COMPARATIVE ANALYSIS OF CLASSIFICATION ALGORITHMS IN PREDICTING EARLY RISK OF DIABETES.

Abstract

Diabetes is one of the most occurring
diseases at present. Irrespective of age and gender,
many people are endan- gered to suffer from
diabetes. Diabetes is a medical condition in which the
sugar levels in the blood rise beyond limits. When
people eat food, glucose is the source of energy for
the cells of the human body. However, if the chemical
called insulin is not released by the pancreas, the levels
of glucose in the human body rise and affect the
metabolism of the human body. Therefore, it is highly
important to predict diabetes in its early stages and
takes steps to prevent it. This is where Machine
Learning comes into play. Machine Learning is known
to be highly useful in cases where prediction is key to
the solution. In the case of predicting diabetes, the
system analyses feature such as sudden weight loss,
genital thrush, and delayed healing. In this project
work, four classification machine learning algorithms
are trained and tested using an open-source dataset
collected from the internet, and their performance is
evaluated and compared.