{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T17:40:50Z","timestamp":1792777250244,"version":"4.5.0"},"reference-count":20,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T00:00:00Z","timestamp":1792713600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"<jats:p>The Computational Barthel Index Tool (CBIT), originally developed using U.S. Department of Veterans Affairs (VA) data, predicts future dependency in activities of daily living up to one year in advance. This study externally validated CBIT in a large non-VA nursing home population and evaluated whether population-specific adaptation could recover performance following external transport. We analyzed SEER-Medicare linked data, including 843,836 patients and over 8 million Minimum Data Set (MDS) assessments. The predictor and outcome structures of the original CBIT models were reconstructed in the SEER-Medicare cohort. Pretrained models were evaluated without modification for discrimination and calibration at current, 3-, 6-, and 12-month prediction timeframes. Population-specific adaptation was evaluated using progressively larger subsets of SEER-Medicare training data and compared with model reconstruction in the SEER-Medicare. Under strict external validation, discrimination declined relative to the original VA models, particularly for longer-term predictions. For evaluation models, mean AUC decreased from 0.795 in the original models to 0.693 at current prediction, 0.595 at 3 months, 0.595 at 6 months, and 0.592 at 12 months. Re-evaluation models showed stronger but similarly declining external performance. Calibration error increased, particularly for evaluation models at longer timeframes. Subgroup analyses showed modest variation in discrimination across demographic and clinical groups. Population-specific adaptation substantially recovered discrimination, with performance improving as more SEER-Medicare training data were incorporated. Using the adaptation training set, adapted models achieved performance comparable to SEER-Medicare model reconstruction. External validation revealed substantial performance degradation when CBIT was transported to a non-VA population. Population-specific adaptation recovered much of this performance loss, supporting a structured approach to clinical ML transportability in which pretrained models are externally validated first, followed by adaptation when performance degradation is observed. Full model reconstruction remains an alternative when sufficient local data are available.<\/jats:p>","DOI":"10.1371\/journal.pdig.0001793","type":"journal-article","created":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T17:24:22Z","timestamp":1792776262000},"page":"e0001793","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["External validation and adaptation of the Computational Barthel Index Tool in a large nursing home cohort"],"prefix":"10.1371","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7950-2563","authenticated-orcid":true,"given":"Lemba Priscille","family":"Ngana","sequence":"first","affiliation":[{"name":"George Mason University","place":["Fairfax, Virginia, United States of America"],"department":["Department of Health Administration, Policy and Informatics"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Janusz","family":"Wojtusiak","sequence":"additional","affiliation":[{"name":"George Mason University","place":["Fairfax, Virginia, United States of America"],"department":["Department of Health Administration, Policy and Informatics"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atefehsadat","family":"Haghighathoseini","sequence":"additional","affiliation":[{"name":"George Mason University","place":["Fairfax, Virginia, United States of America"],"department":["Department of Health Administration, Policy and Informatics"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bhumi","family":"Patel","sequence":"additional","affiliation":[{"name":"George Mason University","place":["Fairfax, Virginia, United States of America"],"department":["Department of Health Administration, Policy and Informatics"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6038-1073","authenticated-orcid":true,"given":"Dharmi","family":"Desai","sequence":"additional","affiliation":[{"name":"George Mason University","place":["Fairfax, Virginia, United States of America"],"department":["Department of Health Administration, Policy and Informatics"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,23]]},"reference":[{"issue":"1","key":"pdig.0001793.ref001","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1186\/s12911-020-01368-8","article-title":"Computational Barthel Index: an automated tool for assessing and predicting activities of daily living among nursing home patients","volume":"21","author":"J Wojtusiak","year":"2021","journal-title":"BMC Med Inform Decis Mak"},{"issue":"10","key":"pdig.0001793.ref002","doi-asserted-by":"crossref","first-page":"2152","DOI":"10.1017\/S0144686X16000842","article-title":"Disability trends among older adults in ten European countries over 2004\u20132013, using various indicators and Survey of Health, Ageing and Retirement in Europe (SHARE) data","volume":"37","author":"G Verropoulou","year":"2016","journal-title":"Ageing Soc"},{"key":"pdig.0001793.ref003","doi-asserted-by":"crossref","DOI":"10.1111\/j.1532-5415.2000.tb03120.x","article-title":"Dying with cancer: patients\u2019 function, symptoms, and care preferences as death approaches","volume":"48","author":"EP McCarthy","year":"2000","journal-title":"J Am Geriatr