Saf. 32, 651\u2013660 (2023).","journal-title":"Pharmacoepidemiol Drug Saf."},{"key":"1312_CR77","doi-asserted-by":"crossref","unstructured":"Savcisens, G. et al. Using sequences of life-events to predict human lives. Nat. Comput. Sci. 1\u201314 (2023).","DOI":"10.21203\/rs.3.rs-2975478\/v1"},{"key":"1312_CR78","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-024-02043-5","volume":"48","author":"K Denecke","year":"2024","unstructured":"Denecke, K., May, R. & Rivera-Romero, O. Transformer Models in Healthcare: A Survey and Thematic Analysis of Potentials, Shortcomings and Risks. J. Med Syst. 48, 23 (2024).","journal-title":"J. Med Syst."},{"key":"1312_CR79","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107573","volume":"236","author":"C Garbin","year":"2023","unstructured":"Garbin, C., Marques, N. & Marques, O. Machine learning for predicting opioid use disorder from healthcare data: A systematic review. Comput. methods Prog. Biomed. 236, 107573 (2023).","journal-title":"Comput. methods Prog. Biomed."},{"key":"1312_CR80","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1177\/00031348231198112","volume":"90","author":"OS Emam","year":"2024","unstructured":"Emam, O. S. et al. Machine learning algorithms predict long-term postoperative opioid misuse: a systematic review. Am Surg. 90, 140\u2013151 (2024).","journal-title":"Am Surg."},{"key":"1312_CR81","doi-asserted-by":"publisher","first-page":"n71","DOI":"10.1136\/bmj.n71","volume":"372","author":"MJ Page","year":"2021","unstructured":"Page, M. J. et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ 372, n71 (2021).","journal-title":"BMJ"},{"key":"1312_CR82","unstructured":"Taylor S. et al. Dependence and withdrawal associated with some prescribed medicines: An evidence review. Public Health England (2019) https:\/\/assets.publishing.service.gov.uk\/media\/5fc658398fa8f5474c800149\/PHE_PMR_report_Dec2020.pdf."},{"key":"1312_CR83","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.jclinepi.2023.03.024","volume":"158","author":"CL Andaur Navarro","year":"2023","unstructured":"Andaur Navarro, C. L. et al. Systematic review finds \u201cspin\u201d practices and poor reporting standards in studies on machine learning-based prediction models. J. Clin. Epidemiol. 158, 99\u2013110 (2023).","journal-title":"J. Clin. Epidemiol."},{"key":"1312_CR84","doi-asserted-by":"publisher","first-page":"1196","DOI":"10.1007\/s00167-022-07181-2","volume":"31","author":"JA Pruneski","year":"2023","unstructured":"Pruneski, J. A. et al. Supervised machine learning and associated algorithms: applications in orthopedic surgery. Knee Surg. Sports Traumatol. Arthrosc. 31, 1196\u20131202 (2023).","journal-title":"Knee Surg. Sports Traumatol. Arthrosc."},{"key":"1312_CR85","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-023-01849-0","volume":"23","author":"BM Fernandez-Felix","year":"2023","unstructured":"Fernandez-Felix, B. M., L\u00f3pez-Alcalde, J., Roqu\u00e9, M., Muriel, A. & Zamora, J. CHARMS and PROBAST at your fingertips: a template for data extraction and risk of bias assessment in systematic reviews of predictive models. BMC Med. Res. Methodol. 23, 44 (2023).","journal-title":"BMC Med. Res. Methodol."},{"key":"1312_CR86","doi-asserted-by":"publisher","first-page":"429","DOI":"10.3233\/IDA-2002-6504","volume":"6","author":"N Japkowicz","year":"2002","unstructured":"Japkowicz, N. & Stephen, S. The class imbalance problem: A systematic study. Intell. Data Anal. 6, 429\u2013449 (2002).","journal-title":"Intell. Data Anal."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-024-01312-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-024-01312-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-024-01312-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T10:02:25Z","timestamp":1737021745000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-024-01312-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,16]]},"references-count":86,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1312"],"URL":"https:\/\/doi.org\/10.1038\/s41746-024-01312-4","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,16]]},"assertion":[{"value":"5 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"30"}}