Figure 5

(A) The calibration curves of differential diagnosis nomogram prediction in the cohort. The x-axis showed the predicted liver cancer. The y-axis showed the actual diagnosis. The solid line indicated the performance of the nomogram, of which an almost close to the diagonal dotted line presented a good predicted capability. (B) The ROC curve for the simplified differential diagnosis nomograms to verify the predicted capability of the model. (C) The decision curve analysis for the simplified nomogram. The y-axis measures the net benefit. The blue line showed the differential diagnosis nomogram. The thin solid line presented the assumption that all patients were distinguished. The thin thick solid line showed the assumption that no patients were distinguished. The decision curve showed that if the threshold probability of a patient or doctor is >6%, using the nomogram to diagnose HAE or liver cancer could acquire much more benefit. Within this range, net benefit was comparable, with several overlaps, on the basis of the differential diagnosis nomogram.