Comparing the prediction performance between the nomogram model
and individual predictors
In the training group, the AUC of the nomogram predicting the
probability of SPTB at < 32 weeks was 0.856 (95%CI:
0.813-0.899), while the AUC of the six meaningful variables was 0.569 to
0.727. The results showed that the prediction accuracy of the nomogram
was significantly higher than that of any single variable(all P<0.05).
The external validation group also proved the advamtage of the nomogram
on predictive accuracy. The AUC of the nomogram in the external
verification set was 0.808 (95%CI: 0.751-0.865), which was
significantly higher than that of either single variable in the
model(all P<0.05)(Figure 3).