{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T18:13:48Z","timestamp":1788545628264,"version":"build-2803163510"},"reference-count":33,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T00:00:00Z","timestamp":1788480000000},"content-version":"vor","delay-in-days":3,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Scotia Scholars Doctoral Award"},{"name":"Killam Predoctoral Scholarship Level 2"},{"name":"Nova Scotia Graduate Scholarship"},{"name":"Michael Smith Foreign Study Supplements"},{"name":"Canadian Institutes of Health Research Canada Graduate Scholarships"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The frailty index (FI) assumes that deficits are interchangeable; the type of individual items matters less than the total count. Machine learning is increasingly used to create shorter FIs, often motivated by perceived barriers to collecting many items in clinical settings despite availability of electronic health records. We explored whether FI item selection matters when predicting mortality in adults living with cardiovascular disease (CVD).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We analysed 3669 adults living with CVD from the National Health and Nutrition Examination Survey (1999\u20132018) with a 46-item FI. Cox and random survival forest models predicted all-cause and CVD-specific mortality using individual items or composite FI scores. Items were ranked by permutation importance. At each item count k (1-46), we compared the top k items as individual predictors, the top k items combined into a single FI and 200 FIs each built from randomly selected k items.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Models using 46 individual items outperformed composite FI approaches for both outcomes (C-index: 0.71 [0.69\u20130.74] vs 0.64\u20130.67). Importance-ranked FI performance peaked at ~10 items then declined. Randomly built FIs improved steadily, converging with the importance-ranked composites by ~35 items (all-cause) and 20 items (CVD). Analyses using imputation produced consistent results.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>When enough items are included, which specific items make up the FI has negligible influence on prediction. Combining items into a single score discards some prognostic information, but this trade-off maintains the generalisability that makes the FI practical. Short importance-ranked FIs benefit from avoiding dilution rather than capturing an optimal item set, and any such selection is outcome-specific and sample-dependent.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/ageing\/afag262","type":"journal-article","created":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T11:48:29Z","timestamp":1787312909000},"source":"Crossref","is-referenced-by-count":0,"title":["Frailty index deficit interchangeability: an empirical test using random survival forests in adults with cardiovascular disease"],"prefix":"10.1093","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0998-0485","authenticated-orcid":false,"given":"Jack","family":"Quach","sequence":"first","affiliation":[{"name":"Faculty of Health, Dalhousie University , Halifax, Nova Scotia ,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6460-782X","authenticated-orcid":false,"given":"Olga","family":"Theou","sequence":"additional","affiliation":[{"name":"Faculty of Health, Dalhousie University , Halifax, Nova Scotia ,","place":["Canada"]},{"name":"School of Physiotherapy, Dalhousie University , Halifax, Nova Scotia ,","place":["Canada"]},{"name":"Division of Geriatric Medicine, Dalhousie University , Halifax, Nova Scotia ,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6674-995X","authenticated-orcid":false,"given":"Kenneth","family":"Rockwood","sequence":"additional","affiliation":[{"name":"Division of Geriatric Medicine, Dalhousie University , Halifax, Nova Scotia ,","place":["Canada"]},{"name":"Department of Medicine, Dalhousie University , Halifax, Nova Scotia ,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Scott","family":"Kehler","sequence":"additional","affiliation":[{"name":"Faculty of Health, Dalhousie University , Halifax, Nova Scotia ,","place":["Canada"]},{"name":"School of Physiotherapy, Dalhousie University , Halifax, Nova Scotia ,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7684-3571","authenticated-orcid":false,"given":"Joanna","family":"Blodgett","sequence":"additional","affiliation":[{"name":"Institute of Sport Exercise & Health, Division of Surgery & Interventional Science, University College London , London ,","place":["UK"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,9,4]]},"reference":[{"key":"2026090413502717300_ref1","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1100\/tsw.2001.58","article-title":"Accumulation of deficits as a proxy measure of aging","volume":"1","author":"Mitnitski","year":"2001","journal-title":"ScientificWorldJournal"},{"key":"2026090413502717300_ref2","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1186\/1471-2318-8-24","article-title":"A