A SURVEY ON PREDICTION OF DIABETIC LEVELS USING MACHINE LEARNING ALGORITHAM

A SURVEY ON PREDICTION OF DIABETIC LEVELS USING MACHINE LEARNING ALGORITHAM

Mrs. M. Vasuki1, Dr. T. Amalraj Victoire2, Suresh kumar S3,

1Associate Professor, Department of Master of Computer Applications, Sri Manakula Vinayagar Engineering College (Autonomous), Pondicherry, India

2Associate Professor, Department of Master of Computer Applications, Sri Manakula Vinayagar Engineering College (Autonomous), Pondicherry, India

3PG Student, Department of Master of Computer Applications, Sri Manakula Vinayagar Engineering College (Autonomous), Pondicherry, India

dheshna@gmail.com; amalrajvictoire@gmail.com; sk17kumar7@gmail.com

ABSTRACT

Diabetes is a serious, long-lasting illness that makes blood sugar levels high. It can lead to many health problems. By 2040, it's expected that 1 in 10 adults worldwide will have diabetes, reaching a staggering 642 million people. This is a big concern and needs attention. Scientists are using advanced technology like machine learning to predict diabetes. They studied data from hospital check-ups in Luzhou, China, which had 14 pieces of information about each person. They used two different methods like decision trees, random forests to make predictions. They tested these methods to see how well they worked, using a technique called five-fold cross-validation. To make sure their findings were reliable; they also did separate tests with a large group of healthy people and those with diabetes. Because the data wasn't evenly balanced between healthy and diabetic people, they adjusted it to make it fair. They found that random forests were the best at predicting diabetes accurately, with about 81% accuracy when using all the information available. They also used techniques like principal component analysis and minimum redundancy maximum relevance to make the data easier to work with.

KEYWORDS : Diabetes, blood sugar, predictions, hospital, China, methods, tests, data, balance, forests, accuracy, analysis.