Autonomous Virtual Cognitive Assessment via NLP and Hand Gesture Recognition

Fast-paced and ever-growing advances in Signal Processing and Machine Learning (ML) models have initiated works on autonomous medical monitoring/screening tasks to assess patients' cognitive state. In conventional cognitive assessment systems, a physician evaluates the mental abilities of the brain by rating the patient's numerical, verbal, and logical responses. Development of an autonomous cognitive assessment system that replaces the physician is a critically challenging task. As a first step towards achieving this objective, in this paper an Automated Virtual Cognitive Assessment (AVCA) framework is proposed that integrates Natural Language Processing (NLP) and hand gesture recognition techniques. The proposed AVCA framework provides individual scores in the seven major cognitive domains, i.e., orientation, attention, language, contractual ability, memory, calculation, and reasoning. More specifically, audio and video signals are fed to the framework in a real-time fashion, where semantic and synthetic analysis are performed using NLP techniques and Deep Neural Network (DNN) models. The AVCA's real-time video processing engines interpret patients' video signals to monitor their hand gestures and enable easier interaction. Initial simulation results corroborate effectiveness of the proposed AVCA framework.