[1]王甘红,奚美娟,华秋雯,等.基于机器学习构建肝硬化门静脉血栓形成风险预测模型及网络应用程序[J].中国医学物理学杂志,2026,43(1):121-131.[doi:DOI:10.3969/j.issn.1005-202X.2026.01.016]
　WANG Ganhong,XI Meijuan,HUA Qiuwen,et al.Development of a machine learning-based predictive model and web application for portal vein thrombosis risk in patients with liver cirrhosis[J].Chinese Journal of Medical Physics,2026,43(1):121-131.[doi:DOI:10.3969/j.issn.1005-202X.2026.01.016]
点击复制

基于机器学习构建肝硬化门静脉血栓形成风险预测模型及网络应用程序()

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
43卷
期数:
2026年第1期
页码:
121-131
栏目:
医学人工智能
出版日期:
2026-01-26

文章信息/Info

Title:
Development of a machine learning-based predictive model and web application for portal vein thrombosis risk in patients with liver cirrhosis
文章编号:
1005-202X（2026）01-0121-11
作者:
王甘红1; 奚美娟1; 华秋雯1; 夏开建2; 3; 倪晓琛1; 陈健3; 4
1.常熟市中医院（常熟市新区医院）消化内科， 江苏 常熟 215500； 2.常熟市第一人民医院（苏州大学附属常熟医院）智能医疗技术研究中心， 江苏 常熟 215500； 3.常熟市医学人工智能与大数据重点实验室， 江苏 常熟 215500； 4.常熟市第一人民医院（苏州大学附属常熟医院）消化内科， 江苏 常熟 215500
Author(s):
WANG Ganhong1;  XI Meijuan1;  HUA Qiuwen1;  XIA Kaijian2;  3;  NI Xiaochen1;  CHEN Jian3;  4
1. Department of Gastroenterology, Changshu Traditional Chinese Medicine Hospital (Changshu New District Hospital), Changshu 215500, China 2. Intelligent Medical Technology Research Center, Changshu No.1 Peoples Hospital (Changshu Hospital Affiliated to Soochow University), Changshu 215500, China 3. Changshu Key Laboratory of Medical Artificial Intelligence and Big Data, Changshu 215500, China 4. Department of Gastroenterology, Changshu No.1 Peoples Hospital (Changshu Hospital Affiliated to Soochow University), Changshu 215500, China
关键词:
肝硬化; 门静脉血栓形成; 机器学习; 应用程序; Streamlit
Keywords:
Keywords: liver cirrhosis portal vein thrombosis machine learning application program Streamlit
分类号:
R318；R575.2
DOI:
DOI:10.3969/j.issn.1005-202X.2026.01.016
文献标志码:
A
摘要:
目的：门静脉血栓（PVT）形成是肝硬化的常见并发症，可加重肝损伤、门静脉高压及相关并发症。本研究旨在基于多种机器学习（ML）方法建立肝硬化并发PVT的预测模型及网络应用程序（App）。方法：回顾性纳入662名肝硬化患者。并将其分为PVT组和非PVT组。共涉及26项潜在预测变量，用以构建和验证1种LASSO回归模型和5种不同的ML模型。各模型的性能通过受试者工作特征曲线下面积（AUC）、灵敏度、特异度和准确率等指标进行评估，并选出表现最佳的模型。利用特征重要性分析和SHAP值散点图等手段实现对模型的可视化解释。最终在Python-Streamlit框架下开发了最佳模型的网络应用，并在另一家医院的独立测试集中进行外部验证。结果：在验证集中，XGBoost模型表现最佳，优于LASSO回归和其他ML模型，AUC为0.93（95%CI：0.88~0.98）。在测试集中，XGBoost模型的准确率、灵敏度、特异度和AUC分别为83.47%、85.71%、82.80%和0.90（95% CI, 0.81~0.97）。特征重要性分析表明，凝血酶原活动度、门静脉内径、MELD评分、D-二聚体、血小板计数、凝血酶原时间和白蛋白这7个特征对预测肝硬化合并PVT具有重要作用。SHAP值散点图和力图可视化关键特征对PVT预测的影响。结论：基于XGBoost机器学习算法构建的预测模型及其网络应用在肝硬化并发PVT风险预测中表现出良好的预测能力和便捷性，可为医护人员筛查PVT高风险患者提供有力支持。
Abstract:
Abstract: Objective Portal vein thrombosis (PVT) is a common complication of liver cirrhosis, exacerbating liver damage, portal hypertension, and associated complications. This study aims to establish a predictive model and web application for PVT complicating liver cirrhosis based on various machine learning (ML) methods. Methods A retrospective study was conducted on 662 patients with liver cirrhosis who were divided into either PVT group or non-PVT groups. Twenty-six potential predictive variables were included to construct and validate a LASSO regression model and 5 different ML models. Model performance was evaluated using metrics including the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy, with the optimal-performing model identified. Visual interpretation of the model was achieved using feature importance analysis and SHAP scatter plots. A web application based on the optimal model was ultimately developed using Python-Streamlit framework and externally validated on an independent test set from another hospital. Results In the validation set, the XGBoost model had the optimal performance, superior to the LASSO regression model and the other ML models, achieving an AUC of 0.93 (95% CI: 0.88-0.98). In the test set, the XGBoost model yielded an accuracy of 83.47%, sensitivity of 85.71%, specificity of 82.80%, and AUC of 0.90 (95% CI: 0.81-0.97). Feature importance analysis revealed that prothrombin activity, portal vein diameter, MELD score, D-dimer, platelet count, prothrombin time, and albumin played critical roles in predicting PVT complicating liver cirrhosis. SHAP scatter plots and force plots visualized the impact of key features on PVT prediction. Conclusion The XGBoost-based predictive model and its corresponding web application demonstrates strong predictive capability and excellent portability for assessing PVT risk in patients with liver cirrhosis, thereby providing valuable support for healthcare professionals to identify patients at high risk of PVT.

