An imaging-based machine learning model outperforms clinical risk scores for prognosis of cirrhotic variceal bleeding

• Published in: European radiology Vol. 33; no. 12; pp. 8965 - 8973
• Main Authors: Gao, Yin, Yu, Qian, Li, Xiaohuan, Xia, Cong, Zhou, Jiaying, Xia, Tianyi, Zhao, Ben, Qiu, Yue, Zha, Jun-hao, Wang, Yuancheng, Tang, Tianyu, Lv, Yan, Ye, Jing, Xu, Chuanjun, Ju, Shenghong
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.12.2023; Springer Nature B.V
• Subjects: Biomarkers; Bleeding; Calibration; Cirrhosis; Computed tomography; Decision analysis; Decision making; Deep learning; Diagnostic Radiology; Gastrointestinal; Imaging; Internal Medicine; Interventional Radiology; Learning algorithms; Liver; Machine learning; Medical imaging; Medical prognosis; Medicine; Medicine & Public Health; Neuroradiology; Patients; Performance prediction; Prognosis; Radiology; Radiomics; Risk; Sensitivity; Spleen; Standardization; Test sets; Ultrasound; Deep learning; Liver cirrhosis; Machine learning; Esophageal and gastric varices; Gastrointestinal hemorrhage
• ISSN: 1432-1084; 0938-7994; 1432-1084
• DOI: 10.1007/s00330-023-09938-w

Objectives To develop and validate a machine learning model based on contrast-enhanced CT to predict the risk of occurrence of the composite clinical endpoint (hospital-based intervention or death) in cirrhotic patients with acute variceal bleeding (AVB). Methods This retrospective study enrolled 330 cirrhotic patients with AVB between January 2017 and December 2020 from three clinical centers. Contrast-enhanced CT and clinical data were collected. Centers A and B were divided 7:3 into a training set and an internal test set, and center C served as a separate external test set. A well-trained deep learning model was applied to segment the liver and spleen. Then, we extracted 106 original features of the liver and spleen separately based on the Image Biomarker Standardization Initiative (IBSI). We constructed the Liver-Spleen (LS) model based on the selected radiomics features. The performance of LS model was evaluated by receiver operating characteristics and calibration curves. The clinical utility of models was analyzed using decision curve analyses (DCA). Results The LS model demonstrated the best diagnostic performance in predicting the composite clinical endpoint of AVB in patients with cirrhosis, with an AUC of 0.782 (95% CI 0.650–0.882) and 0.789 (95% CI 0.674–0.878) in the internal test and external test groups, respectively. Calibration curves and DCA indicated the LS model had better performance than traditional clinical scores. Conclusion A novel machine learning model outperforms previously known clinical risk scores in assessing the prognosis of cirrhotic patients with AVB Clinical relevance statement The Liver-Spleen model based on contrast-enhanced CT has proven to be a promising tool to predict the prognosis of cirrhotic patients with acute variceal bleeding, which can facilitate decision-making and personalized therapy in clinical practice. Key Points • The Liver-Spleen machine learning model (LS model) showed good performance in assessing the clinical composite endpoint of cirrhotic patients with AVB (AUC ≥ 0.782, sensitivity ≥ 80%). • The LS model outperformed the clinical scores (AUC ≤ 0.730, sensitivity ≤ 70%) in both internal and external test cohorts.