Journal of occupational and environmental medicine. 2025 May 28. doi: 10.1097/JOM.0000000000003468 Q31.42025

Occupational mental health: an investigation of risk indicators using interpretable machine learning techniques

可解释机器学习技术在职业心理健康风险指标调查中的应用研究翻译改进

André Luis Schneider¹, Juliana Sampaio Do Carmo¹, Érick Oliveira Rodrigues, Sergio Luiz Ribas Pessa¹

作者单位 +展开

作者单位

¹ Graduate Program in Production & Systems Engineering (PPGEPS), Federal University of Technology - Paraná (UTFPR), Pato Branco, PR, Brazil.

DOI: 10.1097/JOM.0000000000003468 PMID: 40490394

摘要中英对照阅读

Objective: To apply interpretable machine learning to identify key factors influencing work-related mental health cases to support early intervention.

Methods: Using 1,117 records from Brazil's Notifiable Diseases Information System for the period from 2007 to 2022, five machine learning models were developed to classify mental health cases as mild or severe. SHAP analysis was employed to rank and interpret the most influential predictors.

Results: The decision tree model achieved 82.9% accuracy (92 of 111 cases classified, including 83 of 85 severe cases), while the support vector machine reached 82.0% accuracy (91 of 111 correct, including 84 of 85 severe). Key determinants included work removal, protective measures, and regional factors. High-risk occupations comprised energy/water operators, legal professionals, and engineers.

Conclusions: Interpretable machine learning models effectively predict mental health outcomes, revealing actionable socio-demographic and occupational risk factors for targeted interventions.

Keywords: Classification Models; Machine Learning; Mental Disorders; Occupational Health; SHAP Analysis.

Keywords：occupational mental health; risk indicators; interpretable machine learning

目标：

将可解释的机器学习应用于识别影响工作相关心理健康案件的关键因素，以支持早期干预。

方法：

使用来自巴西《通报疾病信息系统》2007年至2022年期间的1,117份记录，开发了五个机器学习模型来将心理健康案例分类为轻度或重度。通过SHAP分析对最重要的预测因子进行排名和解释。

结果：

决策树模型实现了82.9%的准确率（在111个案例中正确分类了92个，包括85个严重案例中的83个），而支持向量机达到了82.0%的准确率（在111个案例中正确分类了91个，包括85个严重案例中的84个）。关键决定因素包括工作调动、保护措施和区域因素。高风险职业包括能源/水运营商、法律专业人士和工程师。

结论：

可解释的机器学习模型有效预测心理健康结果，揭示了有针对性干预的社会人口学和职业风险因素。

关键词：

分类模型；机器学习；精神障碍；职业健康；SHAP分析。

关键词：职业心理健康; 风险指标; 可解释机器学习

翻译效果不满意？用Ai改进或寻求AI助手帮助，对摘要进行重点提炼

相关内容

期刊名：Journal of occupational and environmental medicine

缩写：J OCCUP ENVIRON MED

ISSN：1076-2752

e-ISSN：1536-5948

IF/分区：1.4/Q3

文章目录更多期刊信息

全文链接

官方链接

PMC全文

引文链接

复制

已复制！

格式：

Occupational mental health: an investigation of risk indicators using interpretable machine learning techniques

可解释机器学习技术在职业心理健康风险指标调查中的应用研究翻译改进

Prediction of Cisplatin-Induced Acute Kidney Injury Using an Interpretable Machine Learning Model and Electronic Medical Record Information

基于电子病历信息使用可解释机器学习模型预测顺铂致急性肾损伤

Application of interpretable machine learning models to improve the prediction performance of ionic liquids toxicity

解释性机器学习模型在离子液体毒性预测中的应用

Implementation of Bartlett matched-field processing using interpretable complex convolutional neural network

基于可解释复数卷积神经网络的巴特利特匹配场处理方法

Counterfactual Causal-Effect Intervention for Interpretable Medical Visual Question Answering

一种用于可解释的医学视觉问答的反事实因果效应干预方法

Atomic Adsorption Energies Prediction on Bimetallic Transition Metal Surfaces Using an Interpretable Machine Learning-Accelerated Density Functional Theory Approach

基于可解释机器学习加速的密度泛函理论方法预测双金属表面原子吸附能

Disruption evaluation in end-to-end semiconductor supply chains via interpretable machine learning

基于可解释机器学习的端到端半导体供应链中断评估研究

Boosting the Accuracy of Commercial Real Estate Appraisals: An Interpretable Machine Learning Approach

提高商用房地产评估准确性的可解释机器学习方法研究

Estimation of urban AQI based on interpretable machine learning

基于可解释机器学习的城镇AQI估算

A Novel Tropical Geometry-Based Interpretable Machine Learning Method: Pilot Application to Delivery of Advanced Heart Failure Therapies

一种新型的基于热带几何的可解释机器学习方法：用于终末期心力衰竭治疗的初步应用研究

Occupational mental health: an investigation of risk indicators using interpretable machine learning techniques

可解释机器学习技术在职业心理健康风险指标调查中的应用研究 翻译改进

Prediction of Cisplatin-Induced Acute Kidney Injury Using an Interpretable Machine Learning Model and Electronic Medical Record Information

基于电子病历信息使用可解释机器学习模型预测顺铂致急性肾损伤

Application of interpretable machine learning models to improve the prediction performance of ionic liquids toxicity

解释性机器学习模型在离子液体毒性预测中的应用

Implementation of Bartlett matched-field processing using interpretable complex convolutional neural network

基于可解释复数卷积神经网络的巴特利特匹配场处理方法

Counterfactual Causal-Effect Intervention for Interpretable Medical Visual Question Answering

一种用于可解释的医学视觉问答的反事实因果效应干预方法

Atomic Adsorption Energies Prediction on Bimetallic Transition Metal Surfaces Using an Interpretable Machine Learning-Accelerated Density Functional Theory Approach

基于可解释机器学习加速的密度泛函理论方法预测双金属表面原子吸附能

Disruption evaluation in end-to-end semiconductor supply chains via interpretable machine learning

基于可解释机器学习的端到端半导体供应链中断评估研究

Boosting the Accuracy of Commercial Real Estate Appraisals: An Interpretable Machine Learning Approach

提高商用房地产评估准确性的可解释机器学习方法研究

Estimation of urban AQI based on interpretable machine learning

基于可解释机器学习的城镇AQI估算

A Novel Tropical Geometry-Based Interpretable Machine Learning Method: Pilot Application to Delivery of Advanced Heart Failure Therapies

一种新型的基于热带几何的可解释机器学习方法：用于终末期心力衰竭治疗的初步应用研究

可解释机器学习技术在职业心理健康风险指标调查中的应用研究翻译改进