{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T21:07:51Z","timestamp":1789592871212,"version":"build-2803163510"},"reference-count":55,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Aging"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Early mortality after long-term care facility (LTCF) admission is common; yet, prognostic tools are often derived from Western minimum dataset-based cohorts or require hospital electronic health record linkages that are unavailable at intake in many LTCFs. There is also limited evidence on explainable, admission-feasible machine learning\u2013based prognostication in Asian LTCF settings.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n The aim of the study is to develop and temporally externally validate an interpretable machine learning model for predicting 6-month all-cause mortality among older adults newly admitted to LTCFs in Taiwan using routinely collected LTCF assessment data.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n We conducted a retrospective cohort study using the JUBO Long-Term Care Database, a nationwide private administrative registry covering 636 LTCFs (37.4% of the national LTCFs) in Taiwan. We included residents with first-time LTCF admission and prespecified nonoverlapping cohorts for temporal validation: development (January 1, 2020, to December 31, 2023; n=23,901) and external validation (January 1 to December 31, 2024; n=6216). The outcome measure was death within 180 days of admission. We compared a nonlinear ensemble model (hybrid of extreme gradient boosting and random forest [HybridXGBRF]) with 7 other algorithms, including tree-based and linear benchmarks. Discrimination (area under the receiver operating characteristic curve [AUROC]), classification metrics (accuracy, precision, recall, and\n F<\/jats:italic>\n 1<\/jats:sub>\n ), and calibration (Brier score and calibration plots) were assessed. Model interpretability was examined using Shapley Additive Explanations.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n In the development cohort, 5272 of 23,901 (22.1%) residents died within 180 days. In the 2024 temporal validation cohort, 1781 of 6216 (28.7%) residents died. In internal cross-validation, HybridXGBRF had the highest AUROC among the evaluated models (0.89, 95% CI 0.88\u20100.89). In temporal validation, HybridXGBRF maintained strong discrimination (AUROC 0.90, 95% CI 0.89\u20100.91), with an accuracy of 0.85 and an\n F<\/jats:italic>\n 1<\/jats:sub>\n -score of 0.68. Calibration plots indicated close agreement between predicted and observed risks across most probability ranges, with mild divergences at higher predicted risks. Shapley Additive Explanations analysis identified frequent hospitalizations within 6 months, activities of daily living impairment, and weight loss as influential predictors. The model showed stable AUROC across sex and age strata (0.89\u20100.90) and maintained high discrimination among residents with improving activities of daily living scores (AUROC 0.91, 95% CI 0.90\u20100.92).\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n An interpretable machine learning model using routinely collected Taiwanese LTCF assessment data achieved strong discrimination, acceptable calibration, and stable temporal validation performance without requiring hospital-based electronic health record linkage. The HybridXGBRF had the highest AUROC among the evaluated models, but performance differences from extreme gradient boosting were small. The model may serve as a risk-stratification tool to help identify residents who could benefit from structured care review, advance care planning, or palliative care assessment. Prospective implementation studies could determine its impact on care processes and resident- or family-centered outcomes.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/94567","type":"journal-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T20:22:12Z","timestamp":1789590132000},"page":"e94567-e94567","source":"Crossref","is-referenced-by-count":0,"title":["Development and Temporal External Validation of a Parsimonious, Interpretable Machine Learning Model for Predicting 6-Month Mortality in Long-Term Care Facilities: A Retrospective Cohort Study"],"prefix":"10.2196","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3830-3272","authenticated-orcid":false,"given":"Yun-Cheng","family":"Tsai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2747-7015","authenticated-orcid":false,"given":"Yi-Lin","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1857-9762","authenticated-orcid":false,"given":"Yung-Chen","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9935-7100","authenticated-orcid":false,"given":"Yi-Wen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3585-1767","authenticated-orcid":false,"given":"Yi-Wen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1391-8040","authenticated-orcid":false,"given":"Yi-Ching","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9363-8219","authenticated-orcid":false,"given":"Yu-Tai","family":"Lo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"issue":"4","key":"R1","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1177\/0898264316686575","article-title":"Death