Technology for home-based frailty assessment and prediction: A systematic review.
Background: The current clinical frailty assessments are time-consuming and subjective which can lead to inaccurate results and delayed medical attention. Sensor technology and artificial intelligence enable home-based frailty assessment; however, there are no systematic reviews of existing technolo...
| Publicado en: | Gerontechnology Vol. 19; no. 3; pp. 1 - 14 |
|---|---|
| Autores principales: | , , , , |
| Formato: | research systematic review tables/charts Journal Article |
| Publicado: |
International Society for Gerontechnology
2020
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=155648106&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 155648106 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 15691101 904R jtl: Gerontechnology issn: 15691101 maglogo: N pubinfo: dt: 2020 vid: 19 iid: 3 pid: 54298 pub: International Society for Gerontechnology artinfo: ui: 155648106 155648106 155648106 10.4017/gt.2020.19.003.06 155648106 ppf: 1 ppct: 13 formats: tig: atl: Technology for home-based frailty assessment and prediction: A systematic review. aug: au: Chao Bian Bing Ye Chu, Charlene H. McGilton, Katherine S. Mihailidis, Alex affil: Institute of Biomedical Engineering, University of Toronto, Toronto, Canada sug: subj: Technology Frailty Syndrome Diagnosis Geriatric Assessment Methods Artificial Intelligence Home Health Care Wearable Sensors Systematic Review Risk Assessment Medline Cochrane Library Embase Psycinfo CINAHL Database Functional Status ab: Background: The current clinical frailty assessments are time-consuming and subjective which can lead to inaccurate results and delayed medical attention. Sensor technology and artificial intelligence enable home-based frailty assessment; however, there are no systematic reviews of existing technological methods for home-based frailty assessment and prediction. Objective: To analyze and synthesize the frailty criteria, sensor technology, and the statistical or artificial intelligence methods used in home-based frailty assessment and prediction. Methods: An exhaustive database search was performed. Three reviewers screened all studies by following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. The sensors and AI used for assessing frailty were synthesized with a particular focus on home-based technology. The Sackett's Level of Evidence Scale was also used to evaluate clinical evidence for the included studies. Results: Body-worn sensors were the most commonly used (72%) technology in home-based frailty assessment. All of the body-worn sensors were accelerometer-based. 88% of the included studies measured physical activity for assessing frailty commonly defined by Fried's Frailty Index (75%). Heterogenous machine learning algorithms have been applied for classifying frailty. However, none of the AI methods were tested for the predictability of frailty. Only one longitudinal study followed up older participants for 10 years and revealed a high odds ratio for the development of frailty using physical activity. Conclusion: The database search was limited to definitions of physical frailty and the English language. Various types of sensor technology with good accuracy are used to measure specific frailty criteria and functional tests. However, there is a lack of longitudinal studies for predicting frailty progression. To date, there is limited testing of the sensors using older populations with functional and cognitive comorbidities and because they are at higher risk of frailty they should be a priority moving forward. pubtype: Academic Journal doctype: research systematic review tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|