基于机器学习的CAGIB评分可预测肝硬化急性胃肠道出血患者的院内死亡率。
Machine learning based CAGIB score predicts in-hospital mortality of cirrhotic patients with acute gastrointestinal bleeding.
作者信息
Bai Zhaohui, Lin Su, Sun Mingyu, Yuan Shanshan, Marcondes Mariana Barros, Ma Dapeng, Zhu Qiang, Li Yiling, He Yingli, Philips Cyriac Abby, Liu Xiaofeng, Pinyopornpanish Kanokwan, Shao Lichun, Méndez-Sánchez Nahum, Basaranoglu Metin, Wu Yunhai, Chen Yu, Yang Ling, Mancuso Andrea, Tacke Frank, Li Bimin, Liu Lei, Ji Fanpu, Qi Xingshun
机构信息
Liver Cirrhosis Study Group, Department of Gastroenterology, General Hospital of Northern Theater Command, Shenyang, China.
Department of Pharmacy Administration and Clinical Pharmacy, School of Pharmaceutical Sciences, Peking University, Beijing, China.
出版信息
NPJ Digit Med. 2025 Jul 31;8(1):489. doi: 10.1038/s41746-025-01883-w.
Acute gastrointestinal bleeding (AGIB) is a potentially lethal complication in cirrhosis. In this prospective international multi-center study, the performance of CAGIB score for predicting the risk of in-hospital death in 2467 cirrhotic patients with AGIB was validated. Machine learning (ML) models were established based on CAGIB components, and their area under curves (AUCs) were calculated and compared. Gray zone approach was employed to further stratify the risk of death. In training cohort, the AUC of CAGIB score was 0.789. Among the ML models, the least square support vector machine regression (LS-SVMR) model had the best predictive performance (AUC = 0.986). Patients were further divided into low- (LS-SVMR score <0.084), moderate- (LS-SVMR score 0.084-0.160), and high-risk (LS-SVMR score >0.160) groups with in-hospital mortality of 0.38%, 2.22%, and 64.37%, respectively. Statistical results were retained in validation cohort. LS-SVMR model has an excellent predictive performance for in-hospital death in cirrhotic patients with AGIB (ClinicalTrials.gov; NCT04662918).
急性胃肠道出血（AGIB）是肝硬化患者潜在的致死性并发症。在这项前瞻性国际多中心研究中，对2467例肝硬化合并AGIB患者的CAGIB评分预测院内死亡风险的性能进行了验证。基于CAGIB的组成部分建立机器学习（ML）模型，并计算和比较其曲线下面积（AUC）。采用灰色区域法进一步分层死亡风险。在训练队列中，CAGIB评分的AUC为0.789。在ML模型中，最小二乘支持向量机回归（LS-SVMR）模型具有最佳的预测性能（AUC = 0.986）。患者进一步分为低风险（LS-SVMR评分<0.084）、中度风险（LS-SVMR评分0.084-0.160）和高风险（LS-SVMR评分>0.160）组，院内死亡率分别为0.38%、2.22%和64.37%。统计结果在验证队列中得到保留。LS-SVMR模型对肝硬化合并AGIB患者的院内死亡具有优异的预测性能（ClinicalTrials.gov；NCT04662918）。
Zotero 插件