1.重庆医科大学公共卫生学院,重庆 400016
2.重庆医药高等专科学校公共卫生与应急管理学院,重庆 401331
3.重庆医科大学附属第一医院感染科,重庆 400016
Received:27 August 2024,
Revised:2024-09-06,
Accepted:09 October 2024,
Published:28 March 2025
移动端阅览
尹钰恒,王雨雯,范捷,等.基于可解释机器学习的肝硬化患者早期并发食管静脉曲张风险预测研究[J].重庆医科大学学报,2025,50(3):389-396.
Yin Yuheng,Wang Yuwen,Fan Jie,et al.Risk prediction of early esophageal varices in patients with liver cirrhosis based on interpretable machine learning[J].Journal of Chongqing Medical University,2025,50(3):389-396.
尹钰恒,王雨雯,范捷,等.基于可解释机器学习的肝硬化患者早期并发食管静脉曲张风险预测研究[J].重庆医科大学学报,2025,50(3):389-396. DOI: 10.13406/j.cnki.cyxb.003631.
Yin Yuheng,Wang Yuwen,Fan Jie,et al.Risk prediction of early esophageal varices in patients with liver cirrhosis based on interpretable machine learning[J].Journal of Chongqing Medical University,2025,50(3):389-396. DOI: 10.13406/j.cnki.cyxb.003631.
目的
2
探讨肝硬化患者并发食管静脉曲张的风险因素,并建立预测模型,以便为预防肝硬化患者早期并发食管静脉曲张提供合理的指导。
方法
2
回顾性纳入2006年12月至2021年5月在重庆医渡云大数据平台有电子记录的1 113例肝硬化患者。通过结合递归特征消除算法(recursive feature elimination,RFE)和4种机器学习方法筛选特征,建立5种机器学习预测模型,包括逻辑回归、随机森林、支持向量机(support vector machine,SVM)、决策树和极端梯度提升(eXtreme Gradient Boosting,XGBoost)模型。通过绘制受试者工作特征(receiver operating characteristic,ROC)曲线评估不同模型的性能,并根据表现最优的模型分析肝硬化患者并发食管静脉曲张的风险因素。SHAP图用于解释各风险因素对患者的影响。
结果
2
XGBoost模型在预测肝硬化患者并发食管静脉曲张的风险方面表现最佳,ROC曲线下面积为0.872(95%CI=0.813~0.918)。SHAP图表明,影响肝硬化患者并发食管静脉曲张的风险因素包括血小板计数、门静脉内径、胆碱酯酶、白蛋白、谷丙转氨酶、血红蛋白、凝血酶原比值、凝血酶原时间和血清总蛋白等9项临床指标。
结论
2
本研究构建的XGBoost预测模型具有较高的预测价值,其筛选出的风险因素对临床防治肝硬化患者早期并发食管静脉曲张具有一定的指导意义。
Objective
2
To investigate the risk factors for esophageal varices in patients with liver cirrhosis,to establish a predictive model,and to provide reasonable guidance for the prevention of early esophageal varices in patients with liver cirrhosis.
Methods
2
A retrospective analysis was performed for 1 113 patients with liver cirrhosis who attended the hospitals in Chongqing,China from December 2006 to May 2021. Recursive feature elimination(RFE) and four machine learning methods were used for the screening of features,and five machine learning predictive models were established by logistic regression,random forest,support vector machine(SVM),decision tree,and eXtreme Gradient Boosting(XGBoost). The receiver operating characteristic(ROC) curve was used to evaluate the performance of each model,and the model with the best performance was used to investigate the risk factors for esophageal varices in patients with liver cirrhosis. SHAP plots were used to explain the impact of each risk factor on patients.
Results
2
The XGBoost model showed the best performance in predicting the risk of esophageal varices in patients with liver cirrhosis,with an area under the ROC curve of 0.872(95%CI=0.813-0.918). SHAP plots showed that platelet count,diameter of the portal vein,cholinesterase,albumin,alanine aminotransferase,hemoglobin,prothrombin ratio,prothrombin time,and serum total protein were risk factors for esophageal varices in patients with liver cirrhosis.
Conclusion
2
This study shows that the XGBoost predictive model has a relatively high predictive value,and the risk factors obtained by this model have a certain guiding significance for the clinical prevention and treatment of early esophageal varices in patients with liver cirrhosis.
Ginès P , Krag A , Abraldes JG , et al . Liver cirrhosis [J ] . Lancet , 2021 , 398 ( 10308 ): 1359 - 1376 .
Huang DQ , Terrault NA , Tacke F , et al . Global epidemiology of cirrhosis-aetiology,trends and predictions [J ] . Nat Rev Gastroenterol Hepatol , 2023 , 20 ( 6 ): 388 - 398 .
