{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T21:08:27Z","timestamp":1773349707700,"version":"3.50.1"},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T00:00:00Z","timestamp":1773187200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000092","name":"National Library of Medicine","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000051","name":"National Human Genome Research Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000051","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Biomedical Informatics"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.jbi.2026.105012","type":"journal-article","created":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:26:16Z","timestamp":1773246376000},"page":"105012","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Community medical centers struggle to produce well-calibrated clinical prediction models: Data augmentation can help"],"prefix":"10.1016","volume":"177","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4443-8541","authenticated-orcid":false,"given":"Katherine E.","family":"Brown","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3040-5175","authenticated-orcid":false,"given":"Bradley A.","family":"Malin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0792-8867","authenticated-orcid":false,"given":"Sharon E.","family":"Davis","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"6","key":"10.1016\/j.jbi.2026.105012_b1","doi-asserted-by":"crossref","first-page":"756","DOI":"10.1001\/jamainternmed.2021.0240","article-title":"Physicians, probabilities, and populations\u2014Estimating the likelihood of disease for common clinical scenarios","volume":"181","author":"Manrai","year":"2021","journal-title":"JAMA Intern. Med."},{"issue":"11","key":"10.1016\/j.jbi.2026.105012_b2","doi-asserted-by":"crossref","first-page":"e848","DOI":"10.1093\/cid\/ciaa1576","article-title":"Predicting antibiotic resistance in hospitalized patients by applying machine learning to electronic medical records","volume":"72","author":"Lewin-Epstein","year":"2021","journal-title":"Clin. Infect. Dis."},{"issue":"12","key":"10.1016\/j.jbi.2026.105012_b3","doi-asserted-by":"crossref","first-page":"2670","DOI":"10.1093\/jamia\/ocab211","article-title":"Predicting next-day discharge via electronic health record access logs","volume":"28","author":"Zhang","year":"2021","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.jbi.2026.105012_b4","doi-asserted-by":"crossref","DOI":"10.1038\/tp.2015.182","article-title":"Predicting early psychiatric readmission with natural language processing of narrative discharge summaries","volume":"6","author":"Rumshisky","year":"2016","journal-title":"Transl. Psychiatry"},{"issue":"1","key":"10.1016\/j.jbi.2026.105012_b5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41746-024-01037-4","article-title":"Why do probabilistic clinical models fail to transport between sites","volume":"7","author":"Lasko","year":"2024","journal-title":"Npj Digit. Med."},{"key":"10.1016\/j.jbi.2026.105012_b6","series-title":"Accuracy of the epic sepsis prediction model in a regional health system","author":"Bennett","year":"2019"},{"issue":"8","key":"10.1016\/j.jbi.2026.105012_b7","doi-asserted-by":"crossref","first-page":"1040","DOI":"10.1001\/jamainternmed.2021.3333","article-title":"The epic sepsis model falls short-the importance of external validation","volume":"181","author":"Habib","year":"2021","journal-title":"JAMA Intern. Med."},{"key":"10.1016\/j.jbi.2026.105012_b8","series-title":"Journal of the American Medical Informatics Association","first-page":"1052","article-title":"Calibration drift in regression and machine learning models for acute kidney injury","volume":"vol. 24","author":"Davis","year":"2017"},{"key":"10.1016\/j.jbi.2026.105012_b9","unstructured":"S.E. Davis, T.A. Lasko, G. Chen, M.E. Matheny, Calibration drift among regression and machine learning models for hospital mortality, in: AMIA Annual Symposium Proceedings, vol. 2017, 2018, p. 625."},{"issue":"5","key":"10.1016\/j.jbi.2026.105012_b10","doi-asserted-by":"crossref","first-page":"811","DOI":"10.1093\/jamia\/ocaf038","article-title":"Large language models are less effective at clinical prediction tasks than locally trained machine learning models","volume":"32","author":"Brown","year":"2025","journal-title":"J. Am. Med. Inform. Assoc."},{"issue":"19","key":"10.1016\/j.jbi.2026.105012_b11","doi-asserted-by":"crossref","first-page":"4230","DOI":"10.1002\/sim.9025","article-title":"Minimum sample size for external validation of a clinical prediction model with a binary outcome","volume":"40","author":"Riley","year":"2021","journal-title":"Stat. Med."},{"issue":"7","key":"10.1016\/j.jbi.2026.105012_b12","doi-asserted-by":"crossref","first-page":"1280","DOI":"10.1002\/sim.9275","article-title":"Minimum sample size calculations for external validation of a clinical prediction model with a time-to-event outcome","volume":"41","author":"Riley","year":"2022","journal-title":"Stat. Med."