Table 5 Modification of the voting type to conduct an ablation study, where the sign () and (✘) refer to the identical and dropped accuracy, respectively.

From: BOO-ST and CBCEC: two novel hybrid machine learning methods aim to reduce the mortality of heart failure patients

Case study

Voting type

ALL features

FI features

IG features

Acceptability

3

Hard

89.74

92.5

92.40

Weighted

90

92.59

91.25

Soft

89.74

93.67

92.40