Skip to main content
Fig. 6 | Respiratory Research

Fig. 6

From: A decision tree built with parameters obtained by computed tomographic pulmonary angiography is useful for predicting adverse outcomes in non-high-risk acute pulmonary embolism patients

Fig. 6

The predictive abilities of the decision tree and other predictive scores. The ROC curve built by the recursive partitioning analysis predictive model for all enrolled patients revealed that the area under the ROC was 0.858 (95%CI: 0.775–0.941). For all enrolled patients, the ROC-AUC revealed that the area of risk stratification, Bova scores and sPESI scores were 0.740 (95%CI: 0.690–0.786), 0.739 (95%CI: 0.689–0.785) and 0.548 (95%CI: 0.493–0.602), respectively. The predictive ability of the decision tree was better than others in the ROC-AUC (0.118, 95%CI: 0.0139–0.222, p < 0.05; 0.119, 95%CI: 0.00306–0.234, p < 0.05 and 0.310, 95%CI: 0.229–0.391, p < 0.05)

Back to article page

Respiratory Research

ISSN: 1465-993X

Contact us