Utilization of Machine Learning in Analyzing Post-incident State of Occupational Injuries in Agro-Manufacturing Industries
Advances in Safety Management and Human Performance: Proceedings of the AHFE 2020 Virtual Conferences on Safety Management and Human Factors, and Human Error, Reliability, Resilience, and Performance, July 16-20, 2020, USA
Pedro M. Arezes, Ronald L. Boring
Due to the high frequency and costs of occupational incidents in agro-manufacturing operations, as well as substantial impact of occupational injuries on labor-market outcomes, predicting the post-incident state of an injury and identifying its contributory factors is vital to protect workers, improve workplace safety, and reduce overall costs of injuries. This study evaluates the performance of machine learning algorithms in classifying post-incident outcomes of occupational injuries in agro-manufacturing operations. Injury factors extracted from 14,000 workers’ compensation claims recorded between 2008 and 2016 in the Midwest region of the United States were used to develop machine learning models. The models predicted incident outcomes based on injury details with an overall accuracy rate of 78%, and high accuracy rate for medical post-incident state (97–98%). The results emphasize the significance of quantitative analysis of empirical injury data in safety science, and contributes to enhanced understanding of occupational incidents root causes using predictive modeling along with safety experts’ perspective.
Decision trees, Machine learning, Occupational incident analysis, Occupational safety, Safety management
Aviation and Technology
Fatemeh Davoudi Kakhki, Steven A. Freeman, and Gretchen A. Mosher. "Utilization of Machine Learning in Analyzing Post-incident State of Occupational Injuries in Agro-Manufacturing Industries" Advances in Safety Management and Human Performance: Proceedings of the AHFE 2020 Virtual Conferences on Safety Management and Human Factors, and Human Error, Reliability, Resilience, and Performance, July 16-20, 2020, USA (2020): 3-9. https://doi.org/10.1007/978-3-030-50946-0_1