Table 6 Computational Efficiency of MedFusionNet

From: Hybrid deep learning framework MedFusionNet assists multilabel biomedical risk stratification from imaging and tabular data

Model Variant

AUC

Latency(ms/batch)

GPU memory (gb)

Epochs to converge

Full MedFusionNet

0.945

52

7.8

14

CNN only

0.882

22

3.1

24

ViT only

0.901

38

5.4

20

TCN only

0.855

28

3.6

26

Back to article page