原发性硬化性胆管炎风险估算工具(PREsTo)预测疾病结局:一项使用机器学习的推导与验证研究
研究利用北美多中心509例原发性硬化性胆管炎(PSC)患者推导机器学习模型PREsTo,并在国际多中心278例患者中验证,终点为肝脏失代偿。PREsTo包含9项变量,验证队列C统计量为0.90(95%CI 0.84-0.95),优于MELD评分、Mayo PSC风险评分和SAP<1.5×ULN。
要点
- PREsTo由胆红素、白蛋白、SAP×ULN、血小板、AST、血红蛋白、钠、年龄和确诊年数共9项变量构成。
- 验证队列中PREsTo预测肝脏失代偿的C统计量为0.90(95%CI 0.84-0.95)。
- PREsTo在胆红素<2.0 mg/dL者中C统计量为0.90(95%CI 0.82-0.96)。
核心结论
- PREsTo能准确预测PSC患者的肝脏失代偿,且表现优于其他广泛可用的无创预后评分系统。
研究设计与样本
- 研究为预测模型推导与验证研究,使用梯度提升机器学习技术建立模型。
- 推导队列为北美多中心509例受试者,验证队列为国际多中心278例受试者。
- 基线时晚期PSC或胆管癌(CCA)患者被排除。
主要发现
- PREsTo由9项变量构成:胆红素、白蛋白、血清碱性磷酸酶(SAP)乘以正常上限(ULN)、血小板、天冬氨酸氨基转移酶(AST)、血红蛋白、钠、患者年龄和自PSC确诊以来的年数。
- 验证队列中PREsTo预测失代偿的C统计量为0.90(95%CI 0.84-0.95)。
- 验证队列中MELD评分C统计量为0.72(95%CI 0.57-0.84),Mayo PSC风险评分C统计量为0.85(95%CI 0.77-0.92),SAP<1.5×ULN的C统计量为0.65(95%CI 0.55-0.73)。
- 在胆红素<2.0 mg/dL的个体中PREsTo的C统计量为0.90(95%CI 0.82-0.96)。
- 当评分在疾病较晚阶段重新应用时,PREsTo的C统计量为0.82(95%CI 0.64-0.95)。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
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.
引用
- Eaton JE, Vesterhus M, McCauley BM, et al. Primary Sclerosing Cholangitis Risk Estimate Tool (PREsTo) Predicts Outcomes of the Disease: A Derivation and Validation Study Using Machine Learning. Hepatology. 2018. PMID: 29742811. doi:10.1002/hep.30085
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。