Score and Correlation Coefficient-Based Feature Selection for Predicting Heart Failure Diagnosis by Using Machine Learning Algorithms

Table 5

Balancing the dataset by SMOTE.

	Dataset
Phase	Training 80%		Testing 20%
Classes	Did not die during follow-up	Die during follow-up	Did not die during follow-up	Die during follow-up
Before Oversampling	160	79	43	17
After Oversampling	160	160	43	17