Burnout Risk Prediction with Machine Learning and an Interactive Interface for Organizational Use

• Bruno W. G. Teodosio UNICAP
• Mário J. O. T. Lira UPE
• Pedro H. M. Araújo UNICAP / UPE
• Lucas R. C. Farias CESAR School

DOI: https://doi.org/10.5753/eniac.2026.31367

Resumo

Burnout is a work-related syndrome associated with emotional exhaustion, depersonalization, and reduced personal accomplishment. This paper evaluates burnout risk prediction using the public Are Your Employees Burning Out? dataset. Three supervised regression models were compared: K-Nearest Neighbors, Random Forest, and Support Vector Machine. The models were assessed with 30-fold cross-validation using the coefficient of determination (R²), followed by paired statistical comparisons. Support Vector Machine obtained the highest average performance (R² = 0.84), although the absolute differences among the models were small. The selected model was also integrated into a Streamlit interface to support non-technical organizational use. The results indicate that supervised learning can support exploratory mental health analytics, provided that predictions are interpreted with ethical governance, human oversight, and context-specific validation.

Palavras-chave: Burnout Prediction, Support Vector Machine, Mental Health Analytics, Supervised Learning, Organizational Analytics, Streamlit Interface

Referências

Adapa, P. et al. (2022). Predicting burnout among healthcare professionals using explainable machine learning models. In Studies in Health Technology and Informatics.

Freudenberger, H. J. (1974). Staff burnout. Journal of Social Issues.

Kaggle (2024). Are your employees burning out? hackerearth employee burnout challenge. [link]. Accessed: 25 November 2024.

Kamaruzzaman, M., Othman, M., Hassan, R., Abdul Rahman, A. W., and Mahri, N. (2023). EEG features for driver’s mental fatigue detection: A preliminary work. International Journal on Perceptive and Cognitive Computing, 9(1):88–94.

Lara-González, J. et al. (2021). Comparison of machine learning models for burnout prediction. ECORFAN Journal-Democratic Republic of Congo.

Pillai, M., Liu, C. C., Kwong, E., Kratzke, I., Charguia, N., Mazur, L., and Adapa, K. (2024). Using an explainable machine learning approach to prioritize factors contributing to healthcare professionals’ burnout. Journal of Intelligent Information Systems, pages 1–12.

Pustułka-Piwnik, A. (2014). Burnout among physiotherapists: Demographic and organizational factors. Medycyna Pracy.

Reddy, R. E. and Santhi, K. (2024a). Exploring mental fatigue and burnout in the workplace: A survival analysis approach. EAI Endorsed Transactions on Pervasive Health and Technology.

Reddy, R. E. and Santhi, K. (2024b). The survival analysis of mental fatigue utilizing the estimator of Kaplan–Meier and Nelson–Aalen. In Pareek, P., Gupta, N., and Reis, M. J. C. S., editors, Cognitive Computing and Cyber Physical Systems. Springer, Cham.

Tang, X. et al. (2023). Risk factors for burnout among shift workers: A counterfactual explanation approach. In IEEE EMBS International Conference on Biomedical and Health Informatics.