Heterogeneity in the association between internet use and dementia among older adults: A machine-learning analysis

IF 3.5 3区 医学 Q2 GERIATRICS & GERONTOLOGY
Atsushi Nakagomi , Katsunori Kondo , Koichiro Shiba
{"title":"Heterogeneity in the association between internet use and dementia among older adults: A machine-learning analysis","authors":"Atsushi Nakagomi ,&nbsp;Katsunori Kondo ,&nbsp;Koichiro Shiba","doi":"10.1016/j.archger.2025.105912","DOIUrl":null,"url":null,"abstract":"<div><h3>Background &amp; aims</h3><div>Internet use among older adults may reduce the risk of dementia, but it remains unknown how the effects vary across individuals. The aim of this study was to rigorously examine heterogeneity in the association between internet use and dementia among older adults with a machine learning approach.</div></div><div><h3>Methods</h3><div>This cohort study used data from the Japan Gerontological Evaluation Study involving functionally independent adults aged 65 or older (n = 5,451). The exposure, internet use a few times a month or more often, was assessed with the 2016 survey (baseline) and covariates (potential confounders and effect modifiers) were assessed with the 2013 survey (pre-baseline). Follow-up continued until 2022, identifying 5.5-year dementia onset (n = 549) using the public long-term care insurance system. Using the generalized random forest algorithm, we estimated how the association between internet use and dementia onset during a 5.5-year follow-up period varies by pre-baseline sociodemographic characteristics and health conditions.</div></div><div><h3>Results</h3><div>Internet use was on average associated with a lower risk of dementia (estimated population average effect = -0.033; 95 % CI: -0.051, -0.016). However, we found evidence of between-individual heterogeneity in this association, where internet use appeared more beneficial among individuals who reported middle income, higher education levels, and were socially and physically inactive at the pre-baseline wave.</div></div><div><h3>Conclusions</h3><div>Internet use may disproportionately benefit people based on socioeconomic status, suggesting equity concerns of universal implementation. Understanding such effect heterogeneity can inform more targeted public health interventions.</div></div>","PeriodicalId":8306,"journal":{"name":"Archives of gerontology and geriatrics","volume":"136 ","pages":"Article 105912"},"PeriodicalIF":3.5000,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Archives of gerontology and geriatrics","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0167494325001694","RegionNum":3,"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

Background & aims

Internet use among older adults may reduce the risk of dementia, but it remains unknown how the effects vary across individuals. The aim of this study was to rigorously examine heterogeneity in the association between internet use and dementia among older adults with a machine learning approach.

Methods

This cohort study used data from the Japan Gerontological Evaluation Study involving functionally independent adults aged 65 or older (n = 5,451). The exposure, internet use a few times a month or more often, was assessed with the 2016 survey (baseline) and covariates (potential confounders and effect modifiers) were assessed with the 2013 survey (pre-baseline). Follow-up continued until 2022, identifying 5.5-year dementia onset (n = 549) using the public long-term care insurance system. Using the generalized random forest algorithm, we estimated how the association between internet use and dementia onset during a 5.5-year follow-up period varies by pre-baseline sociodemographic characteristics and health conditions.

Results

Internet use was on average associated with a lower risk of dementia (estimated population average effect = -0.033; 95 % CI: -0.051, -0.016). However, we found evidence of between-individual heterogeneity in this association, where internet use appeared more beneficial among individuals who reported middle income, higher education levels, and were socially and physically inactive at the pre-baseline wave.

Conclusions

Internet use may disproportionately benefit people based on socioeconomic status, suggesting equity concerns of universal implementation. Understanding such effect heterogeneity can inform more targeted public health interventions.
老年人网络使用与痴呆之间的异质性:一项机器学习分析
背景,目的老年人使用互联网可能会降低患痴呆症的风险,但目前还不清楚这种影响在个体之间有何差异。本研究的目的是通过机器学习方法严格检查老年人互联网使用与痴呆症之间关系的异质性。方法:本队列研究使用来自日本老年学评估研究的数据,涉及65岁及以上功能独立的成年人(n = 5,451)。使用2016年的调查(基线)评估暴露程度,即每月使用互联网几次或更频繁,并使用2013年的调查(基线前)评估协变量(潜在混杂因素和效果调节剂)。随访持续到2022年,使用公共长期护理保险系统确定5.5年痴呆发病(n = 549)。使用广义随机森林算法,我们估计了在5.5年随访期间,互联网使用与痴呆发病之间的关系如何随基线前社会人口统计学特征和健康状况而变化。结果互联网使用平均与较低的痴呆风险相关(估计人群平均效应= -0.033;95% ci: -0.051, -0.016)。然而,我们发现了这种关联中个体间异质性的证据,即在基线前浪潮中,中等收入、高等教育水平、社交和身体不活跃的个体中,互联网使用似乎更有益。结论基于社会经济地位,互联网使用可能对人群产生不成比例的好处,提示普遍实施的公平性问题。了解这种效应的异质性可以为更有针对性的公共卫生干预提供信息。
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
7.30
自引率
5.00%
发文量
198
审稿时长
16 days
期刊介绍: Archives of Gerontology and Geriatrics provides a medium for the publication of papers from the fields of experimental gerontology and clinical and social geriatrics. The principal aim of the journal is to facilitate the exchange of information between specialists in these three fields of gerontological research. Experimental papers dealing with the basic mechanisms of aging at molecular, cellular, tissue or organ levels will be published. Clinical papers will be accepted if they provide sufficiently new information or are of fundamental importance for the knowledge of human aging. Purely descriptive clinical papers will be accepted only if the results permit further interpretation. Papers dealing with anti-aging pharmacological preparations in humans are welcome. Papers on the social aspects of geriatrics will be accepted if they are of general interest regarding the epidemiology of aging and the efficiency and working methods of the social organizations for the health care of the elderly.
×
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