Skip to main content

Table 5 The accuracy rates on the public migbase dataset for the different feature extraction techniques

From: A decision support system to follow up and diagnose primary headache patients using semantically enriched data

Technique

Accuracy

Cohen κ

Only RBF

0.9788±0.0115

0.9522±0.0251

Original + RBF

0.9692±0.0167−

0.9303±0.0368−

Only WF

0.9339±0.0384−

0.8588±0.0809−

Original + WF

0.9795±0.0155

0.9534±0.0342

Original + WF + RBF

0.9692±0.0150−

0.9301±0.0323−

Original

0.9784±0.0107

0.9508±0.0237

  1. A cell is marked as.+ or.− if the result is a statistically significant improvement or detriment respectively compared to the baseline (Original), according to a bootstrap test
Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us