Background: Rebleeding after endoscopic treatment for esophagogastric varices (EGVs) in cirrhotic patients remains a significant clinical challenge, with high mortality rates and limited predictive tools. Current methods, relying on clinical indicators, often lack precision and fail to provide personalized risk assessments. This study aims to develop and validate a novel, non-invasive prediction model based on CT radiomics to predict rebleeding risk within one year of treatment, integrating radiomic features from key organs and clinical data.
Methods: 123 patients were enrolled and divided into rebleeding (n = 44) and non-bleeding group (n = 79) within 1 year after endoscopic treatment of EGVs. The liver, spleen, and the lower part of the esophagus were segmented and the extracted radiomics features were selected to construct liver/spleen/esophagus radiomics signatures based on logistic regression. Clinic-radiomics combined models and multi-organ combined radiomics models were constructed based on independent model scores using logistic regression. The model performance was evaluated by ROC analysis, calibration and decision curves. The continuous net reclassification improvement (NRI) and integrated discrimination improvement (IDI) indices were analyzed.
Results: The clinical-liver combined model had the highest AUC of 0.931 (95% CI: 0.887-0.974), which was followed by the liver-based model with AUC of 0.891 (95% CI: 0.835-0.74). The decision curves also showed that the clinical-liver combined model afforded a greater net benefit compared to other models within the threshold probability of 0.45 to 0.80. Significant improvements in discrimination (IDI, P < 0.05) and reclassification (NRI, P < 0.05) were obtained for clinical-liver combined model compared with the independent ones.
Conclusion: The independent and combined liver-based CT radiomics models performed well in predicting rebleeding within 1 year after endoscopic treatment of EGVs.
Keywords: Endoscopy; Esophagogastric varices; Liver cirrhosis; Radiomics; Tomography; X-Ray computed.
© 2024. The Author(s).