Noncontrast Cardiac Magnetic Resonance Imaging Predictors of Heart Failure Hospitalization in Heart Failure With Preserved Ejection Fraction.
Noncontrast Cardiac Magnetic Resonance Imaging Predictors of Heart Failure Hospitalization in Heart Failure With Preserved Ejection Fraction.
复制标题
保留射血分数的心力衰竭患者的非对比心脏磁共振成像预测心力衰竭住院情况。
DOI：
10.1002/jmri.27932
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Nezafat,Reza
中科院分区：
文献类型：
--
作者：
Kucukseymen,Selcuk;Arafati,Arghavan;Al-Otaibi,Talal;El-Rewaidy,Hossam;Fahmy,AhmedS;Ngo,LongH;Nezafat,Reza
射血分数正常的心力衰竭患者未来住院的风险增加。由于伴随肾脏疾病的高患病率，HFpEF患者通常禁忌使用造影剂。因此，心脏磁共振成像（MRI）对HF住院的预后价值非常重要。目的开发和测试可解释的机器学习（ML）模型，以研究心脏MRI对预测HF住院的增量价值。研究类型回顾性。人群共203例HFpEF患者（平均年龄64 ± 12岁，48%为女性）随机分为培训验证组，（143例患者，约70%）和测试集（60例患者，约30%）。场强A 1.5 T，评估基于树提升技术和极端梯度提升模型（XGBoost）构建了两个ML模型：1）使用临床和超声心动图数据的基本临床ML模型和2）基于心脏MRI的ML模型，除基本模型外还包括非造影心脏MRI标记物。主要终点定义为HF住院，高级统计采用Statistical TestsML工具，特征选择采用Elastic Net方法。使用DeLong检验比较模型之间的受试者工作特征（ROC）曲线下面积（AUC）。为了深入了解ML模型，利用了SHapley加法解释（SHAP）方法。结果随访期间（平均50 ± 39个月），85例患者（42%）达到终点。与基本模型（AUC：0.64）相比，使用XGBoost算法的基于心脏MRI的ML模型提供了显著上级的HF住院预测（AUC：0.81）。SHAP分析显示，左心房（LA）和右心房（RV）应变是影响其性能的最重要的成像标记物，其临界值分别为17.5%和− 15%.Data Conclusions使用ML模型，在非对比心脏MRI中测量的RV和LA应变在预测HFpEF患者未来住院治疗方面提供了增量价值。证据等级3技术疗效阶段2
BackgroundHeart failure patients with preserved ejection fraction (HFpEF) are at increased risk of future hospitalization. Contrast agents are often contra‐indicated in HFpEF patients due to the high prevalence of concomitant kidney disease. Therefore, the prognostic value of a noncontrast cardiac magnetic resonance imaging (MRI) for HF‐hospitalization is important.PurposeTo develop and test an explainable machine learning (ML) model to investigate incremental value of noncontrast cardiac MRI for predicting HF‐hospitalization.Study TypeRetrospective.PopulationA total of 203 HFpEF patients (mean, 64 ± 12 years, 48% women) referred for cardiac MRI were randomly split into training validation (143 patients, ~70%) and test sets (60 patients, ~30%).Field strengthA 1.5 T, balanced steady‐state free precession (bSSFP) sequence.AssessmentTwo ML models were built based on the tree boosting technique and the eXtreme Gradient Boosting model (XGBoost): 1) basic clinical ML model using clinical and echocardiographic data and 2) cardiac MRI‐based ML model that included noncontrast cardiac MRI markers in addition to the basic model. The primary end point was defined as HF‐hospitalization.Statistical TestsML tool was used for advanced statistics, and the Elastic Net method for feature selection. Area under the receiver operating characteristic (ROC) curve (AUC) was compared between models using DeLong's test. To gain insight into the ML model, the SHapley Additive exPlanations (SHAP) method was leveraged. AP‐value <0.05 was considered statistically significant.ResultsDuring follow‐up (mean, 50 ± 39 months), 85 patients (42%) reached the end point. The cardiac MRI‐based ML model using the XGBoost algorithm provided a significantly superior prediction of HF‐hospitalization (AUC: 0.81) compared to the basic model (AUC: 0.64). The SHAP analysis revealed left atrium (LA) and right atrium (RV) strains as top imaging markers contributing to its performance with cutoff values of 17.5% and −15%, respectively.Data ConclusionsUsing an ML model, RV and LA strains measured in noncontrast cardiac MRI provide incremental value in predicting future hospitalization in HFpEF.Evidence Level3Technical EfficacyStage 2