Heart Disease Prediction Using Decision Tree in Comparison with k-Nearest Neighbor to Improve Accuracy

The target of the task is to foresee coronary illness by Novel Decision Tree (DT) in examination with k-Nearest Neighbor (KNN) utilizing Cleveland dataset. Coronary Disease forecasting performed applying (N=20) and algorithms. algorithm uses tree structure make decisions. K-nearest neighbor an easy approach solve regression classification problems. heart dataset utilized for identification prediction. data consists 76 attributes however, only 14 features are selected that help diagnosing a patient healthy or affected. Accuracy cardiovascular risk prediction using k-NN 68.9% & decision 81.9%. There exists statistical significant difference between DT 0.035(p<0.05). appears perform significantly better than disease