Machine Learning Approach to Study Social Determinants of Chronic Illness in India: A Comparative Analysis.

IF 0.9 4区 医学 Q4 PUBLIC, ENVIRONMENTAL & OCCUPATIONAL HEALTH Indian journal of public health Pub Date : 2024-01-01 Epub Date: 2024-04-04 DOI:10.4103/ijph.ijph_296_23
Aakanksha Agarwala, Barun Barua, Genevieve Chyrmang, Manab Deka, Kangkana Bora
{"title":"Machine Learning Approach to Study Social Determinants of Chronic Illness in India: A Comparative Analysis.","authors":"Aakanksha Agarwala, Barun Barua, Genevieve Chyrmang, Manab Deka, Kangkana Bora","doi":"10.4103/ijph.ijph_296_23","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Several studies on noncommunicable diseases (NCDs) have been carried out worldwide, the basis of most of which is the identification of risk factors-modifiable (or behavioral) and metabolic. Majority of the NCDs are due to sociodemographic factors, lifestyle, and behavior, which can be prevented to a great extent. Thus, it is a health challenge and a necessity to identify such factors of NCDs.</p><p><strong>Objectives: </strong>The objective is to make a thorough systematic and comparative analysis of diverse machine learning (ML) classifiers and identify the best-performing model to study social determinants of NCDs.</p><p><strong>Materials and methods: </strong>We used data from the Longitudinal Ageing Study in India, and predicted the prevalence of NCDs based on a set of sociodemographic, lifestyle, and behavioral risk factors by conducting a comparative analysis among 25 different algorithms.</p><p><strong>Results: </strong>Evaluating the performance metrics, the random forest model was found to be the most-suited method with 87.9% accuracy and hence chosen as the final model for the analysis. The model's performance was optimized by a hyper-parameter tuning process using grid-search with a 5-fold cross-validation strategy and results suggested that it was able to make accurate predictions on new instances.</p><p><strong>Conclusion: </strong>The epidemic of chronic illness cannot be completely addressed without comprehending the social determinants. With advancements in medical and health-care industry, ML has been applied to analyze diseases based on clinical parameters. This work is an attempt by the authors to explore and encourage the use of ML in the field of social epidemiology.</p>","PeriodicalId":13298,"journal":{"name":"Indian journal of public health","volume":"68 1","pages":"50-54"},"PeriodicalIF":0.9000,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Indian journal of public health","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.4103/ijph.ijph_296_23","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/4/4 0:00:00","PubModel":"Epub","JCR":"Q4","JCRName":"PUBLIC, ENVIRONMENTAL & OCCUPATIONAL HEALTH","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Several studies on noncommunicable diseases (NCDs) have been carried out worldwide, the basis of most of which is the identification of risk factors-modifiable (or behavioral) and metabolic. Majority of the NCDs are due to sociodemographic factors, lifestyle, and behavior, which can be prevented to a great extent. Thus, it is a health challenge and a necessity to identify such factors of NCDs.

Objectives: The objective is to make a thorough systematic and comparative analysis of diverse machine learning (ML) classifiers and identify the best-performing model to study social determinants of NCDs.

Materials and methods: We used data from the Longitudinal Ageing Study in India, and predicted the prevalence of NCDs based on a set of sociodemographic, lifestyle, and behavioral risk factors by conducting a comparative analysis among 25 different algorithms.

Results: Evaluating the performance metrics, the random forest model was found to be the most-suited method with 87.9% accuracy and hence chosen as the final model for the analysis. The model's performance was optimized by a hyper-parameter tuning process using grid-search with a 5-fold cross-validation strategy and results suggested that it was able to make accurate predictions on new instances.

Conclusion: The epidemic of chronic illness cannot be completely addressed without comprehending the social determinants. With advancements in medical and health-care industry, ML has been applied to analyze diseases based on clinical parameters. This work is an attempt by the authors to explore and encourage the use of ML in the field of social epidemiology.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
研究印度慢性病社会决定因素的机器学习方法:比较分析
背景:全世界已开展了多项关于非传染性疾病(NCDs)的研究,其中大部分研究的基础是确定可改变(或行为)和代谢的风险因素。大多数非传染性疾病都是由社会人口因素、生活方式和行为造成的,在很大程度上是可以预防的。因此,确定这些非传染性疾病的因素是一项健康挑战,也是一项必要工作:目的:对各种机器学习(ML)分类器进行全面系统的比较分析,并找出性能最佳的模型,以研究非传染性疾病的社会决定因素:我们使用了印度纵向老龄化研究的数据,并通过对 25 种不同算法进行比较分析,根据一系列社会人口、生活方式和行为风险因素预测了非传染性疾病的发病率:对性能指标进行评估后发现,随机森林模型是最合适的方法,准确率高达 87.9%,因此被选为最终的分析模型。通过使用网格搜索和 5 倍交叉验证策略的超参数调整过程对模型的性能进行了优化,结果表明该模型能够对新实例进行准确预测:如果不了解社会决定因素,就无法彻底解决慢性病流行的问题。随着医疗和保健行业的发展,基于临床参数的 ML 已被应用于分析疾病。这项工作是作者探索和鼓励在社会流行病学领域使用 ML 的一次尝试。
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 去求助
来源期刊
Indian journal of public health
Indian journal of public health PUBLIC, ENVIRONMENTAL & OCCUPATIONAL HEALTH-
CiteScore
2.40
自引率
0.00%
发文量
92
审稿时长
21 weeks
期刊介绍: Indian Journal of Public Health is a peer-reviewed international journal published Quarterly by the Indian Public Health Association. It is indexed / abstracted by the major international indexing systems like Index Medicus/MEDLINE, SCOPUS, PUBMED, etc. The journal allows free access (Open Access) to its contents and permits authors to self-archive final accepted version of the articles. The Indian Journal of Public Health publishes articles of authors from India and abroad with special emphasis on original research findings that are relevant for developing country perspectives including India. The journal considers publication of articles as original article, review article, special article, brief research article, CME / Education forum, commentary, letters to editor, case series reports, etc. The journal covers population based studies, impact assessment, monitoring and evaluation, systematic review, meta-analysis, clinic-social studies etc., related to any domain and discipline of public health, specially relevant to national priorities, including ethical and social issues. Articles aligned with national health issues and policy implications are prefered.
期刊最新文献
Severe Pneumonia and Cytomegalovirus Coinfection in Infants with Human Immunodeficiency Virus Infection. Social and Cultural Influences on Genetic Counseling Acceptability: A Mixed-Methods Study on Beta-Thalassemia Carriers Among Graduate Students in West Bengal, India. Time to Revisit COTPA as Herbs Become Perilous. Training Needs Assessment Should Be Introduced as a Competency for Postgraduate Training in Community Medicine in India. "Fit India Movement" Promotes WHO's Physical Activity Recommendations: Some Issues to Consider.
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1