},{"issue":"12","key":"10.1016\/j.jbi.2026.105012_b13","doi-asserted-by":"crossref","first-page":"1448","DOI":"10.1093\/jamia\/ocz127","article-title":"A nonparametric updating method to correct clinical prediction model drift","volume":"26","author":"Davis","year":"2019","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.jbi.2026.105012_b14","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.jclinepi.2016.05.007","article-title":"Geographic and temporal validity of prediction models: different approaches were useful to examine model performance","volume":"79","author":"Austin","year":"2016","journal-title":"J. Clin. Epidemiol."},{"key":"10.1016\/j.jbi.2026.105012_b15","series-title":"Nanyang Technological University","first-page":"315","article-title":"Development of synthetic patient data to support urban planning for public health","author":"Liu","year":"2020"},{"key":"10.1016\/j.jbi.2026.105012_b16","doi-asserted-by":"crossref","DOI":"10.2196\/52615","article-title":"Generating synthetic electronic health record data using generative adversarial networks: Tutorial","volume":"3","author":"Yan","year":"2024","journal-title":"JMIR AI"},{"key":"10.1016\/j.jbi.2026.105012_b17","unstructured":"N. Jackson, C. Yan, B. Malin, Enhancement of Fairness in AI for Chest X-ray Classification, in: AMIA Annual Symposium Proceedings, vol. 2024, 2025."},{"issue":"1","key":"10.1016\/j.jbi.2026.105012_b18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41746-025-01438-z","article-title":"Improving medical machine learning models with generative balancing for equity and excellence","volume":"8","author":"Theodorou","year":"2025","journal-title":"Npj Digit. Med."},{"issue":"7","key":"10.1016\/j.jbi.2026.105012_b19","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.2105\/AJPH.93.7.1137","article-title":"Area deprivation and widening inequalities in US mortality, 1969\u20131998","volume":"93","author":"Singh","year":"2003","journal-title":"Am. J. Public Health"},{"key":"10.1016\/j.jbi.2026.105012_b20","unstructured":"Rural Health Grants Eligibility Analyzer, URL https:\/\/data.hrsa.gov\/tools\/rural-health."},{"issue":"5","key":"10.1016\/j.jbi.2026.105012_b21","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1177\/1062860617753063","article-title":"Area deprivation index (ADI) predicts readmission risk at an urban teaching hospital","volume":"33","author":"Hu","year":"2018","journal-title":"Am. J. Med. Qual. : Off. J. Am. Coll. Med. Qual."},{"issue":"3","key":"10.1016\/j.jbi.2026.105012_b22","first-page":"61","article-title":"Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods","volume":"10","author":"Platt","year":"1999","journal-title":"Adv. Large Margin Classif."},{"key":"10.1016\/j.jbi.2026.105012_b23","unstructured":"About HRSA \u2014 HRSA, URL https:\/\/www.hrsa.gov\/about."},{"issue":"3","key":"10.1016\/j.jbi.2026.105012_b24","article-title":"LACE+ index: Extension of a validated index to predict early death or urgent readmission after hospital discharge using administrative data","volume":"6","author":"van Walraven","year":"2012","journal-title":"Open Med."},{"issue":"1","key":"10.1016\/j.jbi.2026.105012_b25","doi-asserted-by":"crossref","DOI":"10.1038\/sdata.2018.178","article-title":"The eICU collaborative research database, a freely available multi-center database for critical care research","volume":"5","author":"Pollard","year":"2018","journal-title":"Sci. Data"},{"key":"10.1016\/j.jbi.2026.105012_b26","unstructured":"A.V. Dorogush, V. Ershov, A. Gulin, CatBoost: Gradient boosting with categorical features support."},{"key":"10.1016\/j.jbi.2026.105012_b27","unstructured":"F. Benali, D. Bod\u00e9n\u00e8s, N. Labroche, C. de Runz, MTCopula: Synthetic complex data generation using copula, in: 23rd International Workshop on Design, Optimization, Languages and Analytical Processing of Big Data (DOLAP), 2021, pp. 51\u201360."},{"issue":"11","key":"10.1016\/j.jbi.2026.105012_b28","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Commun. ACM"},{"key":"10.1016\/j.jbi.2026.105012_b29","series-title":"Advances in Neural Information Processing Systems","article-title":"Modeling tabular data using conditional GAN","author":"Xu","year":"2019"},{"issue":"6","key":"10.1016\/j.jbi.2026.105012_b30","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1001\/jamainternmed.2022.7182","article-title":"Factors associated with variability in the performance of a proprietary sepsis prediction model across 9 networked hospitals in the US","volume":"183","author":"Lyons","year":"2023","journal-title":"JAMA Intern. Med."},{"key":"10.1016\/j.jbi.2026.105012_b31","article-title":"Gaps in artificial intelligence research for rural health in the united states: A scoping review","author":"Brown","year":"2025","journal-title":"J. Am. Med. Inform. Assoc."