How Accurately Can Wearable Sensors Assess Low Back Disorder Risks during Material Handling? Exploring the Fundamental Capabilities and Limitations of Different Sensor Signals

Abstract

Low back disorders (LBDs) are a leading occupational health issue. Wearable sensors, such as inertial measurement units (IMUs) and/or pressure insoles, could automate and enhance the ergonomic assessment of LBD risks during material handling. However, much remains unknown about which sensor signals to use and how accurately sensors can estimate injury risk. The objective of this study was to address two open questions: (1) How accurately can we estimate LBD risk when combining trunk motion and under-the-foot force data (simulating a trunk IMU and pressure insoles used together)? (2) How much greater is this risk assessment accuracy than using only trunk motion (simulating a trunk IMU alone)? We developed a data-driven simulation using randomized lifting tasks, machine learning algorithms, and a validated ergonomic assessment tool. We found that trunk motion-based estimates of LBD risk were not strongly correlated (r range: 0.20–0.56) with ground truth LBD risk, but adding under-the-foot force data yielded strongly correlated LBD risk estimates (r range: 0.93–0.98). These results raise questions about the adequacy of a single IMU for LBD risk assessment during material handling but suggest that combining an IMU on the trunk and pressure insoles with trained algorithms may be able to accurately assess risks.

The Effect of Sensor Feature Inputs on Joint Angle Prediction across Simple Movements

“…The result of adding relevant types of input sensors to improve the prediction accuracy was in line with prior research [ 43 , 44 ]. For instance, Nurse et al (2023) showed how the combination of pressure insole data with trunk motion increased low back disorder risk estimates from a range of r = 0.20–0.56 to r = 0.93–0.98 [ 43 ].…”

“…The result of adding relevant types of input sensors to improve the prediction accuracy was in line with prior research [ 43 , 44 ]. For instance, Nurse et al (2023) showed how the combination of pressure insole data with trunk motion increased low back disorder risk estimates from a range of r = 0.20–0.56 to r = 0.93–0.98 [ 43 ]. Substituting trunk IMU with thigh or pelvis IMU did not significantly reduce the prediction accuracy; however, removing more relevant sensors, such as force estimates from pressure insoles, significantly reduced low-back-loading estimation accuracy during MMH [ 45 ].…”

IoT-Based Solution for Detecting and Monitoring Upper Crossed Syndrome

“…Table 1 shows that most papers in the literature that deal with spinal detection use an inertial measurement unit (IMU) that contains an accelerometer, gyroscope, and magnetometer, yielding all three axis planes. Since IMU sensors can detect spinal disorders, they can be applied to different wearable devices [ 13 , 14 , 15 , 16 , 17 , 18 , 20 , 21 , 22 , 23 , 24 ]. Specifically, some papers dealt with musculoskeletal disorders that are related to UCS such as identifying hunched and slouched back [ 14 ], tracking and monitoring the sitting posture [ 15 ], and embedding IMU sensors in clothing to continuously monitor back posture [ 17 , 19 , 20 ].…”