standard procedure for creating a frailty index","volume":"8","author":"Searle","year":"2008","journal-title":"BMC Geriatr"},{"key":"2026090413502717300_ref3","doi-asserted-by":"publisher","first-page":"afad221","DOI":"10.1093\/ageing\/afad221","article-title":"How to construct a frailty index from an existing dataset in 10 steps","volume":"52","author":"Theou","year":"2023","journal-title":"Age Ageing"},{"key":"2026090413502717300_ref4","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1093\/gerona\/62.7.722","article-title":"Frailty in relation to the accumulation of deficits","volume":"62","author":"Rockwood","year":"2007","journal-title":"J Gerontol A Biol Sci Med Sci"},{"key":"2026090413502717300_ref5","doi-asserted-by":"publisher","first-page":"052409","DOI":"10.1103\/PhysRevE.94.052409","article-title":"Network model of human aging: frailty limits and information measures","volume":"94","author":"Farrell","year":"2016","journal-title":"Phys Rev E"},{"key":"2026090413502717300_ref6","doi-asserted-by":"publisher","first-page":"101233","DOI":"10.1016\/j.arr.2020.101233","article-title":"Frailty is highly prevalent in specific cardiovascular diseases and females, but significantly worsens prognosis in all affected patients: a systematic review","volume":"66","author":"Marinus","year":"2021","journal-title":"Ageing Res Rev"},{"key":"2026090413502717300_ref7","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1093\/eurheartj\/ehab850","article-title":"Frailty and cardiovascular mortality in more than 3 million US Veterans","volume":"43","author":"Shrauner","year":"2022","journal-title":"Eur Heart J"},{"key":"2026090413502717300_ref8","doi-asserted-by":"publisher","first-page":"3826","DOI":"10.1093\/eurheartj\/ehac270","article-title":"2022 ESC Guidelines on cardiovascular assessment and management of patients undergoing non-cardiac surgery","volume":"43","author":"Halvorsen","year":"2022","journal-title":"Eur Heart J"},{"key":"2026090413502717300_ref9","doi-asserted-by":"publisher","first-page":"e90475","DOI":"10.1371\/journal.pone.0090475","article-title":"Accumulation of non-traditional risk factors for coronary heart disease is associated with incident coronary heart disease hospitalization and death","volume":"9","author":"Wallace","year":"2014","journal-title":"PLoS One"},{"key":"2026090413502717300_ref10","doi-asserted-by":"publisher","first-page":"e014686","DOI":"10.1161\/JAHA.119.014686","article-title":"Accumulation of deficits as a key risk factor for cardiovascular morbidity and mortality: a pooled analysis of 154 000 individuals","volume":"9","author":"Farooqi","year":"2020","journal-title":"J Am Heart Assoc"},{"key":"2026090413502717300_ref11","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.jss.2013.01.021","article-title":"Accumulating deficits model of frailty and postoperative mortality and morbidity: its application to a national database","volume":"183","author":"Velanovich","year":"2013","journal-title":"J Surg Res"},{"key":"2026090413502717300_ref12","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1016\/j.jamcollsurg.2017.11.005","article-title":"New 5-factor modified frailty index using American College of Surgeons NSQIP Data","volume":"226","author":"Subramaniam","year":"2018","journal-title":"J Am Coll Surg"},{"key":"2026090413502717300_ref13","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1016\/j.amjsurg.2018.11.020","article-title":"Impact of frailty on outcomes in surgical patients: a systematic review and meta-analysis","volume":"218","author":"Panayi","year":"2019","journal-title":"Am J Surg"},{"key":"2026090413502717300_ref14","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.amjcard.2022.11.044","article-title":"Developing a parsimonious frailty index for older, multimorbid adults with heart failure using machine learning","volume":"190","author":"Razjouyan","year":"2023","journal-title":"Am J Cardiol"},{"key":"2026090413502717300_ref15","doi-asserted-by":"publisher","first-page":"921","DOI":"10.1186\/s12967-025-06728-4","article-title":"Development and multi-cohort validation of a machine learning-based simplified frailty assessment tool for clinical risk prediction","volume":"23","author":"Lai","year":"2025","journal-title":"J Transl Med"},{"key":"2026090413502717300_ref16","doi-asserted-by":"publisher","first-page":"afaf077","DOI":"10.1093\/ageing\/afaf077","article-title":"Development and external validation of the electronic frailty index 2 using routine primary care electronic health record data","volume":"54","author":"Best","year":"2025","journal-title":"Age Ageing"},{"key":"2026090413502717300_ref17","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1093\/jamia\/ocz210","article-title":"Using elastic nets to estimate frailty burden from routinely collected national aged care data","volume":"27","author":"Moldovan","year":"2020","journal-title":"J