An Integrated Framework for Advancing Construction Safety Management: A Systematic Review

This chapter presents a comprehensive and systematic review of machine learning applications in construction safety risk management, following the PRISMA guidelines and Scientometric analysis. The aim of the study is to integrate post-accident analysis, pre-accident analysis, and real-time analysis approaches to develop a holistic construction safety risk management plan. A total of 32 relevant articles were meticulously examined, and their contributions to the three categories of accident analysis were assessed. The PRISMA method guided the selection of articles, ensuring a transparent and systematic review process, while bibliographic analysis facilitated the identification of patterns and trends in the literature. A unique framework was proposed that combines the three approaches for a more comprehensive and holistic construction safety risk management plan. By implementing this data-driven framework, the construction industry can reduce accidents, improve safety outcomes, and promote a proactive safety culture. Future research directions include refining and validating the framework using real-world data, exploring novel machine learning methods, and investigating practical implementation strategies in construction projects.