{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:48:11Z","timestamp":1782845291474,"version":"3.54.5"},"reference-count":48,"publisher":"JMIR Publications Inc.","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"\n Background<\/jats:title>\n Modern modeling techniques may potentially provide more accurate predictions of dichotomous outcomes than classical techniques.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n In this study, we aimed to examine the predictive performance of eight modeling techniques to predict mortality by frailty.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n We performed a longitudinal study with a 7-year follow-up. The sample consisted of 479 Dutch community-dwelling people, aged 75 years and older. Frailty was assessed with the Tilburg Frailty Indicator (TFI), a self-report questionnaire. This questionnaire consists of eight physical, four psychological, and three social frailty components. The municipality of Roosendaal, a city in the Netherlands, provided the mortality dates. We compared modeling techniques, such as support vector machine (SVM), neural network (NN), random forest, and least absolute shrinkage and selection operator, as well as classical techniques, such as logistic regression, two Bayesian networks, and recursive partitioning (RP). The area under the receiver operating characteristic curve (AUROC) indicated the performance of the models. The models were validated using bootstrapping.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n We found that the NN model had the best validated performance (AUROC=0.812), followed by the SVM model (AUROC=0.705). The other models had validated AUROC values below 0.700. The RP model had the lowest validated AUROC (0.605). The NN model had the highest optimism (0.156). The predictor variable \u201cdifficulty in walking\u201d was important for all models.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n Because of the high optimism of the NN model, we prefer the SVM model for predicting mortality among community-dwelling older people using the TFI, with the addition of \u201cgender\u201d and \u201cage\u201d variables. External validation is a necessary step before applying the prediction models in a new setting.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/31480","type":"journal-article","created":{"date-parts":[[2022,1,8]],"date-time":"2022-01-08T08:29:38Z","timestamp":1641630578000},"page":"e31480","source":"Crossref","is-referenced-by-count":8,"title":["A Comparison of Different Modeling Techniques in Predicting Mortality With the Tilburg Frailty Indicator: Longitudinal Study"],"prefix":"10.2196","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0429-6753","authenticated-orcid":false,"given":"Tjeerd","family":"van der Ploeg","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6225-5189","authenticated-orcid":false,"given":"Robbert","family":"Gobbens","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2022,3,30]]},"reference":[{"key":"ref1","author":"Hastie, T","year":"2017","journal-title":"The Elements of Statistical Learning: Data Mining, Inference, and Prediction. 2nd edition"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-19425-7","author":"Harrell Jr, FE","year":"2015","journal-title":"Regression Modeling Strategies: With Applications to Linear Models, Logistic and Ordinal Regression, and Survival Analysis. 2nd edition"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-16399-0","author":"Steyerberg, EW","year":"2019","journal-title":"Clinical Prediction Models: A Practical Approach to Development, Validation, and Updating. 2nd edition"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.0050168"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/(sici)1097-0258(19980530)17:10<1169::aid-sim796>3.0.co;2-d"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1214\/08-aoas169"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1090\/dimacs\/055\/01"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2008.10.014"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1093\/gerona\/56.3.m146"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1136\/jech-2015-206717"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jamda.2016.09.010"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s12603-010-0045-6"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jamda.2009.11.003"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jamda.2009.09.015"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2147\/cia.s298191"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.archger.2018.02.013"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.archger.2018.01.013"},{"key":"ref18","first-page":"83","author":"Huisman, M","year":"2011","journal-title":"Frail Older Persons in the Netherlands"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1111\/jgs.12420"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10433-019-00502-4"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0100234"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2007.11.017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1093\/geront\/gnr135"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.jamda.2009.11.008"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v045.i03"},{"key":"ref26","first-page":"1","author":"Breiman, L","year":"1984","journal-title":"Classification and Regression Trees"},{"key":"ref27","first-page":"1","author":"Tuff\u00e9ry, S","year":"2011","journal-title":"Data Mining and Statistics for Decision Making"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/bf00994018"},{"key":"ref29","unstructured":"TsamardinosIAliferisCFTowards principled feature selection: Relevancy, filters and wrappersProceedings of the 9th International Workshop on Artificial Intelligence and Statistics2003The 9th International Workshop on Artificial Intelligence and StatisticsJanuary 3-6, 2003Key West, FL300307"},{"key":"ref30","unstructured":"AliferisCFTsamardinosIStatnikovARBrownLECausal Explorer: A causal probabilistic network learning toolkit for biomedical discoveryProceedings of the International Conference on Mathematics and Engineering Techniques in Medicine and Biological Sciences2003International Conference on Mathematics and Engineering Techniques in Medicine and Biological SciencesJune 23-26, 2003Las Vegas, NV371376"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1186\/s13104-016-1945-2"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102418"},{"key":"ref33","unstructured":"R Core TeamThe R Project for Statistical Computing2022-03-14Vienna, AustriaThe R Foundationhttps:\/\/www.r-project.org\/"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"ref35","first-page":"177","volume":"20","author":"Fisher, A","year":"2019","journal-title":"J Mach Learn Res"},{"key":"ref36","first-page":"1","author":"Efron, B","year":"1994","journal-title":"An Introduction to the Bootstrap"},{"key":"ref37","unstructured":"Your research: Is it subject to the WMO or not?Central Committee on Research Involving Human Subjects2022-03-14https:\/\/english.ccmo.nl\/investigators\/legal-framework-for-medical-scientific-research\/your-research-is-it-subject-to-the-wmo-or-not"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.arr.2012.03.001"},{"key":"ref39","unstructured":"van der PloegTPrediction of Medical Outcomes with Modern Modelling Techniques [doctoral thesis]20172022-03-14Rotterdam, the NetherlandsErasmus University Rotterdamhttps:\/\/repub.eur.nl\/pub\/95059"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s12603-015-0651-4"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2016.03.002"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1002\/(sici)1097-0258(20000430)19:8<1059::aid-sim412>3.0.co;2-0"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2003.11.001"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/s0895-4356(01)00341-9"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-14-40"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2014.09.007"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/s0895-4356(03)00207-5"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-130-6-199903160-00016"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2022\/3\/e31480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:48:25Z","timestamp":1782841705000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2022\/3\/e31480"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,30]]},"references-count":48,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2022]]}},"URL":"https:\/\/doi.org\/10.2196\/31480","relation":{"has-preprint":[{"id-type":"doi","id":"10.2196\/preprints.31480","asserted-by":"object"}]},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,30]]}}}