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

ABSTRACT

OBJECTIVES: To identify and 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). 47 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 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.