Clinical Applications of Artificial Intelligence in Occupational Health: A Systematic Literature Review.

Abstract

Objectives: The aims of the study are to identify and to critically analyze studies using artificial intelligence (AI) in occupational health.

Methods: A systematic search of PubMed, IEEE Xplore, and Web of Science was conducted to identify relevant articles published in English between January 2014-January 2024. Quality was assessed with the validated APPRAISE-AI tool.

Results: The 27 included articles were categorized as follows: health risk assessment ( n = 17), return to work and disability duration ( n = 5), injury severity ( n = 3), and injury management ( n = 2). Forty-seven AI algorithms were utilized, with artificial neural networks, support vector machines, and random forest being most common. Model accuracy ranged from 0.60-0.99 and area under the curve (AUC) from 0.7-1.0. Most studies ( n = 15) were of moderate quality.

Conclusions: While AI has potential clinical utility in occupational health, explainable models that are rigorously validated in real-world settings are warranted.