基于肺部超声影像组学分析联合机器学习评估重症患者血管外肺水指数

Evaluation of extravascular lung water index in critically ill patients based on lung ultrasound radiomics analysis combined with machine learning

目的:探讨与血管外肺水指数(EVLWI)相关的肺部超声影像组学特征,采用基于肺部超声的影像组学方法联合机器学习预测重症患者的EVLWI并进行效能验证。方法:采用回顾性病例对照研究方法,收集2021年11月至2022年10月广西医科大学第一附属医院重症医学科收治的重症患者肺部超声视频和脉搏指示连续心排血量(PiCCO)监测结果,按照8∶2的比例随机分为训练集与验证集。从肺部超声视频取帧得到对应图像并提取影像组学特征,以PiCCO测得的EVLWI为"金标准",通过统计分析和LASSO算法对训练集影像组学特征进行筛选。采用经过筛选的影像组学特征训练8种机器学习模型,包括随机森林(RF)、极限梯度提升(XGBoost)、决策树(DT)、朴素贝叶斯(NB)、多层感知器(MLP)、K-近邻(KNN)、支持向量机(SVM)和Logistic回归(LR);绘制受试者工作特征曲线(ROC曲线),评估上述模型在验证集中对EVLWI的预测效能。结果:最终共30例患者151组样本(包括906份肺部超声视频和151份PiCCO监测结果)纳入分析,其中训练集120组样本,验证集31组样本;两项数据集的性别、年龄、体质量指数(BMI)、平均动脉压(MAP)、中心静脉压(CVP)、心率(HR)、心排血指数(CI)、心功能指数(CFI)、每搏量指数(SVI)、全心舒张期末容积指数(GEDVI)、全身血管阻力指数(SVRI)、肺血管通透性指数(PVPI)、EVLWI等主要基线资料差异均无统计学意义。151份PiCCO监测结果中整体EVLWI范围为3.7~25.6 mL/kg;分层分析显示,两项数据集EVLWI均集中于7~15 mL/kg区间,EVLWI分布差异无统计学意义。通过LASSO算法筛选出2个影像组学特征,即灰阶不均匀性(权重为-0.006?464)和复杂度(权重为-0.167?583),并用于建模;ROC曲线分析显示,MLP模型具有较好的预测效能,其预测验证集EVLWI的ROC曲线下面积(AUC)高于RF、XGBoost、DT、KNN、LR、SVM、NB模型(0.682比0.658、0.657、0.614、0.608、0.596、0.557、0.472)。结论:肺部超声灰阶不均匀性和复杂度是与PiCCO测得的EVLWI相关性最高的影像组学特征;基于肺部超声灰阶不均匀性和复杂度构建的MLP模型可用于半定量预测重症患者EVLWI。

ObjectiveTo explore lung ultrasound radiomics features which related to extravascular lung water index(EVLWI),and to predict EVLWI in critically ill patients based on lung ultrasound radiomics combined with machine learning and validate its effectiveness.MethodsA retrospective case-control study was conducted.The lung ultrasound videos and pulse indicated continuous cardiac output(PiCCO)monitoring results of critically ill patients admitted to the department of critical care medicine of the First Affiliated Hospital of Guangxi Medical University from November 2021 to October 2022 were collected,and randomly divided into training set and validation set at 8∶2.The corresponding images from lung ultrasound videos were obtained to extract radiomics features.The EVLWI measured by PiCCO was regarded as the"gold standard",and the radiomics features of training set was filtered through statistical analysis and LASSO algorithm.Eight machine learning models were trained using filtered radiomics features including random forest(RF),extreme gradient boost(XGBoost),decision tree(DT),Naive Bayes(NB),multi-layer perceptron(MLP),K-nearest neighbor(KNN),support vector machine(SVM),and Logistic regression(LR).Receiver operator characteristic curve(ROC curve)was plotted to evaluate the predictive performance of models on EVLWI in the validation set.ResultsA total of 151 samples from 30 patients were enrolled(including 906 lung ultrasound videos and 151 PiCCO monitoring results),120 in the training set,and 31 in the validation set.There were no statistically significant differences in main baseline data including gender,age,body mass index(BMI),mean arterial pressure(MAP),central venous pressure(CVP),heart rate(HR),cardiac index(CI),cardiac function index(CFI),stroke volume index(SVI),global end diastolic volume index(GEDVI),systemic vascular resistance index(SVRI),pulmonary vascular permeability index(PVPI)and EVLWI.The overall EVLWI range in 151 PiCCO monitoring results was 3.7-25.6 mL/kg.Layered analysis showed that both datasets had EVLWI in the 7-15 mL/kg interval,and there was no statistically significant difference in EVLWI distribution.Two radiomics features were selected by using LASSO algorithm,namely grayscale non-uniformity(weight was-0.006464)and complexity(weight was-0.167583),and they were used for modeling.ROC curve analysis showed that the MLP model had better predictive performance.The area under the ROC curve(AUC)of the prediction validation set EVLWI was higher than that of RF,XGBoost,DT,KNN,LR,SVM,NB models(0.682 vs.0.658,0.657,0.614,0.608,0.596,0.557,0.472).ConclusionsThe gray level non-uniformity and complexity of lung ultrasound were the most correlated radiomics features with EVLWI monitored by PiCCO.The MLP model based on gray level non-uniformity and complexity of lung ultrasound can be used for semi-quantitative prediction of EVLWI in critically ill patients.