Table 6 Performance comparison between stacking and soft voting ensembles over 10 runs. Results presented as mean ± standard deviation. Statistical significance was assessed using a paired t-test.

From: Improved pulmonary embolism detection in CT pulmonary angiogram scans with hybrid vision transformers and deep learning techniques

Metric

Stacking (Mean ± Std)

Soft Voting (Mean ± Std)

P-Value

Acc

97.43 ± 0.13%

97.06 ± 0.10%

< 0.0010

Pre

98.12 ± 0.15%

97.70 ± 0.18%

< 0.0012

Rec

96.50 ± 0.17%

96.00 ± 0.16%

< 0.0010

F1-score

97.42 ± 0.14%

96.83 ± 0.15%

< 0.0010

AUROC

98.85 ± 0.14%

98.40 ± 0.15%

< 0.0011

Back to article page