Abstract
Background & aims: To develop and validate a novel machine learning-based radiomic model (RM) for diagnosing high bleeding risk esophageal varices (HREV) in cirrhosis. Methods: In training cohort, total 218 cirrhotic patients for mild esophageal varices (EV) and 240 for HREV RM were enrolled for training and internal validation. In external validation cohort, 159 and 340 cirrhotic patients were respectively used for mild EV and HREV RM validation. Interesting regions of liver, spleen, and esophagus were labeled on the portal venous-phase enhanced CT images. RM was assessed by area under the receiver operating characteristic curves (AUROC), sensitivity, specificity, calibration and decision curve analysis (DCA). Results: The AUROC of mild EV RM in training and internal validation was 0.943 and 0.732, sensitivity and specificity was 0.863, 0.773 and 0.763, 0.763. The AUROC, sensitivity and specificity was 0.654, 0.773 and 0.632 in external validation. Interestingly, the AUROC of HREV RM in training and internal validation was 0.983 and 0.834, sensitivity and specificity was 0.948, 0.916 and 0.977, 0.969. The AUROC, sensitivity and specificity was 0.736, 0.690 and 0.762 in external validation. Calibration and DCA indicated RM had good performance in clinical practice. Compared with Baveno VI and its expanded criteria, HREV RM had a higher accuracy and net reclassification improvement reached 49.0% and 32.8%. Conclusion: A novel non-invasive RM for diagnosing HREV in cirrhotic patients with highly accuracy was developed. However, this RM still needs to be validated by a multi-center large cohort.
A Novel Machine Learning-Based Radiomic Model for Diagnosing High Bleeding Risk Esophageal Varices in Cirrhotic Patients