Am Med Inform Assoc"},{"key":"2026090413502717300_ref18","author":"NHANES","year":"2022"},{"key":"2026090413502717300_ref19","doi-asserted-by":"publisher","first-page":"e96","DOI":"10.1016\/S2666-7568(20)30059-3","article-title":"Changes in the severity and lethality of age-related health deficit accumulation in the USA between 1999 and 2018: a population-based cohort study","volume":"2","author":"Blodgett","year":"2021","journal-title":"Lancet Healthy Longev"},{"key":"2026090413502717300_ref20","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1214\/08-AOAS169","article-title":"Random survival forests","volume":"2","author":"Ishwaran","year":"2008","journal-title":"Ann Appl Stat"},{"key":"2026090413502717300_ref21","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"2026090413502717300_ref22","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"J Mach Learn Res"},{"key":"2026090413502717300_ref23","doi-asserted-by":"publisher","DOI":"10.1201\/9780429246593","volume-title":"An Introduction to the Bootstrap","author":"Efron","year":"1994"},{"key":"2026090413502717300_ref24","doi-asserted-by":"publisher","first-page":"43068","DOI":"10.1038\/srep43068","article-title":"A frailty index based on deficit accumulation quantifies mortality risk in humans and in mice","volume":"7","author":"Rockwood","year":"2017","journal-title":"Sci Rep"},{"key":"2026090413502717300_ref25","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1007\/978-0-387-84858-7_14","volume-title":"The Elements of Statistical Learning: Data Mining, Inference, and Prediction","author":"Hastie","year":"2009"},{"key":"2026090413502717300_ref26","doi-asserted-by":"publisher","first-page":"738","DOI":"10.1093\/gerona\/62.7.738","article-title":"A comparison of two approaches to measuring frailty in elderly people","volume":"62","author":"Rockwood","year":"2007","journal-title":"J Gerontol A Biol Sci Med Sci"},{"key":"2026090413502717300_ref27","doi-asserted-by":"publisher","first-page":"e16213","DOI":"10.2196\/16213","article-title":"Comparisons between hypothesis- and data-driven approaches for multimorbidity frailty index: a machine learning approach","volume":"22","author":"Peng","year":"2020","journal-title":"J Med Internet Res"},{"key":"2026090413502717300_ref28","doi-asserted-by":"publisher","first-page":"23227","DOI":"10.1038\/s41598-024-74194-x","article-title":"Enhancing the convenience of frailty index assessment for elderly Chinese people with machine learning methods","volume":"14","author":"Huang","year":"2024","journal-title":"Sci Rep"},{"key":"2026090413502717300_ref29","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1016\/j.amjmed.2003.11.014","article-title":"Elevated blood urea nitrogen level as a predictor of mortality in patients admitted for decompensated heart failure","volume":"116","author":"Aronson","year":"2004","journal-title":"Am J Med"},{"key":"2026090413502717300_ref30","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1097\/00001573-200007000-00009","article-title":"Pulse pressure, arterial stiffness, and cardiovascular risk","volume":"15","author":"Safar","year":"2000","journal-title":"Curr Opin Cardiol"},{"key":"2026090413502717300_ref31","doi-asserted-by":"publisher","first-page":"103122","DOI":"10.1016\/j.arr.2026.103122","article-title":"Machine learning for frailty assessment and outcome prediction in cardiovascular disease: a scoping review","volume":"118","author":"Quach","year":"2026","journal-title":"Ageing Res Rev"},{"key":"2026090413502717300_ref32","doi-asserted-by":"publisher","first-page":"1687","DOI":"10.1007\/s11357-022-00723-z","article-title":"Efficient representations of binarized health deficit data: The frailty index and beyond","volume":"45","author":"Pridham","year":"2023","journal-title":"GeroScience"},{"key":"2026090413502717300_ref33","doi-asserted-by":"publisher","first-page":"1457","DOI":"10.1016\/s0047-6374(02)00082-9","article-title":"The mortality rate as a function of accumulated deficits in a frailty index","volume":"123","author":"Mitnitski","year":"2002","journal-title":"Mech Ageing Dev"}],"container-title":["Age and Ageing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/ageing\/article-pdf\/55\/9\/afag262\/70964653\/afag262.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ageing\/article-pdf\/55\/9\/afag262\/70964653\/afag262.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T17:50:37Z","timestamp":1788544237000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/ageing\/article\/doi\/10.1093\/ageing\/afag262\/8785942"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":33,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,9,4]]}},"URL":"https:\/\/doi.org\/10.1093\/ageing\/afag262","relation":{},"ISSN":["0002-0729","1468-2834"],"issn-type":[{"value":"0002-0729","type":"print"},{"value":"1468-2834","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,9]]},"published":{"date-parts":[[2026,9]]},"article-number":"afag262"}}