Kat Usop,Visiting lecturer of Biomedical Engineering at Mohammad 5 University, ENSET-Rabat
With the emergence of mobile applications for instant messaging and data transfer, doctors have adopted these software technologies to better serve the patients especially in times of emergency. Colleagues have the possibility to send a photo of x-ray, cross-sections and wound or any other medical data via these platforms to seek advice, approval or precaution prior to deciding on a set of medical diagnoses. This process has shown convenience for certain doctors in order to shorten the time needed for a medical procedure. The hindrance of such existing platforms are that (1) the personal and professional contacts are shuffled in one platform, thus, disordering the barrier between personal and professional cyber transaction. (2) The media files that are transmitted and received are not segregated according to its type and other signifying labels, thus, the media in the doctor’s phone are merged with other personal media files. (3) The doctors have no way to track back conversations into the specific medical cases due to the lack of a classification of instant messaging in the existing platforms.
This research study seeks to help connect doctors to their respective colleagues during medical diagnosis via a mobile application with a platform designed to accommodate the instant messaging according to the medical case, classification of media files according to facility, time of shift and medical case, and give the doctors the ability to segregating their personal instant messaging from the professional ones, for a timely and organized medical diagnosis and close-knit decision support system. The methodology to be used shall be an application using native (Android, iOS) software development, the classification shall be implemented by integrating supervised learning in Microsoft Azure Cloud Technology for data collection, organization and segregation using “multinomial Classification” problem-solving techniques.
Keywords: medical diagnosis, big data, medical data, artificial intelligence, expert system, mobile application, android development, mobile health, supervised learning, multinomial classification, Microsoft Azure Cloud Technologies