Abstract The construction industry remains one of the most hazardous sectors globally, with workplace injuries posing significant risks to human life and economic productivity. Recent advances in Artificial Intelligence (AI) and Data Analytics offer transformative potential for proactive safety management and injury prevention. This paper presents a systematic review of 25 peer-reviewed studies published between 2014 and 2024, focusing on the integration of AI, Machine Learning, Deep Learning, Predictive Analytics, and real-time monitoring technologies in construction safety. Using the Scopus database and guided by PRISMA protocols, studies were screened based on inclusion criteria including construction relevance, data-driven methods, measurable outcomes, and publication quality. The thematic analysis identified six core themes: (1) Predictive Capabilities and Real-time Monitoring, (2) Data Silos and Challenges to Integration, (3) Human-AI Collaboration and Workforce Implications, (4) Risk Identification and Classification, (5) Regulatory Alignment and Ethical Governance, and (6) Regional Disparities in Research and Adoption. The findings indicate that AI-enabled tools, including wearable devices, computer vision, and IoT sensors, enhance hazard detection, predictive risk assessment, and dynamic safety management. However, adoption is hindered by fragmented data systems, limited technical capacity among small and medium contractors, and workforce apprehension. Furthermore, regulatory gaps and regional disparities, particularly in Africa and South Africa, highlight the need for context-specific frameworks and ethical governance. This review provides a foundation for developing an AI-driven, data-enabled model for injury prevention in South African construction, offering insights for policymakers, practitioners, and researchers on leveraging intelligent technologies to improve workplace safety.
NKOSI et al. (2026) studied this question.