Development of Prediction Models for Healthy Ageing in Community-Dwelling Middle-Aged and Older Adults: A Longitudinal Study Using Machine Learning.

IF 3.8 2区 医学 Q2 GERIATRICS & GERONTOLOGY
Daniel E C Leme, Adriane R Costodio, Cesar de Oliveira, Michael Marmot
{"title":"Development of Prediction Models for Healthy Ageing in Community-Dwelling Middle-Aged and Older Adults: A Longitudinal Study Using Machine Learning.","authors":"Daniel E C Leme, Adriane R Costodio, Cesar de Oliveira, Michael Marmot","doi":"10.1016/j.jamda.2025.105843","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>Healthy ageing is a central issue in public health; however, there is a lack of consensus regarding its determinants. We developed machine learning (ML) models to predict healthy ageing based on the characteristics of community-dwelling middle-aged and older adults.</p><p><strong>Design: </strong>A retrospective study.</p><p><strong>Setting and participants: </strong>This cohort study included participants aged 50 years or older from the English Longitudinal Study of Ageing.</p><p><strong>Methods: </strong>We selected sociodemographic, health, lifestyle, and psychosocial characteristics at baseline. The outcome was healthy ageing at a 4-year follow-up, assessed based on functional status, preserved mobility, preserved muscle strength, absence of elevated depressive symptoms, absence of chronic diseases, and preserved cognitive function. We used the decision tree, logistic regression, neural network, and random forest algorithms to develop ML models and applied the SHapley Additive exPlanations algorithm to determine the contribution, positive or negative, of each predictor to the outcome.</p><p><strong>Results: </strong>Of the 6332 participants at baseline (median age 64 years), 27.9% were ageing healthily after 4 years. The ML model based on the random forest algorithm achieved the best performance on the test data set (area under the curve = 0.78, 95% CI 0.76-0.80). Normal physical performance, greater household wealth, chronological age, and self-perceived age between 50 and 59 years positively contributed, whereas physical inactivity, abdominal obesity, and not using the internet or email at baseline negatively affected the outcome.</p><p><strong>Conclusions and implications: </strong>ML models can help predict healthy ageing based on the characteristics of community-dwelling middle-aged and older adults. The available evidence can provide the basis for health strategies to promote active aging.</p>","PeriodicalId":17180,"journal":{"name":"Journal of the American Medical Directors Association","volume":" ","pages":"105843"},"PeriodicalIF":3.8000,"publicationDate":"2025-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of the American Medical Directors Association","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1016/j.jamda.2025.105843","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"GERIATRICS & GERONTOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Objectives: Healthy ageing is a central issue in public health; however, there is a lack of consensus regarding its determinants. We developed machine learning (ML) models to predict healthy ageing based on the characteristics of community-dwelling middle-aged and older adults.

Design: A retrospective study.

Setting and participants: This cohort study included participants aged 50 years or older from the English Longitudinal Study of Ageing.

Methods: We selected sociodemographic, health, lifestyle, and psychosocial characteristics at baseline. The outcome was healthy ageing at a 4-year follow-up, assessed based on functional status, preserved mobility, preserved muscle strength, absence of elevated depressive symptoms, absence of chronic diseases, and preserved cognitive function. We used the decision tree, logistic regression, neural network, and random forest algorithms to develop ML models and applied the SHapley Additive exPlanations algorithm to determine the contribution, positive or negative, of each predictor to the outcome.

Results: Of the 6332 participants at baseline (median age 64 years), 27.9% were ageing healthily after 4 years. The ML model based on the random forest algorithm achieved the best performance on the test data set (area under the curve = 0.78, 95% CI 0.76-0.80). Normal physical performance, greater household wealth, chronological age, and self-perceived age between 50 and 59 years positively contributed, whereas physical inactivity, abdominal obesity, and not using the internet or email at baseline negatively affected the outcome.

Conclusions and implications: ML models can help predict healthy ageing based on the characteristics of community-dwelling middle-aged and older adults. The available evidence can provide the basis for health strategies to promote active aging.

社区居住中老年人健康老龄化预测模型的发展:一项使用机器学习的纵向研究。
目标:健康老龄化是公共卫生的一个中心问题;然而,对其决定因素缺乏共识。我们开发了机器学习(ML)模型,根据社区居住的中老年人的特征预测健康老龄化。设计:回顾性研究。环境和参与者:本队列研究包括来自英国老龄化纵向研究的年龄在50岁或以上的参与者。方法:我们在基线时选择社会人口统计学、健康、生活方式和心理社会特征。在4年的随访中,结果是健康老龄化,根据功能状态、保留的活动能力、保留的肌肉力量、没有升高的抑郁症状、没有慢性疾病和保留的认知功能进行评估。我们使用决策树、逻辑回归、神经网络和随机森林算法来开发ML模型,并应用SHapley加性解释算法来确定每个预测器对结果的积极或消极贡献。结果:在基线(中位年龄64岁)的6332名参与者中,27.9%的人在4年后健康衰老。基于随机森林算法的ML模型在测试数据集上的性能最好(曲线下面积= 0.78,95% CI 0.76-0.80)。正常的身体表现、较大的家庭财富、实足年龄和50至59岁之间的自我认知年龄对结果有积极影响,而身体活动不足、腹部肥胖、基线时不使用互联网或电子邮件对结果有负面影响。结论和意义:基于社区居住中老年人的特征,ML模型可以帮助预测健康老龄化。现有证据可为促进积极老龄化的健康策略提供依据。
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
CiteScore
11.10
自引率
6.60%
发文量
472
审稿时长
44 days
期刊介绍: JAMDA, the official journal of AMDA - The Society for Post-Acute and Long-Term Care Medicine, is a leading peer-reviewed publication that offers practical information and research geared towards healthcare professionals in the post-acute and long-term care fields. It is also a valuable resource for policy-makers, organizational leaders, educators, and advocates. The journal provides essential information for various healthcare professionals such as medical directors, attending physicians, nurses, consultant pharmacists, geriatric psychiatrists, nurse practitioners, physician assistants, physical and occupational therapists, social workers, and others involved in providing, overseeing, and promoting quality
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信