Skip to main content
Fig. 7 | BMC Medical Imaging

Fig. 7

From: Predicting coronary artery calcified plaques using perivascular fat CT radiomics features and clinical risk factors

Fig. 7

Decision curves of combined model. The x-axis represents the patient’s personal threshold probability (for example, x = 0.6 means that the probability of calcification is 60%), and the y-axis represents the net benefit. The green line represents the clinical factor model. The red line represents the combined radiomics model. The blue line represents the hypothesis that all patients have calcified plaques. The thin black line indicates the assumption that no patient has plaques. The net benefit is calculated by subtracting the proportion of all false-positive patients from the proportion of true positives, and then weighted according to the relative harm of previous treatment and the negative consequences of unnecessary treatment. The decision curve shows that the performance of the combined radiomics model is much higher than the remaining three items

Back to article page