Infection control, Hand hygiene, Movement classification, Artificial intelligence, Inertial sensors
Abstract
During the COVID-19 pandemic, the crucial need for proper hand hygiene as a preventive measure to avoid the spread of the virus has been emphasized. This practice plays a fundamental role in preventing Healthcare-Associated Infections (HAIs). Studies have shown that the correct hand hygiene technique, such as the six-step technique recommended by the World Health Organization (WHO) and the three-step technique, can eliminate 99.9% of transient hand colonization among healthcare professionals. In light of this, the present work presents the development of an algorithm for classifying hand hygiene movements using inertial sensors (accelerometers and gyroscopes) and artificial intelligence. The proposed methodology consists of five stages: data collection, pre-processing, data segmentation, feature extraction, and classification, detailed throughout the article. The presented results demonstrate an accuracy of 89.3%, indicating the feasibility of the proposed methodology for the correct classification of hand hygiene technique.
