Hidden Frailty: Artificial Intelligence Detection of Early Functional Decline Before Clinical Frailty Becomes Apparent
DOI:
https://doi.org/10.64229/x1e6j250Keywords:
Frailty, Artificial intelligence, Machine learning, Functional decline, Digital biomarkers, Wearable sensors, Older adults, Digital phenotypingAbstract
Frailty is a state of reduced physiological reserve that increases the risk of falls, hospitalization, disability, and death in older adults. Established instruments, including the Fried phenotype, the Frailty Index, and the Clinical Frailty Scale, rely on episodic assessment against population thresholds, so decline is usually recognized only after measurable impairment has accumulated. In this narrative review, informed by structured literature searches, we propose hidden frailty as a methodological detection concept rather than a new clinical stage: a sustained, multidomain deviation from an individual's own functional baseline, detectable through continuous monitoring, which may begin while a person is still classified as robust or prefrail. We synthesize evidence on wearable, smartphone, ambient, and electronic-health-record signals of gait, activity, sleep, physiology, and speech, and appraise machine-learning models for frailty classification, prediction, and trajectory detection. Reported discrimination is highest for cross-sectional classification, where overlap between predictors and the frailty definition inflates performance, and lower for prospective prediction. Only one model has addressed trajectory-based detection (internal area under the receiver operating characteristic curve [AUC] 0.70, no external validation), and calibration, decision-curve analysis, and economic evaluation are rarely reported. We propose a six-stage framework that specifies candidate variables, provisional decision criteria, clinical responses, and research priorities for each stage, and outline a pragmatic trial to test it. Because the premise currently rests largely on extrapolation from cross-sectional and short-term data, hidden frailty remains a testable hypothesis whose value depends on whether earlier detection, delivered equitably and with respect for privacy, improves functional outcomes.
References
[1]United Nations, Department of Economic and Social Affairs, Population Division. World population prospects 2024: Summary of results (UN DESA/POP/2024/TR/NO. 9). New York: United Nations. 2024.
[2]O'Caoimh R, Sezgin D, O'Donovan MR, Molloy DW, Clegg A, Rockwood K, et al. Prevalence of frailty in 62 countries across the world: A systematic review and meta-analysis of population-level studies. Age Ageing, 2021, 50(1), 96-104. DOI: 10.1093/ageing/afaa219
[3]Fried LP, Tangen CM, Walston J, Newman AB, Hirsch C, Gottdiener J, et al. Frailty in older adults: Evidence for a phenotype. The Journals of Gerontology: Series A, Biological Sciences and Medical Sciences, 2001, 56(3), M146-M156. DOI: 10.1093/gerona/56.3.M146
[4]Rockwood K, Mitnitski A. Frailty in relation to the accumulation of deficits. The Journals of Gerontology: Series A, Biological Sciences and Medical Sciences, 2007, 62(7), 722-727. DOI: 10.1093/gerona/62.7.722
[5]Searle SD, Mitnitski A, Gahbauer EA, Gill TM, Rockwood K. A standard procedure for creating a frailty index. BMC Geriatrics, 2008, 8, 24. DOI: 10.1186/1471-2318-8-24
[6]Rockwood K, Song X, MacKnight C, Bergman H, Hogan DB, McDowell I, et al. A global clinical measure of fitness and frailty in elderly people. Canadian Medical Association Journal, 2005, 173(5), 489-495. DOI: 10.1503/cmaj.050051
[7]Kim S, Shin MJ, Choi BK, Obradovic Z, Rubin DJ, Park JH. Machine learning-based frailty prediction and classification in community-dwelling older adults: A systematic review of validation, explainability, and implementation readiness. Healthcare (Basel), 2026, 14(11), 1543. DOI: 10.3390/healthcare14111543
