Use of Conventional Artificial Intelligence Methods in the Identification of Frailty: A Scoping Review.
Background: Early identification and management of frailty are crucial, yet its detection in early stages remains difficult for clinicians. Artificial intelligence (AI) has emerged as a promising tool in healthcare. However, the absence of a standard frailty definition and diversity of AI methods cr...
| Publicado en: | Journal of the American Geriatrics Society Vol. 74; no. 7; pp. 2103 - 2115 |
|---|---|
| Autores principales: | , , , , , , , , , , , , , , , , , , , |
| Formato: | Artículo |
| Publicado: |
Wiley-Blackwell
Jul2026
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=195715260&site=ehost-live header: @attributes: shortDbName: ssf uiTerm: 195715260 longDbName: Social Sciences Full Text (H.W. Wilson) uiTag: AN controlInfo: bkinfo: jinfo: jid: 00028614 20Q jtl: Journal of the American Geriatrics Society issn: 00028614 maglogo: Y pubinfo: dt: Jul2026 vid: 74 iid: 7 pid: 480 pub: Wiley-Blackwell artinfo: ui: 195715260 10.1111/jgs.70387 ppf: 2103 ppct: 12 formats: tig: atl: Use of Conventional Artificial Intelligence Methods in the Identification of Frailty: A Scoping Review. aug: au: Dalsania, Kunal Ashok Ménard, Alixe Sundararaman, Shruthi Rahgozar, Arya de Lima, Sarah Lu, Xintong Al‐Ali, Aya Singh, Krishnpriya Hakimjavadi, Ramtin Yan, Hui Sethuram, Claire Bergman, Howard LaPlante, Jim McIsaac, Daniel Rahimi, Samira Abbasgholizadeh Sourial, Nadia Thandi, Manpreet Wong, Sabrina Liddy, Clare Bandeen‐Roche, Karen affil: Interdisciplinary School of Health Sciences, University of Ottawa, Ottawa Ontario,, Canada Bruyère Health Research Institute, Ottawa Ontario,, Canada Faculty of Medicine, University of Ottawa, Ottawa Ontario,, Canada Department of Family Medicine, University of Ottawa, Ottawa Ontario,, Canada Family Medicine, McGill University, Montréal Québec,, Canada Care Partner, Ottawa Ontario,, Canada Anesthesiology and Pain Medicine, the Ottawa Hospital, Ottawa Ontario,, Canada Department of Family Medicine, McGill University, Montréal Québec,, Canada Department of Health Management, Université de Montréal, Montréal Québec,, Canada Centre for Health Services and Policy Research, University of British Columbia, Vancouver British Columbia,, Canada Johns Hopkins Bloomberg School of Public Health, Baltimore Maryland,, USA su: Artificial intelligence Active aging Medical information storage & retrieval systems Random forest algorithms Research funding Grey literature Frail elderly Digital health Logistic regression analysis Descriptive statistics Wearable technology Natural language processing Systematic reviews MEDLINE Computer-aided diagnosis Artificial neural networks Early diagnosis Decision trees Psychology information storage & retrieval systems Biomarkers sug: subj: Artificial intelligence Active aging Medical information storage & retrieval systems Random forest algorithms Research funding Grey literature Frail elderly Digital health Logistic regression analysis Descriptive statistics Wearable technology Natural language processing Systematic reviews MEDLINE Computer-aided diagnosis Artificial neural networks Early diagnosis Decision trees Psychology information storage & retrieval systems Biomarkers keyword: artificial intelligence digital health frailty healthy aging artificial intelligence digital health frailty healthy aging ab: Background: Early identification and management of frailty are crucial, yet its detection in early stages remains difficult for clinicians. Artificial intelligence (AI) has emerged as a promising tool in healthcare. However, the absence of a standard frailty definition and diversity of AI methods create a need for a comprehensive review. This study examines the clinical tools and conceptual frameworks used as reference standards in training AI algorithms for frailty identification and management, describes current AI methods, and explores the engagement of knowledge users in developing and evaluating these technologies. Methods: A scoping review was conducted following the Arksey and O'Malley framework, enhanced by Levac et al. and the Joanna Briggs Institute. Eight academic databases—Medline, Embase, PsycInfo, Cumulative Index to Nursing and Allied Health Literature, Ageline, Web of Science, Scopus, and Institute of Electrical and Electronics Engineers Xplore—and one gray literature source—ProQuest Dissertations & Theses Global—were searched. Abstracts and full‐text screening and data charting were performed in duplicate. Results were summarized through text and graphical representations. Results: The review included 33 publications, predominantly emerging after 2020. Twenty‐three different AI techniques were presented, with standard modeling approaches such as logistic regression and decision trees being most common. Among the 21 distinct reference standards used to train AI models, the Physical Frailty Phenotype was cited most frequently (n = 7). Most AI methods (n = 27) prioritized frailty identification, one addressed frailty management, and five focused on both. None of the papers engaged knowledge users in defining or validating AI tools, and only three studies explored algorithmic biases that could lead to inequities. Conclusions: Like the broader frailty literature, emerging AI tools lack a consistent definition of frailty, leading to design and implementation inconsistencies. The absence of knowledge user involvement may further limit the clinical relevance and equity of these technologies. Trial Registration: OSF Registries [https://doi.org/10.17605/OSF.IO/T54G8]. Summary: Key points ○Artificial intelligence (AI) models for frailty use a wide range of clinical definitions and frameworks, with no standard reference, leading to inconsistent algorithm design and evaluation.○Most AI applications focus on identifying frailty rather than supporting its management.○None of the reviewed studies involved clinicians, older adults, or caregivers in developing or validating AI tools, and few assessed potential algorithmic biases.Why does this paper matter? ○AI offers promise for earlier and more accurate detection of frailty, but our review shows that inconsistent definitions, limited focus on management, and lack of knowledge user engagement may undermine its clinical use and equity.○By identifying these gaps, this paper highlights the need for standardized frameworks and the active involvement of clinicians, older adults, and caregivers in developing AI tools that are both effective and acceptable in real‐world frailty care. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: N holdings: @attributes: islocal: N |
|---|