AI-Driven Fall Prediction across Generations: Integrating Deep Learning and Machine Learning for Young, Middle-Aged, and Older Adults.

IF 3.1 3区医学 Q3 GERIATRICS & GERONTOLOGY

Gerontology Pub Date : 2026-01-01 Epub Date: 2025-11-06 DOI:10.1159/000549410

Fa-Chen Lin, Po-Hung Chen, Cheng-Hong Yang, Chen-Cheng Yang, Hung-Yi Chuang, Chih-Hsing Hung

{"title":"AI-Driven Fall Prediction across Generations: Integrating Deep Learning and Machine Learning for Young, Middle-Aged, and Older Adults.","authors":"Fa-Chen Lin, Po-Hung Chen, Cheng-Hong Yang, Chen-Cheng Yang, Hung-Yi Chuang, Chih-Hsing Hung","doi":"10.1159/000549410","DOIUrl":null,"url":null,"abstract":"Introduction: Falls occur in all age-groups and represent a significant public health concern. Previous studies have implemented artificial intelligence, including machine learning (ML) and deep learning (DL) algorithms for fall risk prediction, but the comparative performance between models and the applicability for younger populations remains unclear. This study aims to develop and compare different ML/DL models and identify key predictive features across age-groups.Methods: We enrolled 1,441 community-dwelling adults aged over 20 years in southern Taiwan and collected demographic, clinical, and physical performance data. Participants were categorized based on fall history. Five ML models (KNN, RF, GBDT, XGBoost, and CatBoost) and two DL models (GRU, AGRU) were trained and evaluated using accuracy, precision, recall, F1 score, and the area under the receiver operating characteristic curve (AUROC). Feature importance was interpreted using SHapley Additive exPlanations values in the best-performing model. Age-stratified subgroup analyses were conducted for groups aged 20-45, 46-65, and >65 years.Results: The AGRU model achieved the highest accuracy (91.39%) and AUROC (0.934) in the overall group and outperformed other models across all subgroups. Feature importance analysis revealed pulse rate, living alone, systolic blood pressure, 5-times Sit-to-Stand test, and sex as major predictors of falls in the overall group. The top five predictive factors varied across age-groups.Conclusion: We developed a robust and interpretable DL model to identify fall risk across different age-groups. Age-specific risk factors highlight the need for tailored preventive strategies. External validation using an independent dataset demonstrated moderate generalizability. Validating the model on larger, more diverse datasets and integration of sequential or sensor-based data are essential for practical applications.","PeriodicalId":12662,"journal":{"name":"Gerontology","volume":" ","pages":"3-18"},"PeriodicalIF":3.1000,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Gerontology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1159/000549410","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/11/6 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"GERIATRICS & GERONTOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Introduction: Falls occur in all age-groups and represent a significant public health concern. Previous studies have implemented artificial intelligence, including machine learning (ML) and deep learning (DL) algorithms for fall risk prediction, but the comparative performance between models and the applicability for younger populations remains unclear. This study aims to develop and compare different ML/DL models and identify key predictive features across age-groups.

Methods: We enrolled 1,441 community-dwelling adults aged over 20 years in southern Taiwan and collected demographic, clinical, and physical performance data. Participants were categorized based on fall history. Five ML models (KNN, RF, GBDT, XGBoost, and CatBoost) and two DL models (GRU, AGRU) were trained and evaluated using accuracy, precision, recall, F1 score, and the area under the receiver operating characteristic curve (AUROC). Feature importance was interpreted using SHapley Additive exPlanations values in the best-performing model. Age-stratified subgroup analyses were conducted for groups aged 20-45, 46-65, and >65 years.

Results: The AGRU model achieved the highest accuracy (91.39%) and AUROC (0.934) in the overall group and outperformed other models across all subgroups. Feature importance analysis revealed pulse rate, living alone, systolic blood pressure, 5-times Sit-to-Stand test, and sex as major predictors of falls in the overall group. The top five predictive factors varied across age-groups.

Conclusion: We developed a robust and interpretable DL model to identify fall risk across different age-groups. Age-specific risk factors highlight the need for tailored preventive strategies. External validation using an independent dataset demonstrated moderate generalizability. Validating the model on larger, more diverse datasets and integration of sequential or sensor-based data are essential for practical applications.

查看原文本刊更多论文

人工智能驱动的跨代跌倒预测：将深度学习和机器学习整合到年轻人、中年人和老年人中。

跌倒发生在所有年龄组，是一个重大的公共卫生问题。以前的研究已经实现了人工智能（AI），包括机器学习（ML）和深度学习（DL）算法，用于跌倒风险预测，但模型之间的比较性能以及对年轻人群的适用性仍然不清楚。本研究旨在开发和比较不同的ML/DL模型，并确定跨年龄组的关键预测特征。方法在台湾南部选取1441名20岁以上的社区居民，收集人口统计、临床及体能资料。参与者根据秋季历史进行分类。5个ML模型（KNN、RF、GBDT、XGBoost和CatBoost）和2个DL模型（GRU、AGRU）进行训练，并使用准确度、精密度、召回率、f1评分和接收者工作特征曲线下面积（AUROC）进行评估。在表现最好的模型中，使用SHapley加性解释（SHAP）值来解释特征重要性。对20-45岁、46-65岁和50 -65岁年龄组进行年龄分层亚组分析。结果agu模型在整体组中准确率最高（91.39%），AUROC最高（0.934），在所有亚组中均优于其他模型。特征重要性分析显示，脉搏率、独居、收缩压、5次坐立测试和性别是整个群体跌倒的主要预测因素。前五大预测因素因年龄组而异。结论：我们建立了一个稳健且可解释的DL模型，用于识别不同年龄组的跌倒风险。针对特定年龄的风险因素突出表明需要制定针对性的预防战略。使用独立数据集的外部验证证明了适度的泛化性。用于验证和集成顺序或基于传感器的数据的更大和更多样化的数据集对于实际应用至关重要。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Gerontology 医学-老年医学

CiteScore

6.00

自引率

0.00%

发文量

审稿时长

6-12 weeks

期刊介绍： In view of the ever-increasing fraction of elderly people, understanding the mechanisms of aging and age-related diseases has become a matter of urgent necessity. ''Gerontology'', the oldest journal in the field, responds to this need by drawing topical contributions from multiple disciplines to support the fundamental goals of extending active life and enhancing its quality. The range of papers is classified into four sections. In the Clinical Section, the aetiology, pathogenesis, prevention and treatment of agerelated diseases are discussed from a gerontological rather than a geriatric viewpoint. The Experimental Section contains up-to-date contributions from basic gerontological research. Papers dealing with behavioural development and related topics are placed in the Behavioural Science Section. Basic aspects of regeneration in different experimental biological systems as well as in the context of medical applications are dealt with in a special section that also contains information on technological advances for the elderly. Providing a primary source of high-quality papers covering all aspects of aging in humans and animals, ''Gerontology'' serves as an ideal information tool for all readers interested in the topic of aging from a broad perspective.