Soc"},{"key":"pdig.0001793.ref004","doi-asserted-by":"crossref","first-page":"106288","DOI":"10.1016\/j.cmpb.2021.106288","article-title":"The importance of being external. methodological insights for the external validation of machine learning models in medicine","volume":"208","author":"F Cabitza","year":"2021","journal-title":"Comput Methods Programs Biomed"},{"key":"pdig.0001793.ref005","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1007\/978-3-030-85292-4_3","article-title":"Foundations of machine learning-based clinical prediction modeling: part ii-generalization and overfitting","volume":"134","author":"JM Kernbach","year":"2022","journal-title":"Acta Neurochir Suppl"},{"key":"pdig.0001793.ref006","first-page":"153","article-title":"Model validation and selection","author":"U Michelucci","year":"2024"},{"issue":"9","key":"pdig.0001793.ref007","doi-asserted-by":"crossref","first-page":"826","DOI":"10.1016\/S0895-4356(03)00207-5","article-title":"External validation is necessary in prediction research: a clinical example","volume":"56","author":"SE Bleeker","year":"2003","journal-title":"J Clin Epidemiol"},{"key":"pdig.0001793.ref008"},{"key":"pdig.0001793.ref009","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.ctrv.2017.10.006","article-title":"Disability in activities of daily living among adults with cancer: a systematic review and meta-analysis","volume":"61","author":"J Neo","year":"2017","journal-title":"Cancer Treat Rev"},{"issue":"3","key":"pdig.0001793.ref010","doi-asserted-by":"crossref","DOI":"10.1177\/0272989X12439755","article-title":"Adaptation of clinical prediction models for application in local settings","volume":"32","author":"TH Kappen","year":"2012","journal-title":"Med Decis Making"},{"issue":"2","key":"pdig.0001793.ref011","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1007\/s00586-019-06189-6","article-title":"External validation of a prediction model for pain and functional outcome after elective lumbar spinal fusion","volume":"29","author":"A Quddusi","year":"2020","journal-title":"Eur Spine J"},{"issue":"1","key":"pdig.0001793.ref012","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.jclinepi.2007.04.018","article-title":"Updating methods improved the performance of a clinical prediction model in new patients","volume":"61","author":"KJM Janssen","year":"2008","journal-title":"J Clin Epidemiol"},{"issue":"1","key":"pdig.0001793.ref013","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1093\/ckj\/sfaa188","article-title":"External validation of prognostic models: what, why, how, when and where?","volume":"14","author":"CL Ramspek","year":"2020","journal-title":"Clin Kidney J"},{"issue":"8","key":"pdig.0001793.ref014","doi-asserted-by":"crossref","first-page":"721","DOI":"10.1016\/S0895-4356(03)00120-3","article-title":"External validity of predictive models: a comparison of logistic regression, classification trees, and neural networks","volume":"56","author":"N Terrin","year":"2003","journal-title":"J Clin Epidemiol"},{"issue":"1","key":"pdig.0001793.ref015","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1186\/s12916-023-02779-w","article-title":"There is no such thing as a validated prediction model","volume":"21","author":"B Van Calster","year":"2023","journal-title":"BMC Med"},{"key":"pdig.0001793.ref016","doi-asserted-by":"crossref","DOI":"10.2196\/88406","article-title":"A Systematic evaluation of cohort selection criteria and their impact on machine learning model performance and demographic disparities in COVID-19 outcomes: cohort study","volume":"10","author":"A Haghighathoseini","year":"2026","journal-title":"JMIR Form Res"},{"key":"pdig.0001793.ref017","first-page":"413","article-title":"Which decisions affect cohort distribution in COVID-19 data analytics?","volume":"2024","author":"A Haghighathoseini","year":"2025","journal-title":"AMIA Annu Symp Proc"},{"issue":"55","key":"pdig.0001793.ref018","first-page":"3","article-title":"Updated overview of the SEER-medicare data: enhanced content and applications","volume":"2020","author":"L Enewold","year":"2020","journal-title":"J Natl Cancer Inst Monogr"},{"key":"pdig.0001793.ref019","doi-asserted-by":"crossref","unstructured":"Patel B, Ngana LP, Haghighathoseini A, Wojtusiak J. Influence of stratified variable encoding on quality of mortality prediction in systolic heart failure. In: 2025 International Conference on Machine Learning and Applications (ICMLA), 2025. pp. 996\u20139. https:\/\/doi.org\/10.1109\/icmla66185.2025.00150","DOI":"10.1109\/ICMLA66185.2025.00150"},{"issue":"1","key":"pdig.0001793.ref020","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1093\/geront\/gnv065","article-title":"Predicting functional decline and recovery for residents in veterans affairs nursing homes","volume":"56","author":"J Wojtusiak","year":"2016","journal-title":"Gerontologist"}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001793","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T17:24:26Z","timestamp":1792776266000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001793"}},"subtitle":[],"editor":[{"given":"Cleva","family":"Villanueva","sequence":"first","affiliation":[{"name":"Instituto Polit\u00e9cnico Nacional Escuela Superior de Medicina: Instituto Politecnico Nacional Escuela Superior de Medicina","place":["MEXICO"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,23]]},"references-count":20,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,23]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0001793","relation":{},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,23]]}}}