Type 2 Diabetic Prediction Using Machine Learning Algorithm

Sreeja Vishaly M, Umamaheswari k

Abstract


Diabetes mellitus is one of the most important chronic disease  and  has  become  a  major  public  health challenge in the recent world. Currently Machine Learning approaches have been used to analyze and  predict the probability of people getting affected by diabetes. Diabetes can  be effectively identified using the proposed Machine  Learning  technique.  Many techniques  and algorithms were used before for the  prediction of  type 2 diabetes  prediction ,one such model was Multinomial Logistic Regression .Moving a step ahead to improve the diagnostic efficiency, this paper  proposes the use of  Weighted K –Nearest  neighbor  for detecting  the  type-2 Diabetes.  This new approach proves higher effectiveness when compared to Multinomial Logistic Regression. Using Pima Indian Dataset the experiments were performed and it shows that efficiency is higher for weighted KNN when compared to Multinomial Logistic Regression. 


Keywords


Machine Learning; Supervised Model; Weighted KNN; Type 2 Diabetes.

Full Text:

PDF

Refbacks

  • There are currently no refbacks.


 
 
  
 

 

  


About ASRJETS | Privacy PolicyTerms & Conditions | Contact Us | DisclaimerFAQs 

ASRJETS is published by (GSSRR).