A Logistic Regression Model for Biomechanical Risk Classification in Lifting Tasks

Abstract

Lifting is one of the most potentially harmful activities for work-related musculoskeletal disorders (WMSDs), due to exposure to biomechanical risk. Risk assessment for work activities that involve lifting loads can be performed through the NIOSH (National Institute of Occupational Safety and Health) method, and specifically the Revised NIOSH Lifting Equation (RNLE). Aim of this work is to explore the feasibility of a logistic regression model fed with time and frequency domains features extracted from signals acquired through one inertial measurement unit (IMU) to classify risk classes associated with lifting activities according to the RNLE. Furthermore, an attempt was made to evaluate which are the most discriminating features relating to the risk classes, and to understand which inertial signals and which axis were the most representative. In a simplified scenario, where only two RNLE variables were altered during lifting tasks performed by 14 healthy adults, inertial signals (linear acceleration and angular velocity) acquired using one IMU placed on the subject's sternum during repeated rhythmic lifting tasks were automatically segmented to extract several features in the time and frequency domains. The logistic regression model fed with significant features showed good results to discriminate "risk" and "no risk" NIOSH classes with an accuracy, sensitivity and specificity equal to 82.8%, 84.8% and 80.9%, respectively. This preliminary work indicated that a logistic regression model-fed with specific inertial features extracted by signals acquired using a single IMU sensor placed on the sternum-is able to discriminate risk classes according to the RNLE in a simplified context, and therefore could be a valid tool to assess the biomechanical risk in an automatic way also in more complex conditions (e.g., real working scenarios).

Keywords: Revised NIOSH Lifting Equation; biomechanical risk assessment; feature extraction; health monitoring; inertial measurement unit; lifting; occupational ergonomics; statistical learning; wearable sensors; work-related musculoskeletal disorders.

Figure 1

Mobility Lab System: access point, docking station, movement monitor, Mobility Lab software.

Figure 2

OPAL sensor and sensor positioning sketches. (a) OPAL sensor positioning sketch. Z axis is orthogonal (positive direction: towards the reader) to the x-y plane. (b) Isometric view (sketch) of the external shape of an OPAL sensor. (a): reproduced with permission from Martini et al., J. Physiother. Res.; published by Insight Medical Publishing (iMedPub), 2021. (b): reproduced with permission from Donisi et al., Sensors; published by Multidisciplinary Publishing Institute (MDPI), 2021.

Figure 3

Phases of the lifting tasks: initial rest position, lifting weight with squatting technique upwards, upper destination point, lifting weight with squatting technique downwards, lower destination point and rest position.

Figure 4

Determination of the ROI (start and end points) corresponding to the lifting by means of the application of Savitzky-Golay filter on the inertial signal (e.g., x-axis acceleration) and an empirical threshold.