Huang DQ , Mathurin P , Cortez-Pinto H , et al . Global epidemiology of alcohol-associated cirrhosis and HCC:trends,projections and risk factors [J ] . Nat Rev Gastroenterol Hepatol , 2023 , 20 ( 1 ): 37 - 49 .
Tapper EB , Parikh ND . Diagnosis and management of cirrhosis and its complications:a review [J ] . JAMA , 2023 , 329 ( 18 ): 1589 - 1602 .
Garcia-Tsao G , Abraldes JG , Berzigotti A , et al . Portal hypertensive bleeding in cirrhosis:risk stratification,diagnosis,and management:2016 practice guidance by the American Association for the study of liver diseases [J ] . Hepatology , 2017 , 65 ( 1 ): 310 - 335 .
Rigo GP , Merighi A , Chahin NJ , et al . A prospective study of the ability of three endoscopic classifications to predict hemorrhage from esophageal varices [J ] . Gastrointest Endosc , 1992 , 38 ( 4 ): 425 - 429 .
Garbuzenko DV , Arefyev NO . Primary prevention of bleeding from esophageal varices in patients with liver cirrhosis:an update and review of the literature [J ] . J Evid Based Med , 2020 , 13 ( 4 ): 313 - 324 .
Marasco G , Dajti E , Ravaioli F , et al . Spleen stiffness measurement for assessing the response to β-blockers therapy for high-risk esophageal varices patients [J ] . Hepatol Int , 2020 , 14 ( 5 ): 850 - 857 .
蔡偌欣 , 马亚楠 , 闻德亮 . 机器学习在非酒精性脂肪肝预测中的应用 [J ] . 中国卫生统计 , 2024 , 41 ( 2 ): 316 - 318 .
Cai RX , Ma YN , Wen DL . Application of machine learning in prediction of nonalcoholic fatty liver disease [J ] . Chin J Health Stat , 2024 , 41 ( 2 ): 316 - 318 .
黄良江 , 毛德文 , 郑景辉 , 等 . 人工智能在肝性脑病风险预测模型中的应用进展 [J ] . 实用医学杂志 , 2024 , 40 ( 3 ): 289 - 294 .
Huang LJ , Mao DW , Zheng JH , et al . Application progress of artificial intelligence in risk prediction model of hepatic encephalopathy [J ] . J Pract Med , 2024 , 40 ( 3 ): 289 - 294 .
Le Berre C , Sandborn WJ , Aridhi S , et al . Application of artificial intelligence to gastroenterology and hepatology [J ] . Gastroenterology , 2020 , 158 ( 1 ): 76 - 94 .
Agarwal S , Sharma S , Kumar M , et al . Development of a machine learning model to predict bleed in esophageal varices in compensated advanced chronic liver disease:a proof of concept [J ] . J Gastroenterol Hepatol , 2021 , 36 ( 10 ): 2935 - 2942 .
Bayani A , Hosseini A , Asadi F , et al . Identifying predictors of varices grading in patients with cirrhosis using ensemble learning [J ] . Clin Chem Lab Med , 2022 , 60 ( 12 ): 1938 - 1945 .
林子淮 , 李欣明 , 全显跃 . 基于机器学习CT影像组学特征联合血清学特征模型预测高出血风险食管静脉曲张 [J ] . 中国CT和MRI杂志 , 2023 , 21 ( 6 ): 93 - 96 .
Lin ZH , Li XM , Quan XY . Predicting high bleeding risk esophageal varices based on machine learning CT imaging features combined with a serological profile model [J ] . Chinese Journal of CT and MRI , 2023 , 21 ( 6 ): 93 - 96 .
Malik S , Tenorio BG , Moond V , et al . Systematic review of machine learning models in predicting the risk of bleed/grade of esophageal varices in patients with liver cirrhosis:a comprehensive methodological analysis [J ] . J Gastroenterol Hepatol , 2024 .
Lundberg SM , Erion G , Chen H , et al . From local explanations to global understanding with explainable AI for trees [J ] . Nat Mach Intell , 2020 , 2 ( 1 ): 56 - 67 .
Şİmşek C , Tekİn E , Sahİn H , et al . Artificial intelligence to predict esophageal varices in patients with cirrhosis [J ] . Acibadem Univ Saglik Bilimleri Dergisi , 2021 , 12 ( 3 ): 625 - 629 .
Abd El-Salam SM , Ezz MM , Hashem S , et al . Performance of machine learning approaches on prediction of esophageal varices for Egyptian chronic hepatitis C patients [J ] . Inform Med Unlocked , 2019 , 17 : 100267 .
