Agarwal Samagra, Sharma Sanchit, Kumar Manoj, Venishetty Shantan, Bhardwaj Ankit, Kaushal Kanav, Gopi Srikanth, Mohta Srikant, Gunjan Deepak, Saraya Anoop, Sarin Shiv Kumar
Department of Gastroenterology and Human Nutrition Unit, All India Institute of Medical Sciences, New Delhi, India.
Department of Hepatology and Liver Transplantation, Institute of Liver and Biliary Sciences, New Delhi, India.
J Gastroenterol Hepatol. 2021 Oct;36(10):2935-2942. doi: 10.1111/jgh.15560. Epub 2021 Jun 13.
Risk stratification beyond the endoscopic classification of esophageal varices (EVs) to predict first episode of variceal bleeding (VB) is currently limited in patients with compensated advanced chronic liver disease (cACLD). We aimed to assess if machine learning (ML) could be used for predicting future VB more accurately.
In this retrospective analysis, data from patients of cACLD with EVs, laboratory parameters and liver stiffness measurement (LSM) were used to generate an extreme-gradient boosting (XGBoost) algorithm to predict the risk of VB. The performance characteristics of ML and endoscopic classification were compared in internal and external validation cohorts. Bleeding rates were estimated in subgroups identified upon risk stratification with combination of model and endoscopic classification.
Eight hundred twenty-eight patients of cACLD with EVs, predominantly related to non-alcoholic fatty liver disease (28.6%), alcohol (23.7%) and hepatitis B (23.1%) were included, with 455 (55%) having the high-risk varices. Over a median follow-up of 24 (12-43) months, 163 patients developed VB. The accuracy of machine learning (ML) based model to predict future VB was 98.7 (97.4-99.5)%, 93.7 (88.8-97.2)%, and 85.7 (82.1-90.5)% in derivation (n = 497), internal validation (n = 149), and external validation (n = 182) cohorts, respectively, which was better than endoscopic classification [58.9 (55.5-62.3)%] alone. Patients stratified high risk on both endoscopy and model had 1-year and 3-year bleeding rates of 31-43% and 64-85%, respectively, whereas those stratified as low risk on both had 1-year and 3-year bleeding rates of 0-1.6% and 0-3.4%, respectively. Endoscopic classification and LSM were the major determinants of model's performance.
Application of ML model improved the performance of endoscopic stratification to predict VB in patients with cACLD with EVs.
在代偿期晚期慢性肝病（cACLD）患者中，目前食管静脉曲张（EV）内镜分类之外用于预测首次静脉曲张出血（VB）的风险分层方法有限。我们旨在评估机器学习（ML）是否可用于更准确地预测未来的VB。
在这项回顾性分析中，使用cACLD合并EV患者的数据、实验室参数和肝脏硬度测量（LSM）来生成极端梯度提升（XGBoost）算法，以预测VB风险。在内部和外部验证队列中比较了ML和内镜分类的性能特征。通过模型与内镜分类相结合进行风险分层确定的亚组中估计出血率。
纳入了828例cACLD合并EV的患者，主要与非酒精性脂肪性肝病（28.6%）、酒精（23.7%）和乙型肝炎（23.1%）相关，其中455例（55%）有高危静脉曲张。中位随访24（12 - 43）个月时，163例患者发生了VB。基于机器学习（ML）的模型预测未来VB的准确率在推导队列（n = 497）、内部验证队列（n = 149）和外部验证队列（n = 182）中分别为98.7（97.4 - 99.5）%、93.7（88.8 - 97.2）%和85.7（82.1 - 90.5）%，优于单独的内镜分类[58.9（55.5 - 62.3）%]。在内镜检查和模型中均分层为高风险的患者1年和3年出血率分别为31 - 43%和64 - 85%，而在内镜检查和模型中均分层为低风险的患者1年和3年出血率分别为0 - 1.6%和0 - 3.4%。内镜分类和LSM是模型性能的主要决定因素。
ML模型的应用提高了内镜分层预测cACLD合并EV患者VB的性能。
