Diabetes Mellitus Prediction using Machine Learning Algorithms (original) (raw)

Diabetes mellitus is related to the high sugar level in the blood. According to the International Diabetes Federation (IDF), there are currently 422 million diabetic people worldwide or 7.7% of the world's population, and this number is expected to rise to 350 billion by 2030. Furthermore, 3.8 million deaths are attributable to diabetes complications every year with, an annual increase of 2.7% from 1990. In this paper, we have proposed the system to predict diabetes using a machine learning algorithm. Early detection of diabetes mellitus would lead to a decrease in the mortality rate. This paper presents an algorithm for naïve Bayes and KNN, which we have implemented using C#. KNN gave the highest accuracy (100%) compared to other algorithms. The other algorithms used are naïve Bayes, Decision tree, Logistic Regression, Random Forest, Support vector machine. A dataset that we have used to build this product contains 21 columns. This product helps in decreasing the mortality rate.