Smart diagnostic system for cardiovascular, neural, and muscular health using AI-based ECG, EEG, and EMG processing

The purpose of this research is to provide a summary of an artificial intelligence (AI)-approach to support ECG, EEG and EMG signal monitoring and analysis. These physiological signals are important variables for cardiovascular, neurological and muscular health assessment, widely employed in the diagnosis of multiple disorders including heart arrhythmia, epilepsy, sleep disturbances and neuromuscular diseases. Traditional monitoring and interpretation of these signals require manual effort from caregivers, is time-consuming, error-prone, and unscalable. With the help of AI derived from machine learning (ML) and deep learning (DL) health-anomaly detection, classification and prediction become automated, high precision. AI-powered monitoring solutions can understand vast amounts of real-time data, identify health-specific patterns and provide the first line of warning for looming health calamities. In this paper, various AI techniques have been applied to ECG, EEG, and EMG signals including supervised learning, unsupervised learning, Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) as well as hybrid AI models. It is sponsored by the companies who plan to invest in R&D of AI-based monitoring and therefore lacks a motivation to address issues that could act as obstacles for deployment of such models (e.g., data quality, computational complexity, interpretability or the need for large amounts of labeled data). There are research made to find out how IoT, cloud computing, Edge AI for real-time signal processing and remote health-care functionalities when connected.