The construction industry remains among the most hazardous sectors globally, facing persistent safety challenges despite advancements in occupational health and safety OHS) measures. The objective of this study is to systematically analyze the use of Artificial Intelligence (AI) in construction safety management and to identify the most effective techniques, data modalities, and validation practices. The method involved a systematic review of 122 peer-reviewed studies published between 2016 and 2025 and retrieved from major academic databases. The selected studies were classified by AI technologies including Machine Learning (ML), Deep Learning (DL), Computer Vision (CV), Natural Language Processing (NLP), and the Internet of Things (IoT), and by their applications in real-time hazard detection, predictive analytics, and automated compliance monitoring. The results show that DL and CV models, particularly Convolutional Neural Network (CNN) and You Only Look Once (YOLO)-based frameworks, are the most frequently implemented for personal protective equipment recognition and proximity monitoring, while ML approaches such as Support Vector Machines (SVM) and ensemble algorithms perform effectively on structured and sensor-based data. Major challenges identified include data quality, generalizability, interpretability, privacy, and integration with existing workflows. The paper concludes that explainable, scalable, and user-centric AI integrated with Building Information Modeling (BIM), Augmented Reality (AR) or Virtual Reality (VR), and wearable technologies is essential to enhance safety performance and achieve sustainable digital transformation in construction environments.
Badhan et al. (2025) studied this question.