Diabetes Mellitus Prediction Through Interactive Machine Learning Approaches

Diabetes is a long-term illness that has the potential to disrupt the global healthcare system. Based on the survey report of International Diabetes Federation (IDF), there are around 382 millions of people, who are affected by diabetes worldwide. This number will have increased to 592 million by 2035. Diabetes is a disease characterized by an increase in blood glucose levels. Elevated blood glucose is characterized by frequent urination, increased thirst and increased hunger. Diabetic consequences include kidney failure, blindness, heart failure, amputations and stroke, to name a few. When we ingest food, our bodies turn it into sugars or glucose. Machine learning is a new field of data science that investigates how computers learn from their prior experiences. The objective of this study is to develop a system that can detect diabetes in a patient early and more accurately using a combination of machine learning techniques. The objective of this study is to use four supervised machine learning algorithms to predict diabetes: Support Vector Machine, logistic regression, random forest and k-nearest neighbour. Each algorithm is used to calculate the model's accuracy. The model with the best accuracy for predicting diabetes is then picked. This paper proposes a comparative study for accurately predicting diabetes mellitus. This research also aims to develop a more efficient approach for identifying diabetic disease.