聚类分析揭示了职业健康队列中具有不同风险概况和缺勤模式的亚组。

IF 2.5 3区 医学 Q1 REHABILITATION
Anniina Anttila, Mikko Nuutinen, Riikka-Leena Leskelä, Mark van Gils, Anu Pekki, Riitta Sauni
{"title":"聚类分析揭示了职业健康队列中具有不同风险概况和缺勤模式的亚组。","authors":"Anniina Anttila, Mikko Nuutinen, Riikka-Leena Leskelä, Mark van Gils, Anu Pekki, Riitta Sauni","doi":"10.1007/s10926-025-10319-x","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>Using unsupervised and supervised machine learning methods, we aimed to identify clinically relevant groups of employees with similar characteristics and analyze the association of long and short sickness absence periods with these groups.</p><p><strong>Methods: </strong>The participants were 12,099 employees of various occupations in Finnish companies. The data comprised 104 variables from medical records including data on sickness absences and a questionnaire used between 2011 and 2019 in health examinations. The latent dimensions for the employees were defined by principal component analysis to reduce the number of variables. Clusters were calculated using the K-means algorithm from datapoints expressed by the resulting five principal components. Logistic regression analyses were used to assess the associations of the clusters with long (> 30 days) and repetitive short (1-10 days) sickness absence (SA) episodes.</p><p><strong>Results: </strong>Employees in cluster one indicated positive managerial performance and workplace atmosphere, and employees had the least of both short and long SA. Cluster two indicated deficiencies related to managerial performance and workplace atmosphere. Cluster three had deficiencies mainly related to mood and depression and cluster four had cardiovascular diseases. Employees in cluster five reported many symptoms, especially dizziness and sensory symptoms, and had the highest occurrence of repetitive short SA. Cluster six indicated deficiencies related to work ability and had the highest occurrence of a long SA episode during follow-up.</p><p><strong>Conclusion: </strong>Unsupervised and supervised machine learning methods identified six clinically coherent employee clusters, providing information on typical combinations of characteristics and risk profiles of sickness absence.</p>","PeriodicalId":48035,"journal":{"name":"Journal of Occupational Rehabilitation","volume":" ","pages":""},"PeriodicalIF":2.5000,"publicationDate":"2025-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Cluster Analysis Reveals Subgroups with Different Risk Profiles and Sickness Absence Patterns in an Occupational Health Cohort.\",\"authors\":\"Anniina Anttila, Mikko Nuutinen, Riikka-Leena Leskelä, Mark van Gils, Anu Pekki, Riitta Sauni\",\"doi\":\"10.1007/s10926-025-10319-x\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Purpose: </strong>Using unsupervised and supervised machine learning methods, we aimed to identify clinically relevant groups of employees with similar characteristics and analyze the association of long and short sickness absence periods with these groups.</p><p><strong>Methods: </strong>The participants were 12,099 employees of various occupations in Finnish companies. The data comprised 104 variables from medical records including data on sickness absences and a questionnaire used between 2011 and 2019 in health examinations. The latent dimensions for the employees were defined by principal component analysis to reduce the number of variables. Clusters were calculated using the K-means algorithm from datapoints expressed by the resulting five principal components. Logistic regression analyses were used to assess the associations of the clusters with long (> 30 days) and repetitive short (1-10 days) sickness absence (SA) episodes.</p><p><strong>Results: </strong>Employees in cluster one indicated positive managerial performance and workplace atmosphere, and employees had the least of both short and long SA. Cluster two indicated deficiencies related to managerial performance and workplace atmosphere. Cluster three had deficiencies mainly related to mood and depression and cluster four had cardiovascular diseases. Employees in cluster five reported many symptoms, especially dizziness and sensory symptoms, and had the highest occurrence of repetitive short SA. Cluster six indicated deficiencies related to work ability and had the highest occurrence of a long SA episode during follow-up.</p><p><strong>Conclusion: </strong>Unsupervised and supervised machine learning methods identified six clinically coherent employee clusters, providing information on typical combinations of characteristics and risk profiles of sickness absence.</p>\",\"PeriodicalId\":48035,\"journal\":{\"name\":\"Journal of Occupational Rehabilitation\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":2.5000,\"publicationDate\":\"2025-07-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Occupational Rehabilitation\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1007/s10926-025-10319-x\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"REHABILITATION\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Occupational Rehabilitation","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s10926-025-10319-x","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"REHABILITATION","Score":null,"Total":0}
引用次数: 0

