Prediction of Work-relatedness of Shoulder Musculoskeletal Disorders as by Using Machine Learning

IF 3.5 3区医学 Q1 PUBLIC, ENVIRONMENTAL & OCCUPATIONAL HEALTH

Safety and Health at Work Pub Date : 2025-03-01 DOI:10.1016/j.shaw.2025.01.003

Saemi Jung , Bogeum Kim , Yoon-Ji Kim , Eun-Soo Lee , Dongmug Kang , Youngki Kim

{"title":"Prediction of Work-relatedness of Shoulder Musculoskeletal Disorders as by Using Machine Learning","authors":"Saemi Jung , Bogeum Kim , Yoon-Ji Kim , Eun-Soo Lee , Dongmug Kang , Youngki Kim","doi":"10.1016/j.shaw.2025.01.003","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>This study aimed to develop prediction models for the work-relatedness of shoulder diseases through machine learning algorithms.</div></div><div><h3>Methods</h3><div>The dataset comprised 7,270 cases of 8,302 individuals who applied for occupational diseases and received the final approval decision from the Korea Workers' Compensation and Welfare Service's Disease Evaluation Committee, which is related to shoulder musculoskeletal disorders between January 2020 and December 2021. In this study, demographic analysis and difference of approval rate by shoulder diseases were performed. Additionally, machine learning algorithms, including logistic regression, support vector machine, decision tree, random forest, and the XGBoost, were utilized to construct prediction models for work-relatedness assessment.</div></div><div><h3>Results</h3><div>The performance of each model was evaluated. XGBoost showed an accuracy of 81.64% and an area under the curve of 0.73, and random forest showed an accuracy of 84.46% and an area under the curve of 0.73. Key factors influencing work-relatedness assessment were employment period, physical burden score, gender, and age.</div></div><div><h3>Conclusion</h3><div>The application of various machine learning techniques showed high performance score, representing that it would be helpful to reduce the differences in judgment between occupational environment medicine physicians.</div></div>","PeriodicalId":56149,"journal":{"name":"Safety and Health at Work","volume":"16 1","pages":"Pages 113-121"},"PeriodicalIF":3.5000,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Safety and Health at Work","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2093791125000034","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PUBLIC, ENVIRONMENTAL & OCCUPATIONAL HEALTH","Score":null,"Total":0}

引用次数: 0

Abstract

Background

This study aimed to develop prediction models for the work-relatedness of shoulder diseases through machine learning algorithms.

Methods

The dataset comprised 7,270 cases of 8,302 individuals who applied for occupational diseases and received the final approval decision from the Korea Workers' Compensation and Welfare Service's Disease Evaluation Committee, which is related to shoulder musculoskeletal disorders between January 2020 and December 2021. In this study, demographic analysis and difference of approval rate by shoulder diseases were performed. Additionally, machine learning algorithms, including logistic regression, support vector machine, decision tree, random forest, and the XGBoost, were utilized to construct prediction models for work-relatedness assessment.

Results

The performance of each model was evaluated. XGBoost showed an accuracy of 81.64% and an area under the curve of 0.73, and random forest showed an accuracy of 84.46% and an area under the curve of 0.73. Key factors influencing work-relatedness assessment were employment period, physical burden score, gender, and age.

Conclusion

The application of various machine learning techniques showed high performance score, representing that it would be helpful to reduce the differences in judgment between occupational environment medicine physicians.

查看原文本刊更多论文

求助全文

约1分钟内获得全文求助全文

来源期刊

Safety and Health at Work Social Sciences-Safety Research

CiteScore

6.40

自引率

5.70%

发文量

1080

审稿时长

38 days

期刊介绍： Safety and Health at Work (SH@W) is an international, peer-reviewed, interdisciplinary journal published quarterly in English beginning in 2010. The journal is aimed at providing grounds for the exchange of ideas and data developed through research experience in the broad field of occupational health and safety. Articles may deal with scientific research to improve workers'' health and safety by eliminating occupational accidents and diseases, pursuing a better working life, and creating a safe and comfortable working environment. The journal focuses primarily on original articles across the whole scope of occupational health and safety, but also welcomes up-to-date review papers and short communications and commentaries on urgent issues and case studies on unique epidemiological survey, methods of accident investigation, and analysis. High priority will be given to articles on occupational epidemiology, medicine, hygiene, toxicology, nursing and health services, work safety, ergonomics, work organization, engineering of safety (mechanical, electrical, chemical, and construction), safety management and policy, and studies related to economic evaluation and its social policy and organizational aspects. Its abbreviated title is Saf Health Work.