Development of a Platform to Assess the Risk of Musculoskeletal Disorders in Manual Load Handling Activities - Preliminary Results.

Risk identification on workstations is a crucial step to prevent the occurrence of musculoskeletal disorders (MSD) in workers. The available methods and tools used by ergonomists to assess and estimate the risk related to manual handling of loads under repetitive work cycles are usually biased by the inter-evaluator error that can lead to a subjective determination of work-related risks due to the application of, mainly, observational methods. This paper shows the preliminary results of a platform to assess the risk of musculoskeletal disorders during manual load-handling tasks using an instrumented system and using the National Institute for Occupational Safety & Health (NIOSH) method. Eight healthy subjects were measured during lifting activities using an optical-based and inertial-based motion capture systems. The developed software implements a semi-automated instrumented version of the NIOSH method, helping the evaluator with automated calculations of body segment locations, displacements and joint angles making it possible to obtain a objective risk classification. Also, we achieved a reduction of 85% in the time for the estimation of the necessary factors for the digital evaluation methodology, making the proposed platform a promising and attractive alternative for its application in real environments for risk assessments.Occupational health relevance- This work proposes an assistance tool for the detection of musculoskeletal disorders in activities related to manual handling of loads, essential to initiate modification strategies in the workplace, reduce the occurrence of occupational diseases and reduce the time of risk classification.

Utilizing Motion Capture Systems for Instrumenting the OCRA Index: A Study on Risk Classification for Upper Limb Work-Related Activities.

In the search to enhance ergonomic risk assessments for upper limb work-related activities, this study introduced and validated the efficiency of an inertial motion capture system, paired with a specialized platform that digitalized the OCRA index. Conducted in a semi-controlled environment, the proposed methodology was compared to traditional risk classification techniques using both inertial and optical motion capture systems. The inertial method encompassed 18 units in a Bluetooth Low Energy tree topology network for activity recording, subsequently analyzed for risk using the platform. Principal outcomes emphasized the optical system's preeminence, aligning closely with the conventional technique. The optical system's superiority was further evident in its alignment with the traditional method. Meanwhile, the inertial system followed closely, with an error margin of just ±0.098 compared to the optical system. Risk classification was consistent across all systems. The inertial system demonstrated strong performance metrics, achieving F1-scores of 0.97 and 1 for "risk" and "no risk" classifications, respectively. Its distinct advantage of portability was reinforced by participants' feedback on its user-friendliness. The results highlight the inertial system's potential, mirroring the precision of both traditional and optical methods and achieving a 65% reduction in risk assessment time. This advancement mitigates the need for intricate video setups, emphasizing its potential in ergonomic assessments.

Predicting risk of falls in elderly using a single Inertial Measurement Unit on the lower-back by estimating spatio-temporal gait parameters.

One of the consequences of aging is the increased risk of falls, especially when someone walks in unknown or uncontrolled environments. Usually, gait is evaluated through observation and clinical assessment scales to identify the state and deterioration of the patient's postural control. Lately, technological systems for bio-mechanical analysis have been used to determine abnormal gait states being expensive, difficult to use, and impossible to apply in real conditions. In this article, we explore the ability of a system based on a single inertial measurement unit located in the lower back to estimate spatio-temporal gait parameters by analyzing the signals available in the Physionet repository "Long Term Movement Monitoring Database" which, together with automatic classification algorithms, allow predicting the risk of falls in the elderly population. Different classification algorithms were trained and evaluated, being the Support Vector Machine classifier with a third-degree polynomial kernel, cost function C = 2 with the best performance, with an Accuracy = 59%, Recall = 91%, and F1- score = 71%, providing promising results regarding a proposal for the quantitative, online and realistic evaluation of gait during activities of daily living, which is where falls actually occur in the target population. Clinical Relevance - This work proposes an early risk of falls detection tool, essential to start preventive treatment strategies to maintain the independence of the elderly through a non-invasive, simple, and low-cost alternative.