Document Type

Article

Publication Date

August 2019

Publication Title

Safety Science

Volume

117

First Page

257

Last Page

262

DOI

10.1016/j.ssci.2019.04.026

Keywords

Injury severity classification, Injury severity prediction, Machine learning

Disciplines

Aviation | Aviation Safety and Security | Engineering | Maintenance Technology | Management and Operations

Abstract

Although machine learning methods have been used as an outcome prediction tool in many fields, their utilization in predicting incident outcome in occupational safety is relatively new. This study tests the performance of machine learning techniques in modeling and predicting occupational incidents severity with respect to accessible information of injured workers in agribusiness industries using workers’ compensation claims. More than 33,000 incidents within agribusiness industries in the Midwest of the United States for 2008–2016 were analyzed. The total cost of incidents was extracted and classified from workers’ compensation claims. Supervised machine learning algorithms for classification (support vector machines with linear, quadratic, and RBF kernels, Boosted Trees, and Naïve Bayes) were applied. The models can predict injury severity classification based on injured body part, body group, nature of injury, nature group, cause of injury, cause group, and age and tenure of injured workers with the accuracy rate of 92–98%. The results emphasize the significance of quantitative analysis of empirical injury data in safety science, and contribute to enhanced understanding of injury patterns using predictive modeling along with safety experts’ perspectives with regulatory or managerial viewpoints. The predictive models obtained from this study can be used to augment the experience of safety professionals in agribusiness industries to improve safety intervention efforts.

Comments

This work can also be read online here.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

COinS