Leveraging Machine Learning to Enhance Occupational Safety and Health in Hospital

Abstract

Objective: This study focuses on utilizing Machine Learning (ML) approaches to improve Occupational Safety and Health (OSH) performance, involving the prediction and prevention of risks based on data.Methods: Analysis of a dataset of 550 OSH incident reports from Metax Cancer Hospital (2019–2023) was conducted using descriptive and inferential statistics. Machine Learning algorithms including decision trees, random forests, and support vector machines were used for prediction and evaluation of OSH results. The models were evaluated using various performance metrics such as accuracy, precision, recall, and AUC.Findings: The analysis made key observations on both workplace environmental factors, safety protocols, and incident occurrence. The ML models demonstrated high prediction performance, with random forests achieving the best accuracy in terms of the correct classification of OSH events. These findings highlight the promise of ML to improve the safety performance of hospitals.Novelty: We propose an original contribution of an ML integration process towards OSH improvement in the hospital ecosystem also characterized with complex safety challenges for which predictive analytics can yield substantial risk mitigation.Research Implications: The study proposes a spillover framework for establishing hospital safety intelligence systems that combines data-driven techniques with traditional OSH management structures. It also highlights the role of real-time predictive analytics in improving OSH outcomes. The study demonstrates the ability of ML to facilitate predictive risk assessment and improve safety.