[8]Baethge C, Goldbeck-Wood S, Mertens S. SANRA—a scale for the quality assessment of narrative review articles. Research Integrity and Peer Review, 2019, 4, 5. DOI: 10.1186/s41073-019-0064-8
[9]Wolff RF, Moons KGM, Riley RD, Whiting PF, Westwood M, Collins GS, et al. PROBAST: A tool to assess the risk of bias and applicability of prediction model studies. Annals of Internal Medicine, 2019, 170(1), 51-58. DOI: 10.7326/M18-1376
[10]Studenski S, Perera S, Patel K, Rosano C, Faulkner K, Inzitari M, et al. Gait speed and survival in older adults. The Journal of the American Medical Association, 2011, 305(1), 50-58. DOI: 10.1001/jama.2010.1923
[11]Schwenk M, Mohler J, Wendel C, D'Huyvetter K, Fain M, Taylor-Piliae R, et al. Wearable sensor-based in-home assessment of gait, balance, and physical activity for discrimination of frailty status: Baseline results of the Arizona frailty cohort study. Gerontology, 2015, 61(3), 258-267. DOI: 10.1159/000369095
[12]Mou C, Yan X, Miao X, Zhu L. Accuracy of wearable devices in predicting falls in older adults: A systematic review and meta-analysis. Frontiers in Public Health, 2026, 14, 1778750. DOI: 10.3389/fpubh.2026.1778750
[13]Culos A, Manas A, Shidara K, Fallazadeh R, Garcia-Garcia FJ, Losa-Reyna J, et al. A machine learning model for frailty based on wearable device measurements. Communications Medicine, 2026, 6(1), 173. DOI: 10.1038/s43856-026-01419-7
[14]Varadhan R, Chaves PH, Lipsitz LA, Stein PK, Tian J, Windham BG, et al. Frailty and impaired cardiac autonomic control: New insights from principal components aggregation of traditional heart rate variability indices. The Journals of Gerontology: Series A, Biological Sciences and Medical Sciences, 2009, 64(6), 682-687. DOI: 10.1093/gerona/glp013
[15]Da Cunha E, Zory R, Chorin F, Manera V, Gros A. Spontaneous speech enables scalable digital phenotyping of physical functional deficits in aging. NPJ Aging, 2026, 12(1), 52. DOI: 10.1038/s41514-026-00343-3
[16]Xiao J, Zhang W, Xu D, Mao H, Yang H. Predictive risk models for frailty onset in older adults: A scoping review of methodological trends, model performance, and clinical translation gap. Clinical Interventions in Aging, 2026, 21, 620467. DOI: 10.2147/CIA.S620467
[17]Xue QL. The frailty syndrome: Definition and natural history. Clinics in Geriatric Medicine, 2011, 27(1), 1-15. DOI: 10.1016/j.cger.2010.08.009
[18]Vetrano DL, Palmer K, Marengoni A, Marzetti E, Lattanzio F, Roller-Wirnsberger R, et al. Frailty and multimorbidity: A systematic review and meta-analysis. The Journals of Gerontology: Series A, Biological Sciences and Medical Sciences, 2019, 74(5), 659-666. DOI: 10.1093/gerona/gly110
[19]Gill TM, Gahbauer EA, Allore HG, Han L. Transitions between frailty states among community-living older persons. Archives of Internal Medicine, 2006, 166(4), 418-423. DOI: 10.1001/archinte.166.4.418
[20]Cesari M, Araujo de Carvalho I, Amuthavalli Thiyagarajan J, Cooper C, Martin FC, Reginster JY, et al. Evidence for the domains supporting the construct of intrinsic capacity. The Journals of Gerontology: Series A, Biological Sciences and Medical Sciences, 2018, 73(12), 1653-1660. DOI: 10.1093/gerona/gly011
[21]Benkaci A, Sliman L, Dellys HN. Vision-based human fall detection systems: A review. Procedia Computer Science, 2024, 241, 203-211. DOI: 10.1016/j.procs.2024.08.028
[22]Ensrud KE, Blackwell TL, Redline S, Ancoli-Israel S, Paudel ML, Cawthon PM, et al. Sleep disturbances and frailty status in older community-dwelling men. Journal of the American Geriatrics Society, 2009, 57(11), 2085-2093. DOI: 10.1111/j.1532-5415.2009.02490.x
[23]Onnela JP, Rauch SL. Harnessing smartphone-based digital phenotyping to enhance behavioral and mental health. Neuropsychopharmacology, 2016, 41(7), 1691-1696. DOI: 10.1038/npp.2016.7
