Biomechanical risk classification according to NIOSH in workers affected by occupational pathologies

Abstract

Manual material handlings could imply biomechanical risk and therefore could cause several work-related musculoskeletal disorders. For this reason, the National Institute for Occupational Safety and Health (NIOSH) proposed an equation to define biomechanical risk classes. In this work, we studied the feasibility of a logistic regression model fed with inertial features to classify biomechanical risk classes according to the Revised NIOSH Lifting Equation (RNLE). A single inertial measurement unit placed on the subject's sternum was used to acquire linear acceleration and angular velocity during lifting tasks. The signals were elaborated in order to extract several features in time and frequency domains. The logistic regression model, fed with the extracted features, showed good results to discriminate NIOSH classes with an accuracy, sensitivity and specificity equal to 83.5 %, 84.4 %, 82.2 % respectively. This work indicated that a logistic regression model fed with specific inertial features is able to discriminate risk classes according to the RNLE and therefore could be a valid tool to assess the biomechanical risk in an automatic way with a view to the reintegration of the disabled person in the workplace.