面向AMI病发即时响应的自适应心音分割方法
An Adaptive Heart Sound Segmentation Method for Immediate Response to Acute Myocardial Infarction
摘要: 基于心音听诊急性心梗(AMI)病发即时响应的关键在于心音特征异常监测精准率，然而由于患者病发状态的非确定性导致基于心音成分分割准确度的特征提取难度较差。鉴于此，本研究提出一种新的基于短时修正希尔伯特变换(STMHT)的自适应分割方法(ASTMHT)实现心音自适应分割以确保提取特征的准确性。实验通过对比平均香浓能量(ASE)算法和STMHT算法在AMI临产数据以及不同状态心音数据集的分割精度分析。对比结果表明，ASTMHT方法识别效果优于平均香农能量ASE方法和STMHT方法，尤其是在非安静状态数据集上，分割准确率比平均香农能量提高了53.95%，比STMHT提高76.57%。进而可为AMI特征提取提供保障。
Abstract: The key to immediate response in acute myocardial infarction (AMI) diagnosis through heart sound auscultation lies in the precision of abnormal heart sound feature detection. However, the uncertainty of patients’ conditions leads to challenges in achieving accurate feature extraction based on heart sound segmentation. To address this, this study proposes a novel adaptive segmentation method (ASTMHT) based on short-time modified Hilbert transform (STMHT) to ensure precise feature extraction through adaptive heart sound segmentation. Experimental analysis compared the segmentation accuracy of the average Shannon energy (ASE) algorithm and the STMHT algorithm on AMI clinical data and heart sound datasets under various conditions. Results demonstrate that the ASTMHT method outperforms both the ASE and STMHT methods, particularly on non-quiet state datasets, with segmentation accuracy improvements of 53.95% over ASE and 76.57% over STMHT, thereby providing a robust foundation for AMI feature extraction.
文章引用：邓琪, 陈金博, 刘广宇, 莫胜美, 刘东壅, 张一卓, 刘熠辉, 蒋灿, 匡文帮, 孙树平. 面向AMI病发即时响应的自适应心音分割方法[J]. 计算机科学与应用, 2025, 15(8): 260-269. https://doi.org/10.12677/csa.2025.158216

参考文献

[1] Ren, Z., Chang, Y., Nguyen, T.T., Tan, Y., Qian, K. and Schuller, B.W. (2024) A Comprehensive Survey on Heart Sound Analysis in the Deep Learning Era. IEEE Computational Intelligence Magazine, 19, 42-57. [Google Scholar] [CrossRef] 
[2] Jia, W., Wang, Y., Chen, R., Ye, J., Li, D., Yin, F., et al. (2024) Zchsound: Open-Source ZJU Paediatric Heart Sound Database with Congenital Heart Disease. IEEE Transactions on Biomedical Engineering, 71, 2278-2286. [Google Scholar] [CrossRef] [PubMed]
[3] Bi, X., Tang, S., Xiao, B., Li, W., Gao, X. and Liò, P. (2025) A Systematic Review of Heart Sound Detection Algorithms: Experimental Results and Insights. IEEE Transactions on Instrumentation and Measurement, 74, 1-16. [Google Scholar] [CrossRef] 
[4] Ameen, A., Fattoh, I.E., Abd El-Hafeez, T. and Ahmed, K. (2024) Advances in ECG and PCG-Based Cardiovascular Disease Classification: A Review of Deep Learning and Machine Learning Methods. Journal of Big Data, 11, Article No. 159. [Google Scholar] [CrossRef] 
[5] Monteiro, S.M. and Silva, H.P.d. (2023) A Novel Approach to Simultaneous Phonocardiography and Electrocardiography during Auscultation. IEEE Access, 11, 78224-78236. [Google Scholar] [CrossRef] 
[6] Tatulli, E., Souriau, R. and Fontecave-Jallon, J. (2025) Unsupervised Segmentation of Heart Sounds from Abrupt Changes Detection. Computers in Biology and Medicine, 186, Article ID: 109712. [Google Scholar] [CrossRef] [PubMed]
[7] Kahankova, R., Mikolasova, M., Jaros, R., Barnova, K., Ladrova, M. and Martinek, R. (2023) A Review of Recent Advances and Future Developments in Fetal Phonocardiography. IEEE Reviews in Biomedical Engineering, 16, 653-671. [Google Scholar] [CrossRef] [PubMed]
[8] Chen, J., et al. (2023) A Robust Deep Learning Framework Based on Spectrograms for Heart Sound Classification. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 21, 936-947.
[9] Xiong, W., Zhang, G., Yan, D., Cao, L., Huang, X. and Li, D. (2025) Multichannel Feature Fusion Network-Based Technique for Heart Sound Signal Classification and Recognition. Expert Systems with Applications, 273, Article ID: 126839. [Google Scholar] [CrossRef] 
[10] Xu, W., Yu, K., Ye, J., Li, H., Chen, J., Yin, F., et al. (2022) Automatic Pediatric Congenital Heart Disease Classification Based on Heart Sound Signal. Artificial Intelligence in Medicine, 126, Article ID: 102257. [Google Scholar] [CrossRef] [PubMed]
[11] Xiang, M., Zang, J., Wang, J., Wang, H., Zhou, C., Bi, R., et al. (2023) Research of Heart Sound Classification Using Two-Dimensional Features. Biomedical Signal Processing and Control, 79, Article ID: 104190. [Google Scholar] [CrossRef] 
[12] Arjoune, Y., Nguyen, T.N., Doroshow, R.W. and Shekhar, R. (2024) A Noise-Robust Heart Sound Segmentation Algorithm Based on Shannon Energy. IEEE Access, 12, 7747-7761. [Google Scholar] [CrossRef] [PubMed]
[13] Sun, S., Tong, Y., He, P., Song, W., Li, X., Liu, G., et al. (2024) A Novel GMM-Based Estimated Splitting Coefficient of Second Heart Sound for Diagnosing Aortic Septal Defect. IEEE Sensors Journal, 24, 16299-16315. [Google Scholar] [CrossRef] 
[14] Sun, S., Song, W., Tong, Y., Li, X., Zhao, M., Deng, Q., et al. (2023) A Novel Methodology for Evaluation of S2 Wide Split via Estimated Parameters. Computer Methods and Programs in Biomedicine, 242, Article ID: 107777. [Google Scholar] [CrossRef] [PubMed]
[15] Sun, S., Tong, Y., Zhang, B., Yang, B., Yan, L., He, P., et al. (2022) A Novel Adaptive Methodology for Removing Spurious Components in a Modified Incremental Gaussian Mixture Model. International Journal of Machine Learning and Cybernetics, 14, 551-566. [Google Scholar] [CrossRef]