Primary Sclerosing Cholangitis Risk Estimate Tool (PREsTo) Predicts Outcomes of the Disease: A Derivation and Validation Study Using Machine Learning.
Primary Sclerosing Cholangitis Risk Estimate Tool (PREsTo) Predicts Outcomes of the Disease: A Derivation and Validation Study Using Machine Learning.
复制标题
DOI：
10.1002/hep.30085
复制
发表时间：
2020-01
期刊：
影响因子：
--
通讯作者：
Lazaridis KN
中科院分区：
文献类型：
--
作者：
Eaton JE;Vesterhus M;McCauley BM;Atkinson EJ;Schlicht EM;Juran BD;Gossard AA;LaRusso NF;Gores GJ;Karlsen TH;Lazaridis KN
需要改进的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，我们试图推导和验证一种新的预测模型，并将其性能与现有的替代标记物进行比较。该模型使用来自北美多中心队列的509例受试者推导，并在国际多中心队列（n=278）中进行了验证。梯度提升（一种基于机器的学习技术）用于创建模型。终点为肝功能失代偿（腹水、静脉曲张出血或脑病）。基线时患有晚期PSC或胆管癌的受试者被排除。PSC风险估计工具（PREsTo）由9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、AST、血红蛋白、钠、患者年龄和自PSC诊断以来的年数。在独立队列中的验证证实PREsTo准确预测失代偿（C统计量0.90，95%置信区间（CI）0.84-0.95），与MELD评分相比表现良好（C统计0.72，95%CI 0.57-0.84），马约PSC风险评分（C统计0.85，95%CI 0.77-0.92）和SAP <1.5 x ULN（C统计0.65，95%CI 0.55-0.73）。PREsTo在胆红素< 2.0 mg/dL的个体中（C统计0.90，95% CI 0.82-0.96）以及在疾病后期重新应用评分时（C统计0.82，95% CI 0.64-0.95）仍然准确。PREsTo可准确预测PSC中的肝功能失代偿，并超过其他广泛使用的非侵入性预后评分系统。
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 new 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 at baseline were excluded. The PSC risk estimate tool (PREsTo) consists of 9 variables: bilirubin, albumin, serum alkaline phosphatase (SAP) times the upper limit of normal (ULN), platelets, AST, hemoglobin, sodium, patient age and the number of years since PSC was diagnosed. Validation in an independent cohort confirms PREsTo accurately predicts decompensation (C statistic 0.90, 95% confidence interval (CI) 0.84-0.95) and performed well compared to 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 < 1.5x 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 re-applied at a later course in the disease (C statistic 0.82, 95% CI 0.64-0.95). PREsTo accurately predicts hepatic decompensation in PSC and exceeds the performance among other widely available, noninvasive prognostic scoring systems.
登录
查看更多内容
影响因子：
3.7
作者：
Casanova R;Saldana S;Chew EY;Danis RP;Greven CM;Ambrosius WT
通讯作者：
Ambrosius WT
影响因子：
29.4
作者：
Corpechot, Christophe;Gaouar, Farid;Chazouilleres, Olivier
通讯作者：
Chazouilleres, Olivier
影响因子：
25.7
作者：
Al Mamari, Said;Djordjevic, Jelena;Chapman, Roger W.
通讯作者：
Chapman, Roger W.
影响因子：
24.5
作者：
Broome, U;Olsson, R;Lindberg, G
通讯作者：
Lindberg, G
影响因子：
29.4
作者：
Eaton JE;Talwalkar JA;Lazaridis KN;Gores GJ;Lindor KD
通讯作者：
Lindor KD