Related Experiment Videos
Occupational Heat Stress in Industrial Workers: Modifiable Predictors and Machine Learning Risk Classification in
Krishnan Srinivasan1, Dibyajyoti Saikia, Ashikh Seethy
1From the Department of Physiology, All India Institute of Medical Sciences (AIIMS), Guwahati, India (K.S., M.B., A. Sinha, S.L., S.M.A., B.H., J.K.); Department of Pharmacology, All India Institute of Medical Sciences (AIIMS), Guwahati, India (D.S.); and Department of Biochemistry, All India Institute of Medical Sciences (AIIMS), Guwahati, India (A. Seethy).
Journal of Occupational and Environmental Medicine
|July 27, 2026
Summary
Occupational heat stress is influenced by modifiable factors like work hours and hydration. Machine learning, specifically Random Forest, can effectively classify heat stress risk for prevention.
Area of Science:
- Occupational health
- Environmental science
- Data science
Background:
- Occupational heat stress is an increasing risk to worker health and productivity, particularly in developing nations.
- This study focused on identifying controllable risk factors for heat stress in industrial settings.
- Machine learning models were assessed for their ability to categorize heat stress risk.
Purpose of the Study:
- To investigate modifiable predictors of occupational heat stress.
- To evaluate machine learning models for heat stress risk classification.
- To inform prevention strategies for industrial workers.
Main Methods:
- A cross-sectional study involved 1300 workers from chemical, construction, and packaging industries.
- Data collected included environmental, physiological, occupational, and behavioral factors via questionnaires and field measurements.
- Multivariable regression and machine learning models were employed for analysis.
Main Results:
- Manual labor, extended work hours, alcohol consumption, and insufficient hydration were linked to increased heat stress risk.
- Access to water, showers, and appropriate uniforms demonstrated protective effects.
- The Random Forest model achieved the highest performance with 72.6% accuracy and an AUC of 0.777.
Conclusions:
- Workplace and behavioral factors significantly influence occupational heat stress.
- Machine learning, particularly Random Forest, provides a robust tool for monitoring and early intervention of heat stress.
- Findings support the development of targeted prevention strategies.