Skip to main content

Table 4 The effect of graph sparsity factor \(\zeta\) on model performance

From: KAMPNet: multi-source medical knowledge augmented medication prediction network with multi-level graph contrastive learning

\(\zeta\)

Jaccard

F1

PR-AUC

0.01

0.4917

0.6398

0.7176

0.02

0.4908

0.6392

0.7163

0.03

0.4895

0.6384

0.7187

0.04

0.4948

0.6431

0.7199

0.05

0.4916

0.6407

0.7176

0.06

0.4924

0.6407

0.7196

0.07

0.4973

0.6454

0.7195

0.08

0.4922

0.6404

0.7201

0.09

0.4933

0.6413

0.7194

0.10

0.4903

0.6382

0.7175

Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us