Comparison of feature reduction and feature selection in early diabetes classification

Abstract

Diabetes is one of the common health problems encountered today, and this problem is increasing day by day due to unbalanced and unconscious eating habits. Once a person is diagnosed with diabetes, the likelihood of recovery from this disease is often low. If a person is diagnosed with diabetes, the individual must usually take medication and/or follow a strict diet program for life. While this may be somewhat more manageable for patients living in developed countries, it is often difficult for citizens in developing countries to access these facilities. Because it is generally more difficult and costly to access medicine and healthy nutrition in these countries. Therefore, in this study, ways to diagnose diabetes at an early stage using machine learning techniques are examined. In the study, symptoms such as age, gender, polyuria, polydipsia, sudden weight loss, weakness, polyphagia, genital fungus, blurred vision, itching, irritability, delayed healing, partial paralysis, cramps, hair loss and obesity are examined and which parameters were more effective in diagnosing diabetes.