following recent admission into nursing home from community living: a systematic review into the transition process","volume":"30","author":"Ferrah","journal-title":"J Aging Health"},{"issue":"9","key":"R2","doi-asserted-by":"publisher","first-page":"105142","DOI":"10.1016\/j.jamda.2024.105142","article-title":"Risk of death among nursing home residents: a cross-national perspective","volume":"25","author":"Morris","journal-title":"J Am Med Dir Assoc"},{"issue":"2","key":"R3","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1001\/jama.2011.1966","article-title":"Prognostic indices for older adults: a systematic review","volume":"307","author":"Yourman","journal-title":"JAMA"},{"issue":"4","key":"R4","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1111\/jgs.15809","article-title":"Decision making for older adults with multiple chronic conditions: executive summary for the American Geriatrics Society guiding principles on the care of older adults with multimorbidity","volume":"67","author":"Boyd","journal-title":"J Am Geriatr Soc"},{"issue":"12","key":"R5","doi-asserted-by":"publisher","first-page":"2353","DOI":"10.1111\/jgs.15579","article-title":"Adaptation and initial validation of Minimum Data Set (MDS) Mortality Risk Index to MDS Version 3.0","volume":"66","author":"Niznik","journal-title":"J Am Geriatr Soc"},{"key":"R6","doi-asserted-by":"publisher","DOI":"10.1186\/1756-0500-3-200","article-title":"The MDS Mortality Risk Index: the evolution of a method for predicting 6-month mortality in nursing home residents","volume":"3","author":"Porock","journal-title":"BMC Res Notes"},{"issue":"17","key":"R7","doi-asserted-by":"publisher","first-page":"1929","DOI":"10.1001\/jama.2010.1572","article-title":"Prediction of 6-month survival of nursing home residents with advanced dementia using ADEPT vs hospice eligibility guidelines","volume":"304","author":"Mitchell","journal-title":"JAMA"},{"issue":"4","key":"R8","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1093\/gerona\/60.4.491","article-title":"Predicting death in the nursing home: development and validation of the 6-month Minimum Data Set mortality risk index","volume":"60","author":"Porock","journal-title":"J Gerontol A Biol Sci Med Sci"},{"issue":"22","key":"R9","doi-asserted-by":"publisher","first-page":"2734","DOI":"10.1001\/jama.291.22.2734","article-title":"Estimating prognosis for nursing home residents with advanced dementia","volume":"291","author":"Mitchell","journal-title":"JAMA"},{"issue":"2","key":"R10","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1046\/j.1532-5415.2003.51060.x","article-title":"Mortality-related factors and 1-year survival in nursing home residents","volume":"51","author":"Flacker","journal-title":"J Am Geriatr Soc"},{"issue":"2","key":"R11","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1089\/jpm.2014.0130","article-title":"Predictors of six-month mortality among nursing home residents: diagnoses may be more predictive than functional disability","volume":"18","author":"Levy","journal-title":"J Palliat Med"},{"issue":"5","key":"R12","doi-asserted-by":"publisher","DOI":"10.1093\/ageing\/afae098","article-title":"Predictors of mortality shortly after entering a long-term care facility","volume":"53","author":"Jorissen","journal-title":"Age Ageing"},{"issue":"17","key":"R13","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph17176234","article-title":"Application of machine learning methods in nursing home research","volume":"17","author":"Lee","journal-title":"Int J Environ Res Public Health"},{"issue":"8","key":"R14","doi-asserted-by":"publisher","first-page":"1403","DOI":"10.1016\/j.jamda.2022.01.069","article-title":"Risk prediction model for 6-month mortality for patients discharged to skilled nursing facilities","volume":"23","author":"Chandra","journal-title":"J Am Med Dir Assoc"},{"key":"R15","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2025.108653","article-title":"Towards clinical prediction with transparency: an explainable AI approach to survival modelling in residential aged care","volume":"263","author":"Susnjak","journal-title":"Comput Methods Programs Biomed"},{"issue":"6","key":"R16","doi-asserted-by":"publisher","DOI":"10.1002\/hsr2.1309","article-title":"Prediction models of all-cause mortality among older adults in nursing home setting: a systematic review and meta-analysis","volume":"6","author":"Zhang","journal-title":"Health Sci Rep"},{"issue":"10","key":"R17","doi-asserted-by":"publisher","first-page":"912","DOI":"10.1016\/j.healthpol.2019.08.004","article-title":"LTC 2.0: the 2017 reform of home- and community-based long-term care in Taiwan","volume":"123","author":"Hsu","journal-title":"Health Policy"},{"issue":"1","key":"R18","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1111\/j.1365-2702.2007.01974.x","article-title":"Service needs of residents in community-based long-term care facilities in northern Taiwan","volume":"17","author":"Huang","journal-title":"J Clin