Automated Quality Assessment of Hand Washing Using Deep Learning
This work aims to improve hand hygiene compliance among medical professionals to prevent infectious disease transmission, offering an incremental step towards automated quality control.
This paper addresses the problem of ensuring medical staff adhere to WHO hand washing guidelines by developing neural networks to automatically recognize different washing movements. Using pre-trained models like MobileNetV2 and Xception, the system achieved over 64% accuracy in recognizing these movements.
Washing hands is one of the most important ways to prevent infectious diseases, including COVID-19. Unfortunately, medical staff does not always follow the World Health Organization (WHO) hand washing guidelines in their everyday work. To this end, we present neural networks for automatically recognizing the different washing movements defined by the WHO. We train the neural network on a part of a large (2000+ videos) real-world labeled dataset with the different washing movements. The preliminary results show that using pre-trained neural network models such as MobileNetV2 and Xception for the task, it is possible to achieve >64 % accuracy in recognizing the different washing movements. We also describe the collection and the structure of the above open-access dataset created as part of this work. Finally, we describe how the neural network can be used to construct a mobile phone application for automatic quality control and real-time feedback for medical professionals.