Diabetes type i self-monitoring using mobile devices: architecture blueprint using cloud and machine learning

Abstract

The modern capabilities of smartphones, cloud technologies and machine learning techniques have created possibilities of creation of innovative approaches to monitor chronic deseases. This study represents an architecture blueprint aimed at improving the efficiency of type I diabetes self-monitoring with help of mobile devices. The approach is based on a machine learning algorithm trained on diverse data sets, which offers users insights and personalized health recommendations. The platform helps improving the accuracy of diabetes tracking, provides people with immediate feedback based on history analytical data. The study highlights the merge of medical and technology fields and set a baseground for future improvements.