Text

Introduction: Despite increased automation, manual heavy lifting remains a health risk for workers. Current assessment methods rely on subjective reports, lacking precision, or complex EMG laboratory methods unsuitable for large-scale workplace monitoring. However, in order to increase organizational/worker health, accurate and feasible measures are needed. Therefore, this study aims to develop and validate LiftID – a simple method for objectively identifying heavy lifting across occupations.

Methods: LiftID comprises three phases. Phase 1: (Laboratory Study - Simplifying Measurement) LiftID's development involves identifying the optimal sensor configuration of wearables (heart rate, PPG sensors, and accelerometers) for detecting physiological and movement patterns associated with heavy lifting in controlled conditions. Phase 2: (Field Study - Ensuring Precision) A comprehensive field study will assess LiftID’s accuracy across occupations, industries, and demographics. Utilizing supervised machine learning, the system will be refined to accurately identify heavy lifting patterns during field scenarios/work tasks. Phase 3: (Feasibility Study - Real-world Applicability) LiftID’s feasibility will be assessed through user interaction. Workers will engage with the system during tasks, evaluating feasibility and data quality. This phase will ensure LiftID’s seamless integration into workplaces for reliable heavy lifting measurements, unlocking its potential for large-scale implementation.

Results: Preliminary findings from pilot studies show promising results in identifying heavy lifting, using PPG and accelerometer signals from simple wearables. Findings from the laboratory study (phase 1) and the field study (phase 2) will be presented at the conference.

Discussion/Conclusion: This research has the potential to bridge the long-standing gap in large-scale identification of heavy lifting. LiftID, incorporating wearable sensors and machine learning, offers a promising solution.