Research News

Long-term sickness absence (LTSA) is a significant issue, causing productivity decline, financial difficulties, and increased mental health issues, with mental disorders being the most common cause. Occupational stressors are also linked to increased risk of LTSA due to mental disorders (LTSA-MD). 

Osaka Metropolitan University researchers analyzed occupational stressors data from 231,425 Japanese public servants collected between 2011 to 2022 from the Brief Job Stress Questionnaire to predict LTSA-MD using machine learning and sampling methods and to assess their performance. The researchers compared five machine learning models and six sampling methods, random sampling, equal size sampling, SMOTE-synthetic minority oversampling technique, bootstrapping, borderline-SMOTE and ADASYN-adaptive synthetic sampling and addressed class imbalance. The team prioritized average precision (AP) to identify the most promising model–sampling combinations to give the severe class imbalance.

The gradient boosted trees model and bootstrap oversampling method demonstrated the highest AP among all integrations of machine learning and sampling methods, with an AP of 0.040 and a ROC-AUC of 0.81. However, no significant difference in superiority was observed between the combinations of higher-level AP machine learning and sampling methods. The results demonstrated that machine learning models’ predictive ability for LTSA-MD is generally low, requiring further research.

Paper information

Journal: Scientific Reports
Title: Machine learning prediction of long-term sickness absence due to mental disorders using Brief Job Stress Questionnaire data
DOI: 10.1038/s41598-025-32857-3
Authors: Shinichi Iwasaki, Yasuhiko Deguchi, Shohei Okura, Kunio Maekubo, Ayaka Matsunaga, Koki Inoue
Published:  16 December 2025
URL: https://doi.org/10.1038/s41598-025-32857-3

Contact

Shinichi Iwasaki
Graduate School of Medicine
Email: shinichiiwasaki05[at]gmail.com

*Please change [at] to @.