Nurs"},{"key":"R19","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","journal-title":"BMJ"},{"issue":"8","key":"R20","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1016\/S1474-4422(14)70120-6","article-title":"The Glasgow Coma Scale at 40 years: standing the test of time","volume":"13","author":"Teasdale","journal-title":"Lancet Neurol"},{"key":"R21","volume":"14","author":"Mahoney","journal-title":"Md State Med J"},{"issue":"2","key":"R22","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1080\/07317115.2020.1839992","article-title":"Performance of the Geriatric Depression Scale-15 with older adults aged over 65 years: an updated review 2000-2019","volume":"44","author":"Park","journal-title":"Clin Gerontol"},{"issue":"4","key":"R23","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1001\/archinternmed.2007.113","article-title":"Comparison of 2 frailty indexes for prediction of falls, disability, fractures, and death in older women","volume":"168","author":"Ensrud","journal-title":"Arch Intern Med"},{"issue":"9","key":"R24","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1007\/s12603-009-0214-7","article-title":"Validation of the Mini Nutritional Assessment short-form (MNA-SF): a practical tool for identification of nutritional status","volume":"13","author":"Kaiser","journal-title":"J Nutr Health Aging"},{"issue":"10","key":"R25","doi-asserted-by":"publisher","first-page":"1926","DOI":"10.1111\/j.1532-5415.2008.01935.x","article-title":"A manual of guidelines to score the modified cumulative illness rating scale and its validation in acute hospitalized elderly patients","volume":"56","author":"Salvi","journal-title":"J Am Geriatr Soc"},{"key":"R26","doi-asserted-by":"publisher","DOI":"10.2196\/79307","article-title":"Methods for addressing missingness in electronic health record data for clinical prediction models: comparative evaluation","volume":"13","author":"Digitale","journal-title":"JMIR Med Inform"},{"issue":"3","key":"R27","doi-asserted-by":"publisher","first-page":"1035","DOI":"10.13063\/2327-9214.1035","article-title":"Strategies for handling missing data in electronic health record derived data","volume":"1","author":"Wells","journal-title":"EGEMS (Wash DC)"},{"key":"R28","unstructured":"Wu K Dahlem D Hane C Halperin E Zou J . Collecting data when missingness is unknown: a method for improving model performance given under-reporting in patient populations. Presented at: Conference on Health, Inference, and Learning; Jun 22-24, 2023; Cambridge, MA, USA. URL: https:\/\/proceedings.mlr.press\/v209\/wu23b.html [Accessed 24-08-2026]"},{"key":"R29","doi-asserted-by":"crossref","unstructured":"Cabello-Solorzano K de Araujo IO . The impact of data normalization on the accuracy of machine learning algorithms: a comparative analysis. Presented at: 18th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2023); Sep 5-7, 2023; Salamanca, Spain. [doi: 10.1007\/978-3-031-42536-3_33]","DOI":"10.1007\/978-3-031-42536-3_33"},{"key":"R30","doi-asserted-by":"crossref","unstructured":"Chen T Guestrin C . XGBoost: a scalable tree boosting system. Presented at: 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; Aug 13-17, 2016; San Francisco, CA, USA. [doi: 10.1145\/2939672.2939785]","DOI":"10.1145\/2939672.2939785"},{"issue":"1","key":"R31","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","journal-title":"Mach Learn"},{"issue":"1","key":"R32","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1080\/00401706.1970.10488634","article-title":"Ridge regression: biased estimation for nonorthogonal problems","volume":"12","author":"Hoerl","journal-title":"Technometrics"},{"issue":"1","key":"R33","doi-asserted-by":"publisher","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","journal-title":"J R Stat Soc B"},{"issue":"2","key":"R34","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","article-title":"Regularization and variable selection via the elastic net","volume":"67","author":"Zou","journal-title":"J R Stat Soc B"},{"issue":"1","key":"R35","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","journal-title":"Nat Mach Intell"},{"key":"R36","unstructured":"Lundberg SM Lee SI . A unified approach to interpreting model predictions. Presented at: 31st International Conference on Neural Information Processing Systems; Dec 4-9, 2017; Long Beach, CA, USA. URL: https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/8a20a8621978632d76c43dfd28b67767-Paper.pdf [Accessed 24-08-2026]"},{"issue":"1","key":"R37","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-022-01620-x","article-title":"An approach to exploring patterns of imbalance and potential missingness in reports of the randomized baseline values for primary outcomes measurable at baseline in randomized controlled trials for meta-analyses","volume":"22","author":"Park","journal-title":"BMC Med Res Methodol"},{"issue":"1","key":"R38","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1034\/j.1601-5215.2002.51017.x","article-title":"The MDS-CHESS scale: a new measure to predict mortality in institutionalized older people","volume":"51","author":"Hirdes","journal-title":"J Am Geriatr Soc"},{"issue":"5","key":"R39","doi-asserted-by":"publisher","first-page":"976","DOI":"10.1111\/jgs.15305","article-title":"Minimum