Li Yu-Jie, Zhong Kun-Hua, Bai Xue-Hong, Tang Xi, Li Peng, Yang Zhi-Yong, Zhi Hong-Yu, Li Xiao-Jun, Chen Yang, Deng Peng, Qin Xiao-Lin, Gu Jian-Teng, Ning Jiao-Lin, Lu Kai-Zhi, Zhang Ju, Xia Zheng-Yuan, Chen Yu-Wen, Yi Bin
Department of Anaesthesiology, Southwest Hospital, Third Military Medical University (First Affiliated Hospital of Army Medical University), Chongqing, China.
Chengdu Institute of Computer Applications, Chinese Academy of Sciences, Chengdu, Sichuan, China.
J Clin Transl Hepatol. 2021 Oct 28;9(5):682-689. doi: 10.14218/JCTH.2020.00184. Epub 2021 Apr 29.
Screening for hepatopulmonary syndrome in cirrhotic patients is limited due to the need to perform contrast enhanced echocardiography (CEE) and arterial blood gas (ABG) analysis. We aimed to develop a simple and quick method to screen for the presence of intrapulmonary vascular dilation (IPVD) using noninvasive and easily available variables with machine learning (ML) algorithms.
Cirrhotic patients were enrolled from our hospital. All eligible patients underwent CEE, ABG analysis and physical examination. We developed a two-step model based on three ML algorithms, namely, adaptive boosting (termed AdaBoost), gradient boosting decision tree (termed GBDT) and eXtreme gradient boosting (termed Xgboost). Noninvasive variables were input in the first step (the NI model), and for the second step (the NIBG model), a combination of noninvasive variables and ABG results were used. Model performance was determined by the area under the curve of receiver operating characteristics (AUCROCs), precision, recall, F1-score and accuracy.
A total of 193 cirrhotic patients were ultimately analyzed. The AUCROCs of the NI and NIBG models were 0.850 (0.738-0.962) and 0.867 (0.760-0.973), respectively, and both had an accuracy of 87.2%. For both negative and positive cases, the recall values of the NI and NIBG models were both 0.867 (0.760-0.973) and 0.875 (0.771-0.979), respectively, and the precisions were 0.813 (0.690-0.935) and 0.913 (0.825-1.000), respectively.
We developed a two-step model based on ML using noninvasive variables and ABG results to screen for the presence of IPVD in cirrhotic patients. This model may partly solve the problem of limited access to CEE and ABG by a large numbers of cirrhotic patients.
由于需要进行对比增强超声心动图（CEE）和动脉血气（ABG）分析，肝硬化患者肝肺综合征的筛查受到限制。我们旨在开发一种简单快速的方法，利用无创且易于获取的变量和机器学习（ML）算法来筛查肺内血管扩张（IPVD）的存在。
从我院招募肝硬化患者。所有符合条件的患者均接受了CEE、ABG分析和体格检查。我们基于三种ML算法开发了一个两步模型，即自适应增强（称为AdaBoost）、梯度提升决策树（称为GBDT）和极端梯度提升（称为Xgboost）。第一步输入无创变量（NI模型），第二步（NIBG模型）使用无创变量和ABG结果的组合。通过受试者操作特征曲线下面积（AUCROCs）、精确率、召回率、F1分数和准确率来确定模型性能。
最终共分析了193例肝硬化患者。NI模型和NIBG模型的AUCROCs分别为0.850（0.738 - 0.962）和0.867（0.760 - 0.973），两者的准确率均为87.2%。对于阴性和阳性病例，NI模型和NIBG模型的召回率分别为0.867（0.760 - 0.973）和0.875（0.771 - 0.979），精确率分别为0.813（0.690 - 0.935）和0.913（0.825 - 1.000）。
我们基于ML开发了一个两步模型，使用无创变量和ABG结果来筛查肝硬化患者中IPVD的存在。该模型可能部分解决了大量肝硬化患者难以进行CEE和ABG检查这一问题。
