European journal of gastroenterology & hepatology · 2026
Risk factors and predictive model for transjugular intrahepatic portosystemic shunt dysfunction in cirrhotic patients.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Zhao Yongbing, Xiong Tingwei, Hu Sijie, Zhou Hao, Liu En, Xu Zhengguo, Xie Rui
Аннотация
BACKGROUND: Transjugular intrahepatic portosystemic shunt (TIPS) has been widely adopted for the management of decompensated portal hypertension in cirrhotic patients. However, TIPS dysfunction remains a critical clinical challenge. This study aimed to identify risk factors for TIPS dysfunction and develop a predictive model to assess this complication.
METHODS: A retrospective study was conducted involving cirrhotic patients who underwent TIPS between 2017 and 2024. Among 1052 initially screened patients, 676 were finally included in the analysis. TIPS dysfunction was diagnosed using ultrasound and angiographic evaluations. The dataset was randomly divided into a training set and a validation set at a ratio of 7 : 3. A stepwise logistic regression analysis was performed in the training set to establish a predictive model. Ten-fold cross-validation was used for internal validation, and the validation set was applied for external validation. The predictive discrimination was evaluated using the receiver operating characteristic curve, and the calibration curve was used to assess the consistency. Shapley Additive Explanations analysis was conducted to interpret the model.
RESULTS: Independent risk factors for TIPS dysfunction included age, main portal vein thrombosis, platelets, D value, angle β, and the angle between the selected hepatic vein and inferior vena cava. The model showed good predictive performance with an area under the curve of 0.896 (sensitivity 0.804, specificity 0.844, and accuracy 93.2%) for training set and 0.905 (sensitivity 0.870, specificity 0.826, and accuracy 86.5%) for validation set. The calibration curve from the 10-fold cross-validation in the training set also showed good agreement between prediction and observation. Shapley Additive Explanations analysis showed that Beta value is the most important feature affecting prediction, and allows the estimation of the specific risk of TIPS dysfunction for each individual in the model.
CONCLUSION: This study developed a valid predictive model for assessing risk factors for TIPS dysfunction in cirrhotic patients. Recognition of these risk factors and optimized TIPS shunt management may contribute to improved outcomes in patients undergoing TIPS procedures.
METHODS: A retrospective study was conducted involving cirrhotic patients who underwent TIPS between 2017 and 2024. Among 1052 initially screened patients, 676 were finally included in the analysis. TIPS dysfunction was diagnosed using ultrasound and angiographic evaluations. The dataset was randomly divided into a training set and a validation set at a ratio of 7 : 3. A stepwise logistic regression analysis was performed in the training set to establish a predictive model. Ten-fold cross-validation was used for internal validation, and the validation set was applied for external validation. The predictive discrimination was evaluated using the receiver operating characteristic curve, and the calibration curve was used to assess the consistency. Shapley Additive Explanations analysis was conducted to interpret the model.
RESULTS: Independent risk factors for TIPS dysfunction included age, main portal vein thrombosis, platelets, D value, angle β, and the angle between the selected hepatic vein and inferior vena cava. The model showed good predictive performance with an area under the curve of 0.896 (sensitivity 0.804, specificity 0.844, and accuracy 93.2%) for training set and 0.905 (sensitivity 0.870, specificity 0.826, and accuracy 86.5%) for validation set. The calibration curve from the 10-fold cross-validation in the training set also showed good agreement between prediction and observation. Shapley Additive Explanations analysis showed that Beta value is the most important feature affecting prediction, and allows the estimation of the specific risk of TIPS dysfunction for each individual in the model.
CONCLUSION: This study developed a valid predictive model for assessing risk factors for TIPS dysfunction in cirrhotic patients. Recognition of these risk factors and optimized TIPS shunt management may contribute to improved outcomes in patients undergoing TIPS procedures.