Data Set Changes in Health, End-Stage Disease and Symptoms and Signs Scale: a revised measure to predict mortality in nursing home residents","volume":"66","author":"Ogarek","journal-title":"J Am Geriatr Soc"},{"issue":"10","key":"R40","doi-asserted-by":"publisher","first-page":"1099","DOI":"10.1111\/j.1553-2712.2011.01185.x","article-title":"Logistic regression: a brief primer","volume":"18","author":"Stoltzfus","journal-title":"Acad Emerg Med"},{"issue":"11","key":"R41","doi-asserted-by":"publisher","first-page":"1800","DOI":"10.1016\/j.jamda.2022.05.019","article-title":"Predictors for the transitions of poor clinical outcomes among geriatric rehabilitation inpatients","volume":"23","author":"Soh","journal-title":"J Am Med Dir Assoc"},{"issue":"1","key":"R42","first-page":"34","volume":"104","author":"Gaddey","journal-title":"Am Fam Physician"},{"issue":"4","key":"R43","doi-asserted-by":"publisher","first-page":"938","DOI":"10.1111\/jgs.16915","article-title":"Improvement in activities of daily living during a nursing home stay and one\u2010year mortality among older adults with sepsis","volume":"69","author":"Downer","journal-title":"J Am Geriatr Soc"},{"issue":"6","key":"R44","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1016\/j.jamda.2014.11.018","article-title":"Functional improvement among short-stay nursing home residents in the MDS 3.0","volume":"16","author":"Wysocki","journal-title":"J Am Med Dir Assoc"},{"issue":"1","key":"R45","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1016\/j.archger.2011.06.031","article-title":"Terminal lucidity: a review and a case collection","volume":"55","author":"Nahm","journal-title":"Arch Gerontol Geriatr"},{"issue":"2","key":"R46","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1080\/09540261.2025.2503726","article-title":"End-of-life experiences in patients: a scoping review of types, characteristics, and implications for the mind-brain relationship","volume":"37","author":"Silva","journal-title":"Int Rev Psychiatry"},{"key":"R47","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2022.101610","article-title":"Dynamics of multimorbidity and frailty, and their contribution to mortality, nursing home and home care need: a primary care cohort of 1 456 052 ageing people","volume":"52","author":"Carrasco-Ribelles","journal-title":"EClinicalMedicine"},{"issue":"8","key":"R48","doi-asserted-by":"publisher","first-page":"1389","DOI":"10.1016\/j.jamda.2022.01.067","article-title":"Multimorbidity patterns and 5-year mortality in institutionalized older adults","volume":"23","author":"Vetrano","journal-title":"J Am Med Dir Assoc"},{"issue":"1","key":"R49","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.archger.2011.06.034","article-title":"Severe frailty and cognitive impairment are related to higher mortality in 12-month follow-up of nursing home residents","volume":"55","author":"Matusik","journal-title":"Arch Gerontol Geriatr"},{"issue":"9","key":"R50","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1056\/NEJMra2214964","article-title":"Considering biased data as informative artifacts in AI-assisted health care","volume":"389","author":"Ferryman","journal-title":"N Engl J Med"},{"issue":"4","key":"R51","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2023.8795","article-title":"Advanced care planning for hospitalized patients following clinician notification of patient mortality by a machine learning algorithm","volume":"6","author":"Chi","journal-title":"JAMA Netw Open"},{"issue":"6","key":"R52","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1177\/0272989X06295361","article-title":"Decision curve analysis: a novel method for evaluating prediction models","volume":"26","author":"Vickers","journal-title":"Med Decis Making"},{"issue":"9","key":"R53","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1016\/j.jamda.2013.02.022","article-title":"Factors associated with weight loss, low BMI, and malnutrition among nursing home patients: a systematic review of the literature","volume":"14","author":"Tamura","journal-title":"J Am Med Dir Assoc"},{"issue":"8","key":"R54","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1097\/MLR.0b013e3182984bff","article-title":"Potentially avoidable hospitalizations for elderly long-stay residents in nursing homes","volume":"51","author":"Spector","journal-title":"Med Care"},{"issue":"2","key":"R55","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/s10488-010-0319-7","article-title":"Outcomes for implementation research: conceptual distinctions, measurement challenges, and research agenda","volume":"38","author":"Proctor","journal-title":"Adm Policy Ment Health"}],"container-title":["JMIR Aging"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T20:22:18Z","timestamp":1789590138000},"score":1,"resource":{"primary":{"URL":"https:\/\/aging.jmir.org\/2026\/1\/e94567"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,16]]},"references-count":55,"URL":"https:\/\/doi.org\/10.2196\/94567","relation":{},"ISSN":["2561-7605"],"issn-type":[{"value":"2561-7605","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,16]]},"article-number":"v9i4e94567"}}