},{"issue":"11","key":"10.1016\/j.jbi.2026.105012_b32","doi-asserted-by":"crossref","DOI":"10.2196\/31337","article-title":"Predicting COVID-19\u2013related health care resource utilization across a statewide patient population: Model development study","volume":"23","author":"Kasturi","year":"2021","journal-title":"J. Med. Internet Res."},{"issue":"11","key":"10.1016\/j.jbi.2026.105012_b33","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0277479","article-title":"Predicting length of stay using machine learning for total joint replacements performed at a rural community hospital","volume":"17","author":"Sridhar","year":"2022","journal-title":"PLoS One"},{"issue":"1","key":"10.1016\/j.jbi.2026.105012_b34","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1097\/TA.0b013e318240507b","article-title":"Comparison of massive blood transfusion predictive models in the rural setting","volume":"72","author":"Krumrei","year":"2012","journal-title":"J. Trauma Acute Care Surg."},{"issue":"11","key":"10.1016\/j.jbi.2026.105012_b35","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0259538","article-title":"Predicting increases in COVID-19 incidence to identify locations for targeted testing in West Virginia: A machine learning enhanced approach","volume":"16","author":"Price","year":"2021","journal-title":"Plos One"},{"issue":"4","key":"10.1016\/j.jbi.2026.105012_b36","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2021.4622","article-title":"Algorithmovigilance\u2014advancing methods to analyze and monitor artificial intelligence\u2013driven health care for effectiveness and equity","volume":"4","author":"Embi","year":"2021","journal-title":"JAMA Netw. Open"},{"key":"10.1016\/j.jbi.2026.105012_b37","unstructured":"V. Mahajan, V.K. Venugopal, M. Murugavel, H. Mahajan, The algorithmic audit: Working with vendors to validate radiology-AI algorithms\u2014how we do it, Acad. Radiol.."},{"key":"10.1016\/j.jbi.2026.105012_b38","unstructured":"K. Kunjan, T. Toscos, A. Turkcan, B.N. Doebbeling, A multidimensional data warehouse for community health centers, in: AMIA Annual Symposium Proceedings, vol. 2015, 2015, p. 1976."},{"issue":"6","key":"10.1016\/j.jbi.2026.105012_b39","doi-asserted-by":"crossref","first-page":"899","DOI":"10.1007\/s10552-022-01571-0","article-title":"An informatics infrastructure to catalyze cancer control research and practice","volume":"33","author":"Rose","year":"2022","journal-title":"Cancer Causes & Control."},{"issue":"1","key":"10.1016\/j.jbi.2026.105012_b40","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1093\/jamia\/ocab233","article-title":"Building capacity of community health centers to overcome data challenges with the development of an agile COVID-19 public health registry: A multistate quality improvement effort","volume":"29","author":"Romero","year":"2022","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.jbi.2026.105012_b41","series-title":"StatPearls","article-title":"Health insurance portability and accountability act (hipaa) compliance","author":"Edemekong","year":"2025"},{"issue":"1","key":"10.1016\/j.jbi.2026.105012_b42","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s41666-020-00082-4","article-title":"Federated learning for healthcare informatics","volume":"5","author":"Xu","year":"2021","journal-title":"J. Heal. Inform. Res."},{"key":"10.1016\/j.jbi.2026.105012_b43","series-title":"FedSyn: Synthetic data generation using federated learning","author":"Behera","year":"2022"},{"key":"10.1016\/j.jbi.2026.105012_b44","article-title":"The \u201cAll of Us\u201d research program","year":"2019","journal-title":"New Engl. J. Med."},{"issue":"5","key":"10.1016\/j.jbi.2026.105012_b45","doi-asserted-by":"crossref","first-page":"845","DOI":"10.1093\/jamia\/ocaf039","article-title":"Emerging algorithmic bias: fairness drift as the next dimension of model maintenance and sustainability","volume":"32","author":"Davis","year":"2025","journal-title":"J. Am. Med. Inform. Assoc."}],"container-title":["Journal of Biomedical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1532046426000365?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1532046426000365?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T10:34:58Z","timestamp":1773311698000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1532046426000365"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":45,"alternative-id":["S1532046426000365"],"URL":"https:\/\/doi.org\/10.1016\/j.jbi.2026.105012","relation":{},"ISSN":["1532-0464"],"issn-type":[{"value":"1532-0464","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Community medical centers struggle to produce well-calibrated clinical prediction models: Data augmentation can help","name":"articletitle","label":"Article Title"},{"value":"Journal of Biomedical Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jbi.2026.105012","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"105012"}}