| Sumario: | Ergonomic assessments are critical to preventing work-related musculoskeletal disorders. The integration of machine learning with wearable sensor technology offers new approaches to risk assessment by capturing external forces and non-ergonomic working conditions. We conducted a systematic literature search, reviewing 851 studies from PubMed, Web of Science and Embase, and included 15 studies in our analysis. This review summarises and critically discusses these studies, which focus on posture classification, activity duration and external weight estimation in load handling tasks. Although the results are promising, current research covers only a few aspects, with limited emphasis on the measurement of external forces. Furthermore, many studies faced fundamental issues such as small sample sizes and limited access to research data and algorithms. Future advances in this area could greatly benefit from the sharing of datasets and algorithms, thereby increasing the comparability and robustness of findings. Practitioner Summary: Machine learning and wearable sensors show promise for ergonomic risk assessment, focusing on posture, activity and load handling. However, external forces are often neglected and many studies remain laboratory-based with small sample sizes. Future work should improve data sharing and better integrate external load assessments for comprehensive assessments.
|
|---|