Abstract
1 min readThe increasing severity of climate-related workplace hazards poses a significant challenge to occupational health and safety. Public Health and Safety Inspectors are particularly vulnerable to extreme temperatures, air pollution, and high-risk environments, which contribute to immediate physical threats and long-term burnout. This study employs secondary data analysis AI-driven predictive analytics to assess workplace hazards and forecast burnout risks, integrating machine learning models and tools such as eXtreme Gradient Boosting (XGBoost), Random Forest, Autoencoders, and Long Short-Term Memory (LSTMs), adapted for modeling and data processing. The results indicate that predictive models achieved 85–90% accuracy in predicting workplace hazards, with early warning systems reducing workplace incidents by 35% over six months. Burnout risk analysis identified key predictors, including physical hazard exposure (β = 0.76, p < 0.01), extended work hours (>10h/day, +40% risk). Inadequate training (β = 0.68, p < 0.05), adaptive workload scheduling, fatigue monitoring, successfully lowered burnout prevalence by 28%. The models improved hazard detection by incorporating real-time environmental data, while Natural Language Processing (NLP)-based text mining identified stress-related indicators in worker reports. The evidence indicates the effectiveness of the driven predictions in workplace safety, demonstrating its ability to predict, classify, and mitigate occupational risks before escalation. The findings underscore the necessity of reinforcement learning-based adaptive monitoring to optimize workforce well-being. Expanding predictive-driven occupational health frameworks to broader industries could enhance safety protocols and ensure proactive, data-driven risk mitigation strategies for a sustainable workforce and future applications for integrating biometric wearables and real-time physiological monitoring to improve predictive accuracy.
Discussion(0)
No comments yet. Be the first to comment.