Exploring Cloud Computing for Real-Time Analysis and Storage of Data Generated by Medical Devices

Real-time analysis and storage of data measured by native medical instruments, including insulin pump, pacemaker, and wearable monitor, is crucial for the advancement of modern healthcare and that has made cloud computing vital. These devices produce real-time data that has to be analyzed to make timely interventions in the projects. This work discusses the execution of these devices by using cloud- based systems such as AWS and Google Cloud for dealing with the data produced by such devices. Since cloud is inherently scalable and computational, real-time monitoring and analytical capabilities is possible, potentially beneficial in diabetes and arrhythmias. The implementation of Random Forest model together with LSTM models improved the accuracy in diseases diagnosis and patient tracking. Various strategies to tackle the scarcity issue of the real-time data include data augmentation techniques which acted as a powerful strategy used to enhance the performance of the models. The results indicated excellent fitness in outcome anticipation while the evaluation time in the cloud platforms was remarkably low. For patient monitoring, another web-based dashboard was also designed to show information about patient health to allow healthcare professionals monitor their patients from a distance. Of course, the system presented in the paper is effective when it comes to monitoring patients in real time; however, issues like network delay and syncing the devices used in healthcare facilities persist. It will be therefore deduced from this study that cloud computing is an apt answer to the real-time processing and archiving of medical related data with tangible impacts on the quality of patient care. Continuing work will involve including edge computing to enhance the system’s performance in a low connectivity situation with less delay.