摘要

目的:使用无监督和有监督机器学习方法,我们旨在识别具有相似特征的临床相关员工群体,并分析长病假和短病假与这些群体的关联。方法:研究对象为芬兰公司各类职业的12099名员工。这些数据包括医疗记录中的104个变量,包括病假数据和2011年至2019年健康检查中使用的问卷。为了减少变量的数量,我们采用主成分分析法来定义员工的潜在维度。聚类使用K-means算法从结果的五个主成分表示的数据点计算。采用Logistic回归分析来评估长时间(50 ~ 30天)和重复性短时间(1 ~ 10天)缺勤(SA)发作的相关性。结果:聚类一的员工对管理绩效和工作氛围表现出积极的态度,员工对短期和长期SA的态度最低。第二组指出与管理业绩和工作场所气氛有关的缺陷。第三类缺乏主要与情绪和抑郁有关,第四类有心血管疾病。聚类5的员工报告了许多症状,尤其是头晕和感觉症状,重复性短SA的发生率最高。第六组显示与工作能力有关的缺陷,在随访期间最长的SA发作发生率最高。结论:无监督和有监督的机器学习方法确定了六个临床连贯的员工集群,提供了关于病假特征和风险概况的典型组合的信息。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Cluster Analysis Reveals Subgroups with Different Risk Profiles and Sickness Absence Patterns in an Occupational Health Cohort.

Purpose: Using unsupervised and supervised machine learning methods, we aimed to identify clinically relevant groups of employees with similar characteristics and analyze the association of long and short sickness absence periods with these groups.

Methods: The participants were 12,099 employees of various occupations in Finnish companies. The data comprised 104 variables from medical records including data on sickness absences and a questionnaire used between 2011 and 2019 in health examinations. The latent dimensions for the employees were defined by principal component analysis to reduce the number of variables. Clusters were calculated using the K-means algorithm from datapoints expressed by the resulting five principal components. Logistic regression analyses were used to assess the associations of the clusters with long (> 30 days) and repetitive short (1-10 days) sickness absence (SA) episodes.

Results: Employees in cluster one indicated positive managerial performance and workplace atmosphere, and employees had the least of both short and long SA. Cluster two indicated deficiencies related to managerial performance and workplace atmosphere. Cluster three had deficiencies mainly related to mood and depression and cluster four had cardiovascular diseases. Employees in cluster five reported many symptoms, especially dizziness and sensory symptoms, and had the highest occurrence of repetitive short SA. Cluster six indicated deficiencies related to work ability and had the highest occurrence of a long SA episode during follow-up.

Conclusion: Unsupervised and supervised machine learning methods identified six clinically coherent employee clusters, providing information on typical combinations of characteristics and risk profiles of sickness absence.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
5.80
自引率
12.10%
发文量
64
期刊介绍: The Journal of Occupational Rehabilitation is an international forum for the publication of peer-reviewed original papers on the rehabilitation, reintegration, and prevention of disability in workers. The journal offers investigations involving original data collection and research synthesis (i.e., scoping reviews, systematic reviews, and meta-analyses). Papers derive from a broad array of fields including rehabilitation medicine, physical and occupational therapy, health psychology and psychiatry, orthopedics, oncology, occupational and insurance medicine, neurology, social work, ergonomics, biomedical engineering, health economics, rehabilitation engineering, business administration and management, and law.  A single interdisciplinary source for information on work disability rehabilitation, the Journal of Occupational Rehabilitation helps to advance the scientific understanding, management, and prevention of work disability.
×
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