A scoping review of machine learning models to predict risk of falls in elders, without using sensor data

Abstract Objectives This scoping review assesses machine learning (ML) tools that predicted falls, relying on information in health records without using any sensor data. The aim was to assess the available evidence on innovative techniques to improve fall prevention management. Methods Studies were...

Full description

Saved in:
Bibliographic Details
Main Authors: Angelo Capodici, Claudio Fanconi, Catherine Curtin, Alessandro Shapiro, Francesca Noci, Alberto Giannoni, Tina Hernandez-Boussard
Format: Article
Language:English
Published: BMC 2025-05-01
Series:Diagnostic and Prognostic Research
Subjects:
Online Access:https://doi.org/10.1186/s41512-025-00190-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850190828547342336
author Angelo Capodici
Claudio Fanconi
Catherine Curtin
Alessandro Shapiro
Francesca Noci
Alberto Giannoni
Tina Hernandez-Boussard
author_facet Angelo Capodici
Claudio Fanconi
Catherine Curtin
Alessandro Shapiro
Francesca Noci
Alberto Giannoni
Tina Hernandez-Boussard
author_sort Angelo Capodici
collection DOAJ
description Abstract Objectives This scoping review assesses machine learning (ML) tools that predicted falls, relying on information in health records without using any sensor data. The aim was to assess the available evidence on innovative techniques to improve fall prevention management. Methods Studies were included if they focused on predicting fall risk with machine learning in elderly populations and were written in English. There were 13 different extracted variables, including population characteristics (community dwelling, inpatients, age range, main pathology, ethnicity/race). Furthermore, the number of variables used in the final models, as well as their type, was extracted. Results A total of 6331 studies were retrieved, and 19 articles met criteria for data extraction. Metric performances reported by authors were commonly high in terms of accuracy (e.g., greater than 0.70). The most represented features included cardiovascular status and mobility assessments. Common gaps identified included a lack of transparent reporting and insufficient fairness assessments. Conclusions This review provides evidence that falls can be predicted using ML without using sensors if the amount of data and its quality is adequate. However, further studies are needed to validate these models in diverse groups and populations.
format Article
id doaj-art-c988bf147cd8454cab95b65bc1a16650
institution OA Journals
issn 2397-7523
language English
publishDate 2025-05-01
publisher BMC
record_format Article
series Diagnostic and Prognostic Research
spelling doaj-art-c988bf147cd8454cab95b65bc1a166502025-08-20T02:15:08ZengBMCDiagnostic and Prognostic Research2397-75232025-05-01911910.1186/s41512-025-00190-yA scoping review of machine learning models to predict risk of falls in elders, without using sensor dataAngelo Capodici0Claudio Fanconi1Catherine Curtin2Alessandro Shapiro3Francesca Noci4Alberto Giannoni5Tina Hernandez-Boussard6Department of Health Management (Direzione Sanitaria), IRCCS Istituto Ortopedico RizzoliDepartment of Electrical Engineering and Information Technology, ETH ZurichDepartment of Surgery, Veterans’ Affairs Palo Alto Healthcare SystemDepartment of Medicine, Stanford Center for Biomedical Informatics Research (BMIR), Stanford UniversityInterdisciplinary Research Center for Health Science, Sant’Anna School of Advanced StudiesInterdisciplinary Research Center for Health Science, Sant’Anna School of Advanced StudiesDepartment of Medicine, Stanford Center for Biomedical Informatics Research (BMIR), Stanford UniversityAbstract Objectives This scoping review assesses machine learning (ML) tools that predicted falls, relying on information in health records without using any sensor data. The aim was to assess the available evidence on innovative techniques to improve fall prevention management. Methods Studies were included if they focused on predicting fall risk with machine learning in elderly populations and were written in English. There were 13 different extracted variables, including population characteristics (community dwelling, inpatients, age range, main pathology, ethnicity/race). Furthermore, the number of variables used in the final models, as well as their type, was extracted. Results A total of 6331 studies were retrieved, and 19 articles met criteria for data extraction. Metric performances reported by authors were commonly high in terms of accuracy (e.g., greater than 0.70). The most represented features included cardiovascular status and mobility assessments. Common gaps identified included a lack of transparent reporting and insufficient fairness assessments. Conclusions This review provides evidence that falls can be predicted using ML without using sensors if the amount of data and its quality is adequate. However, further studies are needed to validate these models in diverse groups and populations.https://doi.org/10.1186/s41512-025-00190-yArtificial intelligenceMachine learningEldersFallsSensorlessScoping review
spellingShingle Angelo Capodici
Claudio Fanconi
Catherine Curtin
Alessandro Shapiro
Francesca Noci
Alberto Giannoni
Tina Hernandez-Boussard
A scoping review of machine learning models to predict risk of falls in elders, without using sensor data
Diagnostic and Prognostic Research
Artificial intelligence
Machine learning
Elders
Falls
Sensorless
Scoping review
title A scoping review of machine learning models to predict risk of falls in elders, without using sensor data
title_full A scoping review of machine learning models to predict risk of falls in elders, without using sensor data
title_fullStr A scoping review of machine learning models to predict risk of falls in elders, without using sensor data
title_full_unstemmed A scoping review of machine learning models to predict risk of falls in elders, without using sensor data
title_short A scoping review of machine learning models to predict risk of falls in elders, without using sensor data
title_sort scoping review of machine learning models to predict risk of falls in elders without using sensor data
topic Artificial intelligence
Machine learning
Elders
Falls
Sensorless
Scoping review
url https://doi.org/10.1186/s41512-025-00190-y
work_keys_str_mv AT angelocapodici ascopingreviewofmachinelearningmodelstopredictriskoffallsinelderswithoutusingsensordata
AT claudiofanconi ascopingreviewofmachinelearningmodelstopredictriskoffallsinelderswithoutusingsensordata
AT catherinecurtin ascopingreviewofmachinelearningmodelstopredictriskoffallsinelderswithoutusingsensordata
AT alessandroshapiro ascopingreviewofmachinelearningmodelstopredictriskoffallsinelderswithoutusingsensordata
AT francescanoci ascopingreviewofmachinelearningmodelstopredictriskoffallsinelderswithoutusingsensordata
AT albertogiannoni ascopingreviewofmachinelearningmodelstopredictriskoffallsinelderswithoutusingsensordata
AT tinahernandezboussard ascopingreviewofmachinelearningmodelstopredictriskoffallsinelderswithoutusingsensordata
AT angelocapodici scopingreviewofmachinelearningmodelstopredictriskoffallsinelderswithoutusingsensordata
AT claudiofanconi scopingreviewofmachinelearningmodelstopredictriskoffallsinelderswithoutusingsensordata
AT catherinecurtin scopingreviewofmachinelearningmodelstopredictriskoffallsinelderswithoutusingsensordata
AT alessandroshapiro scopingreviewofmachinelearningmodelstopredictriskoffallsinelderswithoutusingsensordata
AT francescanoci scopingreviewofmachinelearningmodelstopredictriskoffallsinelderswithoutusingsensordata
AT albertogiannoni scopingreviewofmachinelearningmodelstopredictriskoffallsinelderswithoutusingsensordata
AT tinahernandezboussard scopingreviewofmachinelearningmodelstopredictriskoffallsinelderswithoutusingsensordata