Assessing the accuracy of a wireless sensor system for estimating lumbar moments during manual lifting tasks considering the effects of load weight, asymmetry, and height

This study assessed the accuracy of L5/S1 moment estimates calculated with an Inertial Motion Capture (IMC) system during an asymmetrical and variable height lifting task. The effects of load weight, asymmetry, and lifting height on estimates of lumbar moment have not been comprehensively considered in studies using IMC systems. Thirty-six participants engaged in tasks involving three loads, lifting heights, and trunk rotation angles. Lumbar moments were calculated using bottom-up and top-down biomechanical models. Gold-standard Optical Motion Capture (OMC) and Force Plates (FP) were used as the reference. A randomized block partially confounded design was used to compare the root mean square errors (RMSE) between the IMC and OMC-based reference estimates. The IMC system's estimated peak moments were 12%–13% lower than those estimated using the gold standard OMC-BU inverse dynamics, while the RMSE varied between 19 and 21 Nm. A Load*Height interaction was found; a trend was identified where the RMSE values increased as both the load and height levels increased. The angle did not show a significant effect on any of the tested scenarios. A close correspondence between the IMC and OMC-based moment estimates was established, with the load being the main factor affecting the differences between systems. The IMC system shows potential for use in occupational settings to capture data on the lumbar moments of workers, which could be utilized to assess ergonomic risk. •RMSE increases with load at all heights, but the rate of increase varies across different heights.•Asymmetry (angle) and lifting height showed no statistical trends for systematic variability.•OMC and IMC RMSE estimates closely matched, aligning with existing literature.•For Top-Down calculations, assigning load weight to the hands is a viable option to simplify the analysis.•IMC moment underestimation may stem from differences in segment length between models.