Skip to main content

Table 4 The mean accuracies and κ-scores on the migbase dataset for the original training set and the transformed datasets obtained using three over-sampling techniques

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

Technique

Accuracy

Cohen κ

Prior knowledge

0.9807±0.0025+

0.9558±0.0057+

ADASYN

0.9775±0.0026−

0.9490±0.0058−

SMOTE

0.9782±0.0034

0.9501±0.0077

Sample weight

0.9762±0.003−

0.9457±0.0069−

None

0.9785±0.0029

0.9508±0.0066

  1. A cell is marked as.+ or.− if the result is a statistically significant (ρ≤0.05) improvement or detriment respectively compared to the baseline (None), according to a bootstrap test
Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us