Table 4 the abnormality triage model results: the binary classification model that detect normal and abnormal simples.

From: Improving diagnosis accuracy with an intelligent image retrieval system for lung pathologies detection: a features extractor approach

Metrics

Normal

Abnormal

Accuracy

0.937333

0.937333

F1-score

0.889542

0.956259

Negative predictive value

0.935792

0.941542

Positive predictive value

0.941542

0.935792

Precision

0.941542

0.935792

Sensitivity

0.842984

0.977640

Specificity

0.977640

0.842984