Kucukseymen Selcuk, Arafati Arghavan, Al-Otaibi Talal, El-Rewaidy Hossam, Fahmy Ahmed S, Ngo Long H, Nezafat Reza
Department of Medicine, Cardiovascular Division, Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts, USA.
Department of Computer Science, Technical University of Munich, Munich, Germany.
J Magn Reson Imaging. 2022 Jun;55(6):1812-1825. doi: 10.1002/jmri.27932. Epub 2021 Sep 24.
Heart 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.
To develop and test an explainable machine learning (ML) model to investigate incremental value of noncontrast cardiac MRI for predicting HF-hospitalization.
Retrospective.
A 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%).
A 1.5 T, balanced steady-state free precession (bSSFP) sequence.
Two 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.
ML 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. A P-value <0.05 was considered statistically significant.
During 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.
Using an ML model, RV and LA strains measured in noncontrast cardiac MRI provide incremental value in predicting future hospitalization in HFpEF.
3 TECHNICAL EFFICACY: Stage 2.
射血分数保留的心力衰竭（HFpEF）患者未来住院风险增加。由于合并肾脏疾病的患病率较高，造影剂在HFpEF患者中常被列为禁忌。因此，非增强心脏磁共振成像（MRI）对HF住院的预后价值很重要。
开发并测试一种可解释的机器学习（ML）模型，以研究非增强心脏MRI在预测HF住院方面的增量价值。
回顾性研究。
共203例因心脏MRI检查而转诊的HFpEF患者（平均年龄64±12岁，48%为女性）被随机分为训练验证组（143例患者，约70%）和测试组（60例患者，约30%）。
1.5T，平衡稳态自由进动（bSSFP）序列。
基于树增强技术和极端梯度增强模型（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；2）基于心脏MRI的ML模型，除基本模型外还包括非增强心脏MRI标记物。主要终点定义为HF住院。
使用ML工具进行高级统计分析，并采用弹性网络方法进行特征选择。使用德龙检验比较各模型之间的受试者操作特征曲线（ROC）下面积（AUC）。为深入了解ML模型，采用了夏普利加性解释（SHAP）方法。P值<0.05被认为具有统计学意义。
在随访期间（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模型对HF住院的预测明显更优（AUC：0.81）。SHAP分析显示，左心房（LA）和右心房（RV）应变是其性能的主要影像标记物，截断值分别为17.5%和-15%。
使用ML模型，非增强心脏MRI测量的RV和LA应变在预测HFpEF患者未来住院方面具有增量价值。
3级 技术效能：二级