[24]Rieke N, Hancox J, Li W, Milletari F, Roth HR, Albarqouni S, et al. The future of digital health with federated learning. NPJ Digital Medicine, 2020, 3, 119. DOI: 10.1038/s41746-020-00323-1
[25]Amann J, Blasimme A, Vayena E, Frey D, Madai VI. Explainability for artificial intelligence in healthcare: A multidisciplinary perspective. BMC Medical Informatics and Decision Making, 2020, 20(1), 310. DOI: 10.1186/s12911-020-01332-6
[26]Siontis GCM, Tzoulaki I, Castaldi PJ, Ioannidis JPA. External validation of new risk prediction models is infrequent and reveals worse prognostic discrimination. Journal of Clinical Epidemiology, 2015, 68(1), 25-34. DOI: 10.1016/j.jclinepi.2014.09.007
[27]Vickers AJ, Elkin EB. Decision curve analysis: A novel method for evaluating prediction models. Medical Decision Making, 2006, 26(6), 565-574. DOI: 10.1177/0272989X06295361
[28]Jacobson NS, Truax P. Clinical significance: A statistical approach to defining meaningful change in psychotherapy research. Journal of Consulting and Clinical Psychology, 1991, 59(1), 12-19. DOI: 10.1037/0022-006X.59.1.12
[29]Perera S, Mody SH, Woodman RC, Studenski SA. Meaningful change and responsiveness in common physical performance measures in older adults. Journal of the American Geriatrics Society, 2006, 54(5), 743-749. DOI: 10.1111/j.1532-5415.2006.00701.x
[30]Folorunsho S, Lawal OP, Somuah MA. Functional impairment without a depression diagnosis as an indicator of psychological distress in older adults. Cambridge Prisms: Global Mental Health, 2025, 12, e138. DOI: 10.1017/gmh.2025.10098
[31]Gijzel SMW, Whitson HE, van de Leemput IA, Scheffer M, van Asselt D, Rector JL, et al. Resilience in clinical care: Getting a grip on the recovery potential of older adults. Journal of the American Geriatrics Society, 2019, 67(12), 2650-2657. DOI: 10.1111/jgs.16149
[32]Hart TL, Swartz AM, Cashin SE, Strath SJ. How many days of monitoring predict physical activity and sedentary behaviour in older adults? The International Journal of Behavioral Nutrition and Physical Activity, 2011, 8, 62. DOI: 10.1186/1479-5868-8-62
[33]Troiano RP, Berrigan D, Dodd KW, Mâsse LC, Tilert T, McDowell M. Physical activity in the United States measured by accelerometer. Medicine & Science in Sports & Exercise, 2008, 40(1), 181-188. DOI: 10.1249/mss.0b013e31815a51b3
[34]Apóstolo J, Cooke R, Bobrowicz-Campos E, Santana S, Marcucci M, Cano A, et al. Effectiveness of interventions to prevent pre-frailty and frailty progression in older adults: A systematic review. JBI Database of Systematic Reviews and Implementation Reports, 2018, 16(1), 140-232. DOI: 10.11124/JBISRIR-2017-003382
[35]Glasgow RE, Vogt TM, Boles SM. Evaluating the public health impact of health promotion interventions: The RE-AIM framework. American Journal of Public Health, 1999, 89(9), 1322-1327. DOI: 10.2105/AJPH.89.9.1322
[36]Kaye JA, Maxwell SA, Mattek N, Hayes TL, Dodge H, Pavel M, et al. Intelligent systems for assessing aging changes: Home-based, unobtrusive, and continuous assessment of aging. The Journals of Gerontology, Series B: Psychological Sciences and Social Sciences, 2011, 66B(Suppl 1), i180-i190. DOI: 10.1093/geronb/gbq095
[37]Van Calster B, McLernon DJ, van Smeden M, Wynants L, Steyerberg EW. Calibration: The Achilles heel of predictive analytics. BMC Medicine, 2019, 17(1), 230. DOI: 10.1186/s12916-019-1466-7
[38]Collins GS, Moons KGM, Dhiman P, Riley RD, Beam AL, Van Calster B, et al. TRIPOD+AI statement: Updated guidance for reporting clinical prediction models that use regression or machine learning methods. British Medical Journal, 2024, 385, e078378. DOI: 10.1136/bmj-2023-078378
[39]US Food and Drug Administration. Artificial Intelligence/Machine Learning (AI/ML)-Based Software as a Medical Device (SaMD) Action Plan. Silver Spring, MD: FDA, 2021.
