Towards Diabetes Mellitus Prediction Based on Machine- Learning
Houda El Bouhissi, Rafa E. Al-Qutaish, Amine Ziane, Kamal Amroun, Nabila Yaya, Melissa Lachi
Abstract
Diabetes is a chronic pathology caused by a disorder of the pancreas, which leads to a high concentration of sugar in the blood and can affect the functioning of the body system at. This disease may cause damage to the heart, blood vessels, eyes, kidneys, and nerves. Therefore, the development of a suitable system for effectively earlier diagnosing diabetic patients using personal, historical, and medical information is required. This system can assist patients in preventing this disease and its complications. Several machine-learning techniques were used for the predictive analysis of diabetes. In this paper, we conduct a review of the most important works related to diabetes prediction and propose an approach for the prediction of gestational diabetes using Deep Neural Network (DNN), Support Vector Machine (SVM), and Random Forest (RF) classifiers. The experiment was conducted using a real dataset from Frankfurt Hospital indicating that the Random Forest algorithm provides more accuracy.