Optimizing Manual Material Handling Safety: A Hybrid Approach Using NIOSH and Artificial Intelligence

Manual material handling (MMH) tasks are one of the leading causes of musculoskeletal disorders (MSDs) in industrial and logistics environments. This study proposes a hybrid approach that integrates the NIOSH lifting equation with artificial intelligence (AI) technologies, with the aim of optimizing ergonomic evaluation in MMH processes. The developed system combines real-time posture detection through computer vision, using MediaPipe Pose, with automated calculation of the Lifting Index (LI) based on the parameters of the NIOSH method. The research was carried out with a sample of 30 workers in a logistics center, evaluated over a four-week period. The validity of the system was verified by comparing its results with manual expert evaluations, achieving a Pearson’s correlation coefficient of 0.96. The findings showed a 44. 1% reduction in the average LI and 60% decrease in reported incidents. In addition, surveys indicated an improvement in workers’ perception of fatigue and musculoskeletal discomfort. These findings demonstrate that integrating AI with established ergonomic methods provides a practical, accurate and scalable solution to mitigate ergonomic risks, enhancing workplace safety and productivity in logistics operations.