相似文献/References:

[1]何锋坚,李立夫,刘素英,等.经皮微波消融治疗肝硬化脾功能亢进症的临床研究[J].中国医学物理学杂志,2016,33(5):510.[doi:10.3969/j.issn.1005-202X.2016.05.016]
　[J].Chinese Journal of Medical Physics,2016,33(1):510.[doi:10.3969/j.issn.1005-202X.2016.05.016]
[2]蔡刁龙. 微波治疗在合并肝硬化胆囊切除术胆囊床出血中的应用[J].中国医学物理学杂志,2018,35(6):742.[doi:DOI:10.3969/j.issn.1005-202X.2018.06.023]
　CAI Diaolong. Application of microwave therapy in cholecystectomy for cholecystolithiasis complicated with cirrhosis[J].Chinese Journal of Medical Physics,2018,35(1):742.[doi:DOI:10.3969/j.issn.1005-202X.2018.06.023]
[3]任占丽,雷雨欣,陈晓侠,等. 能谱CT基物质分离技术在肝硬化与正常肝脏血流定量研究中的应用[J].中国医学物理学杂志,2019,36(10):1200.[doi:DOI:10.3969/j.issn.1005-202X.2019.10.017]
　REN Zhanli,LEI Yuxin,CHEN Xiaoxia,et al. Application of basis material decomposition technique with energy spectral CT in the quantitative study on blood flows in cirrhotic liver and healthy liver[J].Chinese Journal of Medical Physics,2019,36(1):1200.[doi:DOI:10.3969/j.issn.1005-202X.2019.10.017]
[4]牛广利,刘翔,宋家琳,等.结合快速傅里叶变换的肝实质病变特征量化检测[J].中国医学物理学杂志,2022,39(2):188.[doi:DOI:10.3969/j.issn.1005-202X.2022.02.010]
　NIU Guangli,LIU Xiang,SONG Jialin,et al.Quantitative detection of liver parenchymal lesion characteristics after the combination with fast Fourier transform[J].Chinese Journal of Medical Physics,2022,39(1):188.[doi:DOI:10.3969/j.issn.1005-202X.2022.02.010]
[5]朱佳琦,刘翔,宋家琳.全局与局部特征结合的肝硬化病程分类方法[J].中国医学物理学杂志,2023,40(11):1362.[doi:DOI:10.3969/j.issn.1005-202X.2023.11.008]
　ZHU Jiaqi,LIU Xiang,SONG Jialin.Classification of liver cirrhosis using global and local features[J].Chinese Journal of Medical Physics,2023,40(1):1362.[doi:DOI:10.3969/j.issn.1005-202X.2023.11.008]

备注/Memo

备注/Memo:
【收稿日期】2025-06-15 【基金项目】常熟市科技发展计划（CSWS202316, CS202454）；常熟市科技计划（社会发展）项目（CS202452）；江苏省中医药科技发展计划（MS2024084）；苏州市科技发展计划（SYW2025034） 【作者简介】王甘红，副主任护师，研究方向：医学人工智能、机器学习等，E-mail: 651943259@qq.com 【通信作者】陈健，副主任医师，研究方向：消化内镜人工智能，E-mail: szcs10132716@163.com
更新日期/Last Update: 2026-01-27