Division of Gastroenterology &, Hepatology Mayo Clinic, Rochester, MN.
Norwegian PSC Research Center, Division of Surgery, Inflammatory Medicine and Transplantation, Oslo University Hospital, Rikshospitalet, Oslo, Norway.
Hepatology. 2020 Jan;71(1):214-224. doi: 10.1002/hep.30085. Epub 2018 Dec 28.
Improved methods are needed to risk stratify and predict outcomes in patients with primary sclerosing cholangitis (PSC). Therefore, we sought to derive and validate a prediction model and compare its performance to existing surrogate markers. The model was derived using 509 subjects from a multicenter North American cohort and validated in an international multicenter cohort (n = 278). Gradient boosting, a machine-based learning technique, was used to create the model. The endpoint was hepatic decompensation (ascites, variceal hemorrhage, or encephalopathy). Subjects with advanced PSC or cholangiocarcinoma (CCA) at baseline were excluded. The PSC risk estimate tool (PREsTo) consists of nine variables: bilirubin, albumin, serum alkaline phosphatase (SAP) times the upper limit of normal (ULN), platelets, aspartate aminotransferase (AST), hemoglobin, sodium, patient age, and number of years since PSC was diagnosed. Validation in an independent cohort confirms that PREsTo accurately predicts decompensation (C-statistic, 0.90; 95% confidence interval [CI], 0.84-0.95) and performed well compared to Model for End-Stage Liver Disease (MELD) score (C-statistic, 0.72; 95% CI, 0.57-0.84), Mayo PSC risk score (C-statistic, 0.85; 95% CI, 0.77-0.92), and SAP <1.5 × ULN (C-statistic, 0.65; 95% CI, 0.55-0.73). PREsTo continued to be accurate among individuals with a bilirubin <2.0 mg/dL (C-statistic, 0.90; 95% CI, 0.82-0.96) and when the score was reapplied at a later course in the disease (C-statistic, 0.82; 95% CI, 0.64-0.95). Conclusion: PREsTo accurately predicts hepatic decompensation (HD) in PSC and exceeds the performance among other widely available, noninvasive prognostic scoring systems.
需要改进方法来对原发性硬化性胆管炎（PSC）患者进行风险分层和预测结局。因此，我们试图开发和验证一个预测模型，并将其性能与现有替代标志物进行比较。该模型是使用来自多中心北美队列的 509 名受试者推导得出的，并在国际多中心队列中进行了验证（n=278）。梯度提升，一种基于机器学习的技术，被用于创建该模型。终点是肝失代偿（腹水、静脉曲张出血或肝性脑病）。基线时患有晚期 PSC 或胆管癌（CCA）的受试者被排除在外。PSC 风险估计工具（PREsTo）由九个变量组成：胆红素、白蛋白、血清碱性磷酸酶（SAP）乘以正常值上限（ULN）、血小板、天冬氨酸氨基转移酶（AST）、血红蛋白、钠、患者年龄和从 PSC 诊断后的年数。在独立队列中的验证证实，PREsTo 可准确预测失代偿（C 统计量，0.90；95%置信区间[CI]，0.84-0.95），并且与终末期肝病模型（MELD）评分（C 统计量，0.72；95%CI，0.57-0.84）、Mayo PSC 风险评分（C 统计量，0.85；95%CI，0.77-0.92）和 SAP<1.5×ULN（C 统计量，0.65；95%CI，0.55-0.73）相比表现良好。在胆红素<2.0mg/dL 的个体中（C 统计量，0.90；95%CI，0.82-0.96）和在疾病后期重新应用该评分时（C 统计量，0.82；95%CI，0.64-0.95），PREsTo 仍然准确。结论：PREsTo 可准确预测 PSC 中的肝失代偿（HD），并且优于其他广泛可用的非侵入性预后评分系统。
