Mobile AI Stroke Health App: A Novel Mobile Intelligent Edge Computing Engine based on Deep Learning models for Stroke Prediction – Research and Industry Perspective

Abstract

Artificial Intelligence (AI) techniques for mobile Health (mHealth) in remote medical systems has opened up new opportunities in healthcare systems. Combining AI techniques to the existing Internet of Medical things(IoMT) will enhance the quality of care that patients receive at home remotely or The success establishment of Smart living environments while still having access to the resources within reach to respond to any medical diagnostic crisis. Mobile Health is a steadily growing field in telemedicine. However, building a real AI for Mobile Edge computing is a challenging problem due to the complexities of receiving IoT medical sensors data, data analysis and Deep Learning algorithm complexity programming for Mobile Edge Computing Complexities, especially when we tackle real-time environments of wearable technologies. In this paper, we introduce a New Real-Time Artificial Intelligence and IoMT Engine for Mobile Health Edge Computing technology. Its main goal to is to Predict stroke diseases as an urgent case that may cause that may cause problems like weakness, numbness, vision problems, confusion, trouble walking or moving or talking. It may also cause sudden death. However, today ’s Mobile Health research still missing an intelligent remote diagnosis engine for Stroke Prediction and Diagnosis for patient emergency cases This research work proposes a Hybrid Intelligent remote diagnosis technique for Mobile Health Application for Stroke Prediction and diagnosis. The hybrid techniques are Sparse Auto-Encoders Deep Learning (DL) technique and Group Handling method (GMDH) neural networks. Both techniques depend on dataset of Electromyography (EMG) signals, which provides significant source of information for identification of stroke normal and abnormal motions. The State of the art of the presented Artificial Intelligence mHealth App is new and the proposed techniques achieves high accuracies as Sparse Auto-Encoders reaches almost 98% for Stroke Diagnosis and GMDH Neural Networks proves to be a good technique for monitoring the EMG signal of the same patient case with average accuracies 98.60% to average 96.68% of the signal prediction. This paper also presents conclusion and future works for the proposed overall new system architecture.