An Efficient Exploration on Big Data Analysis in Adolescent Diabetic Prediction with Deep Learning Techniques

Abstract

The foundation of big data analysis is a massive volume of data. Diabetes is caused by an excess of sugar collected in the blood. Diabetes is one of the most serious chronic health issues. Diabetes sufferers' eyes, hearts, kidneys, and nerves may be damaged if they go undiagnosed. Humans can benefit from automated technologies to assist them in managing their hectic schedules. It inspires us to create a diabetes management scheme for patients that uses an IoT device to track their blood sugar, blood pressure, sports activities, nutrition plan, oxygen level, and ECG data. Machine learning has risen to prominence in healthcare services (HCS) due to its potential to enhance disease prediction. AI and ML approaches have already been used in the HCS field. We give a complete review of DL applications in diabetes in this study. We did a thorough literature review as well as discovered three key areas where this method is used: diabetes diagnosis, glucose control, and diabetes-related complication diagnosis. The search yielded 40 original research articles, from which we summarised essential data on used learning methods, development methods, main outcomes, and performance evaluation baseline techniques. According to the Reviewed Literature, various DL techniques and frameworks attained state-of-the-art performance in many diabetes-related tasks by outperforming conventional ML methods.