Ensemble stacking classifier model for prediction of diabetes

Abstract

Diabetes,  being  a  chronic  condition,  possesses  the  capacity  to instigate  a global healthcare catastrophe. This condition can be managed and potentially cured  with  prompt  diagnosis  and  treatment.  Integrating  machine  learning technology with medical science enables precise prognosis of an individual’s susceptibility to diabetes. The proposed work presents the ensemble stacking classifier  model.  This  efficient  and  effective  diabetes  prediction  model predicts  a  patient’s  diabetes  risk  by  combining  the  output  of  multiple machine-learning   techniques   into   a   single   model.   The performance parameters   of   four   distinct machine   learning   classification   algorithmsK-nearest  neighbors  (KNN), random  forest  (RF), support  vector  machine (SVM), and decision tree (DT) are compared in this study with those of the proposed stacked classifiermodel. The suggested model is developed using ensemble methods, where the previously discussed algorithms are integrated to create the base classifier layer of the stack classifier. The meta-classifier is implemented  in  the  form  of the  logistic  regression(LR)algorithm.  Upon evaluating the performance of both the developed model and its algorithms, it  is  proved  that  the  proposed  model  attains  a  testing  accuracy  of  88.5%, surpassing the accuracy of all baseline classification algorithms. As a result, this work  determines  that  the ensemble  stacking  classifiermodel exhibits higher  prediction  accuracy  than  the  base  classifier  algorithms.  This  finding underscores  the  model’s  potential  as  a  viable  instrument  for  predicting diabetes in individuals.