[40]Kyzas PA, Denaxa-Kyza D, Ioannidis JPA. Almost all articles on cancer prognostic markers report statistically significant results. European Journal of Cancer, 2007, 43(17), 2559-2579. DOI: 10.1016/j.ejca.2007.08.030
[41]Yang R, Gao S, Jiang Y. Digital divide as a determinant of health in the U.S. older adults: Prevalence, trends, and risk factors. BMC Geriatrics, 2024, 24(1), 1027. DOI: 10.1186/s12877-024-05612-y
[42]Grant PM, Dall PM, Mitchell SL, Granat MH. Activity-monitor accuracy in measuring step number and cadence in community-dwelling older adults. Journal of Aging and Physical Activity, 2008, 16(2), 201-214. DOI: 10.1123/japa.16.2.201
[43]Bent B, Goldstein BA, Kibbe WA, Dunn JP. Investigating sources of inaccuracy in wearable optical heart rate sensors. NPJ Digital Medicine, 2020, 3, 18. DOI: 10.1038/s41746-020-0226-6
[44]Sjoding MW, Dickson RP, Iwashyna TJ, Gay SE, Valley TS. Racial bias in pulse oximetry measurement. The New England Journal of Medicine, 2020, 383(25), 2477-2478. DOI: 10.1056/NEJMc2029240
[45]Obermeyer Z, Powers B, Vogeli C, Mullainathan S. Dissecting racial bias in an algorithm used to manage the health of populations. Science, 2019, 366(6464), 447-453. DOI: 10.1126/science.aax2342
[46]Mheidly N, Dempsey PR, Quinn K. Older adults' privacy perceptions of passive in-home monitoring technologies: A comprehensive scoping review. Ageing & Society, 2026, 46, e58. DOI: 10.1017/S0144686X26100701
[47]Lu LC, Lan SH, Hsieh YP, Lin LY, Lan SJ, Chen JC. Effectiveness of companion robot care for dementia: A systematic review and meta-analysis. Innovation in Aging, 2021, 5(2), igab013. DOI: 10.1093/geroni/igab013
[48]Pol M, van Nes F, van Hartingsveldt M, Buurman B, de Rooij S, Kröse B. Older people's perspectives regarding the use of sensor monitoring in their home. Gerontologist, 2016, 56(3), 485-493. DOI: 10.1093/geront/gnu104
[49]Sumner J, Chong LS, Bundele A, Lim YW. Co-designing technology for aging in place: A systematic review. Gerontologist, 2021, 61(7), e395-e409. DOI: 10.1093/geront/gnaa064
[50]Fernandes G, Figueiredo T, Costa E, Coelho L, Loyens D. Impact of telehealth on health outcomes and quality of life in the older adults population: A systematic review. Frontiers in Digital Health, 2025, 7, 1708960. DOI: 10.3389/fdgth.2025.1708960
[51]Palmer K, Villani ER, Vetrano DL, Cherubini A, Cruz-Jentoft AJ, Curtin D, et al. Association of polypharmacy and hyperpolypharmacy with frailty states: A systematic review and meta-analysis. European Geriatric Medicine, 2019, 10(1), 9-36. DOI: 10.1007/s41999-018-0124-5
[52]Elechi KW, Soyemi T, Shekoni M, Ede NS, Elechi US, Iloanusi CA, et al. Building healthcare capacity for neurodegenerative disease management in Nigeria: Challenges and opportunities. Journal of Public Health Research, 2025, 14(2). DOI: 10.1177/22799036251350957
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Anyebe Daniel Ameh, Uchenna Ugochukwu Ozoekwe , IyinOluwa Ayoola Opadere (Author)

This work is licensed under a Creative Commons Attribution 4.0 International License.