Department of Gastroenterology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, 324, Jing 5 Rd, Ji'nan, Shandong Province, China.
Peking University, 5, Yiheyuan Road, Haidian District, Beijing, China.
Dig Dis Sci. 2024 Dec;69(12):4392-4404. doi: 10.1007/s10620-024-08701-5. Epub 2024 Oct 28.
A high portal pressure gradient (PPG) is associated with an increased risk of failure to control esophagogastric variceal hemorrhage and refractory ascites in patients with decompensated cirrhosis. However, direct measurement of PPG is invasive, limiting its routine use in clinical practice. Consequently, there is an urgent need for non-invasive techniques to assess PPG.
To develop and validate a deep learning model that predicts PPG values for patients with decompensated cirrhosis and identifies those with high-risk portal hypertension (HRPH), who may benefit from early transjugular intrahepatic portosystemic shunt (TIPS) intervention.
Data of 520 decompensated cirrhosis patients who underwent TIPS between June 2014 and December 2022 were retrospectively analyzed. Laboratory and imaging parameters were used to develop an artificial neural network model for predicting PPG, with feature selection via recursive feature elimination for comparison experiments. The best performing model was tested by external validation.
After excluding 92 patients, 428 were included in the final analysis. A series of comparison experiments demonstrated that a three-parameter (3P) model, which includes the international normalized ratio, portal vein diameter, and white blood cell count, achieved the highest accuracy of 87.5%. In two distinct external datasets, the model attained accuracy rates of 85.40% and 90.80%, respectively. It also showed notable ability to distinguish HRPH with an AUROC of 0.842 in external validation.
The developed 3P model could predict PPG values for decompensated cirrhosis patients and could effectively distinguish HRPH.
高门静脉压力梯度（PPG）与失代偿性肝硬化患者食管胃静脉曲张出血和难治性腹水控制失败的风险增加相关。然而，PPG 的直接测量具有侵袭性，限制了其在临床实践中的常规使用。因此，迫切需要非侵入性技术来评估 PPG。
开发和验证一种深度学习模型，用于预测失代偿性肝硬化患者的 PPG 值，并识别那些具有高危门静脉高压（HRPH）的患者，他们可能受益于早期经颈静脉肝内门体分流术（TIPS）干预。
回顾性分析了 2014 年 6 月至 2022 年 12 月期间接受 TIPS 的 520 例失代偿性肝硬化患者的数据。使用实验室和影像学参数开发了一种用于预测 PPG 的人工神经网络模型，并通过递归特征消除进行特征选择进行比较实验。通过外部验证测试最佳表现模型。
排除 92 例患者后，最终分析了 428 例患者。一系列比较实验表明，包括国际标准化比值、门静脉直径和白细胞计数在内的三参数（3P）模型具有最高的准确性 87.5%。在两个不同的外部数据集，该模型的准确率分别为 85.40%和 90.80%。它在外验证中还表现出区分 HRPH 的显著能力，AUROC 为 0.842。
开发的 3P 模型可以预测失代偿性肝硬化患者的 PPG 值，并可以有效区分 HRPH。
