Machine learning ensemble approach for healthcare data analytics

In healthcare machine learning is used mainly for disease diagnosis or acute condition detection based on patient data analysis. the proposed work diabetic dataset analysis done hypoglycemia which means lowering of blood glucose level. Often in it observed that imbalanced. Therefore an Ensemble Approach using imbalanced techniques Synthetic Minority Over-sampling Technique and Adaptive oversampling methods with different evaluation like train-test, k-fold, Stratified K-Fold repeat train-test were used. This ensemble approach was implemented K-Nearest Neighbor, Support Vector Machine, Random Forest, Naïve Bayes Logistic Regression classifiers average Stacking-C method thereafter to conclude. Comparative three considerations. The results showed KNN forest gives more stable metric values both balanced dataset. confusion matrix consideration concluded Forest found be better least false negative maximum true positive count. But if train test time taken into then had time. Thus considerations clarity classifier implementation learning.