Table 3 Performance Comparison of Early, Late, and Hybrid Models, which presents the Best and Mean±SD is the mean and standard deviation across metrics in 15 evaluation runs. Metrics include, Accuracy, AUC, Precision, Recall, and F1-score.

From: Integrative multimodal hybrid data fusion for mortality prediction

Model

Accuracy

AUC

Precision

Recall

F1-score

Best

Mean±SD

Best

Mean±SD

Best

Mean±SD

Best

Mean±SD

Best

Mean±SD

Early Fusion

0.9220

0.9081±0.0142

0.9460

0.9371±0.0176

0.7536

0.7730±0.0990

0.7602

0.6562±0.1242

0.7569

0.6927±0.0425

Late Fusion

0.9350

0.9183±0.0090

0.9680

0.9517±0.0099

0.7843

0.7333±0.0361

0.8187

0.7407±0.0608

0.8011

0.7358±0.0401

Hybrid Fusion

0.9360

0.9206±0.0094

0.9619

0.9530±0.0111

0.8233

0.7551±0.0425

0.7632

0.7268±0.0572

0.7921

0.7388±0.0334

Back to article page