Development of a Hand-Arm Vibration Syndrome (HAVS) Detection Tool for Construction Workers

Abstract

Hand-Arm Vibration Syndrome (HAVS) results from prolonged exposure to hand-held vibrating tools, such as jackhammers, drills, and grinders. Construction workers frequently use these tools for extended periods and are therefore prone to developing HAVS over time. HAVS can affect the vascular, neurological, and musculoskeletal systems of workers, leading to both short-term and long-term disability. Despite its severity, HAVS is often under-reported due to a lack of awareness and delayed detection. Existing methods for detecting HAVS primarily focus on assessing the vibration levels of hand-held equipment rather than the condition of the exposed workers. This study proposes a machine learning tool to assess the hand and arm conditions of construction workers exposed to vibrating equipment. The tool is capable of analyzing hand drawings to detect hand tremors, an early symptom of HAVS. This innovative approach offers a potential solution for the regular monitoring of construction workers' health, enabling early detection and management of HAVS symptoms.