Unterhuber Matthias, Rommel Karl-Philipp, Kresoja Karl-Patrik, Lurz Julia, Kornej Jelena, Hindricks Gerhard, Scholz Markus, Thiele Holger, Lurz Philipp
Department of Cardiology, Heart Center Leipzig at University Leipzig, Strümpellstraße 39, 04289 Leipzig, Germany.
Department of Electrophysiology, Heart Center Leipzig at University Leipzig, Strümpellstraße 39, 04289 Leipzig, Germany.
Eur Heart J Digit Health. 2021 Sep 17;2(4):699-703. doi: 10.1093/ehjdh/ztab081. eCollection 2021 Dec.
Heart failure with preserved ejection fraction (HFpEF) is a rapidly growing global health problem. To date, diagnosis of HFpEF is based on clinical, invasive, and laboratory examinations. Electrocardiographic findings may vary, and there are no known typical ECG features for HFpEF.
This study included two patient cohorts. In the derivation cohort, we included = 1884 patients who presented with exertional dyspnoea or equivalent and preserved ejection fraction (≥50%) and clinical suspicion for coronary artery disease. The ECGs were divided in segments, yielding a total of 77 558 samples. We trained a convolutional neural network (CNN) to classify HFpEF and control patients according to European Society of Cardiology (ESC) criteria. An external group of 203 volunteers in a prospective heart failure screening programme served as a validation cohort of the CNN. The external validation of the CNN yielded an area under the curve of 0.80 [95% confidence interval (CI) 0.74-0.86] for detection of HFpEF according to ESC criteria, with a sensitivity of 0.99 (95% CI 0.98-0.99) and a specificity of 0.60 (95% CI 0.56-0.64), with a positive predictive value of 0.68 (95%CI 0.64-0.72) and a negative predictive value of 0.98 (95% CI 0.95-0.99).
In this study, we report the first deep learning-enabled CNN for identifying patients with HFpEF according to ESC criteria including NT-proBNP measurements in the diagnostic algorithm among patients at risk. The suitability of the CNN was validated on an external validation cohort of patients at risk for developing heart failure, showing a convincing screening performance.
射血分数保留的心力衰竭（HFpEF）是一个在全球范围内迅速增长的健康问题。迄今为止，HFpEF的诊断基于临床、侵入性和实验室检查。心电图表现可能各不相同，目前尚无已知的HFpEF典型心电图特征。
本研究纳入了两个患者队列。在推导队列中，我们纳入了1884例出现劳力性呼吸困难或类似症状且射血分数保留（≥50%）并临床怀疑患有冠状动脉疾病的患者。心电图被分成多个片段，共产生77558个样本。我们训练了一个卷积神经网络（CNN），根据欧洲心脏病学会（ESC）标准对HFpEF患者和对照患者进行分类。在前瞻性心力衰竭筛查项目中的一组203名志愿者作为CNN的验证队列。根据ESC标准，CNN的外部验证得出检测HFpEF的曲线下面积为0.80[95%置信区间（CI）0.74 - 0.86]，灵敏度为0.99（95%CI 0.98 - 0.99），特异性为0.60（95%CI 0.56 - 0.64），阳性预测值为0.68（95%CI 0.64 - 0.72），阴性预测值为0.98（95%CI 0.95 - 0.99）。
在本研究中，我们报告了首个基于深度学习的CNN，用于根据ESC标准识别HFpEF患者，该标准在诊断算法中包括对有风险患者进行NT - proBNP测量。CNN的适用性在有发生心力衰竭风险的患者外部验证队列中得到验证，显示出令人信服的筛查性能。