王伟 , 李文杰 , 李佳晨 . 基于社交信息扩散的网络传染病传播防控研究 [J ] . 重庆医科大学学报 , 2023 , 48 ( 12 ): 1393 - 1400 .
Wang W , Li WJ , Li JC . Prevention and control strategy for network infectious disease spreading based on social information diffusion [J ] . J Chongqing Med Univ , 2023 , 48 ( 12 ): 1393 - 1400 .
Sato M , Morimoto K , Kajihara S , et al . Machine-learning approach for the development of a novel predictive model for the diagnosis of hepatocellular carcinoma [J ] . Sci Rep , 2019 , 9 ( 1 ): 7704 .
Wang J , Wang ZQ , Chen MK , et al . An interpretable artificial intelligence system for detecting risk factors of gastroesophageal variceal bleeding [J ] . NPJ Digit Med , 2022 , 5 ( 1 ): 183 .
Wu CC , Yeh WC , Hsu WD , et al . Prediction of fatty liver disease using machine learning algorithms [J ] . Comput Methods Programs Biomed , 2019 , 170 : 23 - 29 .
Dong TS , Kalani A , Aby ES , et al . Machine learning-based development and validation of a scoring system for screening high-risk esophageal varices [J ] . Clin Gastroenterol Hepatol , 2019 , 17 ( 9 ): 1894 - 1901 . e1.
Yan YJ , Li Y , Fan CL , et al . A novel machine learning-based radiomic model for diagnosing high bleeding risk esophageal varices in cirrhotic patients [J ] . Hepatol Int , 2022 , 16 ( 2 ): 423 - 432 .
王 伟 , 李文杰 , 李佳晨 . 基于社交信息扩散的网络传染病传播防控研究门 [J ] . 重庆医科大学学报 , 2023 , 48 ( 12 ): 1393 - 1400 .
Wang W , Li W , Li JC . Prevention and control strategy fornetwork infectious disease spreading based on socialinformation diffusionU] . JChongging Med Univ , 2023 , 48 ( 12 ): 1393 - 1400 .
张俊文 , 段 红 . 肝硬化患者血小板功能的研究 [J ] . 重庆医科大学学报 , 2000 , 25 ( 2 ): 186 - 187,193 .
Zhang JW , Duan H . Study on the platelet functions in patients with liver cirrhosis [J ] . J Chongqing Med Univ , 2000 , 25 ( 2 ): 186 - 187,193 .
Schepis F , Cammà C , Niceforo D , et al . Which patients with cirrhosis should undergo endoscopic screening for esophageal varices detection? [J ] . Hepatology , 2001 , 33 ( 2 ): 333 - 338 .
Zaman A , Becker T , Lapidus J , et al . Risk factors for the presence of varices in cirrhotic patients without a history of variceal hemorrhage [J ] . Arch Intern Med , 2001 , 161 ( 21 ): 2564 - 2570 .
Wang CY , Huang YF , Liu CC , et al . Diagnosis of clinically significant portal hypertension using CT- and MRI-based vascular model [J ] . Radiology , 2023 , 307 ( 2 ): e221648 .
杨舒馨影 , 李 涛 . 脑出血患者循环血中HBP、ALT、AST、WBC、NEU、PLT表达与感染及预后的相关性 [J ] . 重庆医科大学学报 , 2024 , 49 ( 10 ): 1119 - 1124 .
Yang SXY , Li T . Correlation of HBP,ALT,AST,WBC,NEU,and PLT Expression in Circulating Blood with Infection and Prognosis in Patients with Intracerebral Hemorrhage [J ] . J Chongging Med Univ , 2024 , 49 ( 10 ): 1119 - 1124 .
罗 亚 , 黄维嘉 . 肝病患者血清胆碱酯酶测定及意义 [J ] . 重庆医科大学学报 , 2001 , 26 ( 2 ): 199 - 200 .
Luo Y , Huang WJ . Measurement of serum cholinesterase in patients with hepatopathy [J ] . J Chongqing Med Univ , 2001 , 26 ( 2 ): 199 - 200 .
Ramachandran J , Sajith KG , Priya S , et al . Serum cholinesterase is an excellent biomarker of liver cirrhosis [J ] . Trop Gastroenterol , 2014 , 35 ( 2 ): 15 - 20 .
郑文凤 , 殷琳琳 , 李山林 , 等 . 肝硬化食管静脉曲张破裂出血的危险因素分析 [J ] . 医药论坛杂志 , 2024 , 45 ( 10 ): 1050 - 1053 .
Zheng WF , Yin LL , Li SL , et al . Analysis of risk factors for esophageal variceal bleeding in patients with liver cirrhosis [J ] . Journal of Medical Forum , 2024 ,45,( 10 ): 1050 - 1053 .
0
Views
10
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621
