V Yogalakshmi, T Manikandan
Department of ECE, Rajalakshmi Engineering College, Chennai, Tamil Nadu, India.
Catheter Cardiovasc Interv. 2025 Jul 24. doi: 10.1002/ccd.70041.
Hypertrophic Cardiomyopathy (HCM) affects the left ventricle of the heart, leading to thickening of the ventricular wall and potentially life-threatening conditions, such as atrial fibrillation, cardiac failure, and sudden death. Early and accurate detection of HCM from Electrocardiogram (ECG) signals is critical for reducing mortality risk. However, most existing methods fail to simultaneously capture spatial and temporal patterns in ECG data, resulting in reduced diagnostic reliability.
This paper proposes a hybrid Deep Learning (DL) network for detecting HCM using the ECG. Initially, input ECG signals are forwarded for pre-processing by Kalman filter. Then, processed signal is fed to feature extraction phase for extracting Empirical Mode Decomposition (EMD), statistical and medical features, which is followed by feature fusion, wherein the optimal feature is merged by Deep Belief Network (DBN) with Jensen-Shannon distance. Moreover, Convolutional Neural Network Fused with Recurrent Network (CNNFRN) performs HCM detection and final detected output is effectively achieved. The proposed CNNFRN combines Kalman Neural Network (CNN) and Recurrent Neural Network (RNN) based on regression modelling. Finally, the model is trained under a supervised framework using the Adam optimizer.
The proposed model is validated using the PTB Diagnostic ECG Database and Shaoxing and Ningbo Hospital ECG Database. The results show that the proposed CNNFRN model achieved an accuracy of 0.940, sensitivity of 1.000, specificity of 0.913, and an F1-score of 0.956. These findings confirm the model's effectiveness in robust and early detection of HCM, offering significant clinical value.
The proposed model accurately detects HCM by combining advanced feature extraction and a hybrid deep learning approach that captures both spatial and temporal ECG patterns. It also shows strong performance and reliability across multiple databases, making it valuable for early and effective clinical diagnosis.
肥厚型心肌病（HCM）会影响心脏左心室，导致心室壁增厚，并引发潜在的危及生命的状况，如心房颤动、心力衰竭和猝死。从心电图（ECG）信号中早期准确检测HCM对于降低死亡风险至关重要。然而，大多数现有方法无法同时捕捉ECG数据中的空间和时间模式，导致诊断可靠性降低。
本文提出了一种用于使用ECG检测HCM的混合深度学习（DL）网络。首先，将输入的ECG信号转发给卡尔曼滤波器进行预处理。然后，将处理后的信号输入特征提取阶段，以提取经验模态分解（EMD）、统计和医学特征，随后进行特征融合，其中通过深度信念网络（DBN）与詹森-香农距离合并最优特征。此外，融合卷积神经网络与循环神经网络（CNNFRN）进行HCM检测，并有效实现最终检测输出。所提出的CNNFRN基于回归建模结合了卡尔曼神经网络（CNN）和循环神经网络（RNN）。最后，使用Adam优化器在监督框架下对模型进行训练。
使用PTB诊断ECG数据库以及绍兴和宁波医院ECG数据库对所提出的模型进行了验证。结果表明，所提出的CNNFRN模型的准确率为0.940，灵敏度为1.000，特异性为0.913，F1分数为0.956。这些发现证实了该模型在稳健和早期检测HCM方面的有效性，具有重要的临床价值。
所提出的模型通过结合先进的特征提取和捕捉ECG空间和时间模式的混合深度学习方法，准确检测HCM。它在多个数据库中也表现出强大的性能和可靠性，对早期和有效的临床诊断具有重要价值。
