Keywords
Artificial intelligence
Deep learning
Auscultation of heart sounds
Submitted : 2025-03-06
Accepted : 2025-03-21
Published : 2025-04-05
Abstract
Congenital heart disease (CHD) is one of the most common congenital birth defects. With the deepening of people’s understanding of CHD disease and the continuous improvement of screening methods, children with CHD have been able to receive diagnosis and treatment at an early stage, thus improving the survival rate and quality of life. The main means of early screening of CHD are heart sound auscultation and percutaneous oxygen saturation detection. At present, there are relatively mature commercial equipment for transcutaneous oximetry, but the heart sound assessment is greatly affected by personal experience and external factors, which is prone to misdiagnosis and missed diagnosis. In recent years, the continuous development of artificial intelligence (AI) makes the digital collection, storage, and analysis of heart sound signals, and then makes the intelligent auscultation-assisted diagnosis technology of cardiovascular diseases possible. At present, it is based on deep learning. DL’s AI algorithm has been extensively studied in CHD cardiac sound auscultation assisted diagnosis, but most of them are still in the algorithm research stage and are implemented based on specific data sets, and have not been verified in clinical Settings. In this paper, the development and research status of AI auscultation technology at the current stage are reviewed, the development of DL based intelligent auscultation technology in the field of CHD in recent years is summarized and the problems to be solved in the clinical application of heart sound auscultation are proposed.
References
Pierpont ME, Brueckner M, Chung WK, et al., 2018, Genetic Basis for Congenital Heart Disease: Revisited: A Scientific Statement From the American Heart Association. Circulation, 138(21): e653–e711. DOI: 10.1161/cir.0000000000000606.
Zhao QM, Ma XJ, Ge XL, et al., 2014, Pulse Oximetry with Clinical Assessment to Screen for Congenital Heart Disease in Neonates in China: a prospective study. Lancet, 384(9945): 747–54. DOI: 10.1016/s0140-6736(14)60198-7.
Bengio Y, Courville A, Vincent P, 2013, Representation Learning: A Review and New Perspectives. IEEE Trans Pattern Anal Mach Intell, 35(8): 1798–828. DOI: 10.1109/tpami.2013.50.
Clifford G, Liu C, Moody B, et al., 2017, Recent Advances in Heart Sound Analysis. Physiol Meas, 38(8): E10–E25. DOI: 10.1088/1361-6579/aa7ec8.
Cheng J, Sun K, 2023, Heart Sound Classification Network Based on Convolution and Transformer. Sensors, 23(19): 1–19. DOI: 10.3390/s23198168.
Bozkurt B, Germanakis I, Stylianou Y, 2018, A study of Time-Frequency Features for CNN-based Automatic Heart Sound Classification for Pathology Detection. Comput Biol Med, 100: 132–43. DOI: 10.1016/j.compbiomed.2018.06.026.
Chakir F, Jilbab A, Nacir C, et al., 2018, Phonocardiogram Signals Processing Approach for PASCAL Classifying Heart Sounds Challenge. Signal Image Video Process, 12(6): 1149–55. DOI: 10.1007/s11760-018-1261-5.
Cheng X, Zhang Z, 2014, Denoising Method of Heart Sound Signals Based on Self-Construct Heart Sound Wavelet. AIP Advances, 4(8): 1–10. DOI: 10.1063/1.4891822.
Abdollahpur M, Ghaffari A, Ghiasi S, et al., 2017, Detection of Pathological Heart Sounds. Physiol Meas, 38(8): 1616–30. DOI: 10.1088/1361-6579/aa7840.
Li S, Li F, Tang S, et al., 2020, A Review of Computer-Aided Heart Sound Detection Techniques. BioMed Research International, 2020: 1–10. DOI: 10.1155/2020/5846191.
Mondal A, Saxena I, Tang H, et al., 2017, A Noise Reduction Technique Based on Nonlinear Kernel Function for Heart Sound Analysis. IEEE J Biomed Health Inform, 22(3): 775–784. DOI: 10.1109/jbhi.2017.2667685.
Gradolewski D, Magenes G, Johansson S, et al., 2019, A Wavelet Transform-Based Neural Network Denoising Algorithm for Mobile Phonocardiography. Sensors (Basel, Switzerland), 19(4): 1–18. DOI: 10.3390/s19040957.
Ali MN, El-Dahshan ELSA, Yahia AH, 2017, Denoising of Heart Sound Signals Using Discrete Wavelet Transform. Circuits, Systems, and Signal Processing, 36(11): 4482–4497. DOI: 10.1007/s00034-017-0524-7.
Vican I, Krekovic G, Jambrosic K, 2021, Can Empirical Mode Decomposition Improve Heartbeat Detection in Fetal Phonocardiography Signals? Comput Methods Programs Biomed, 203: 106038. DOI: 10.1016/j.cmpb.2021.106038.
Zheng Y, Guo X, Jiang H, et al., 2017, An innovative multi-level singular value decomposition and compressed sensing based framework for noise removal from heart sounds. Biomed Signal Process Control, 38: 34–43. DOI: 10.1016/j.bspc.2017.04.005.
Shah G, Koch P, Papadias CB, 2015, On the Blind Recovery of Cardiac and Respiratory Sounds. IEEE J Biomed Health Inform, 19(1): 151–157. DOI: 10.1109/jbhi.2014.2349156.
Guo Y, Yang H, Guo T, et al., 2023, A Novel Heart Sound Segmentation Algorithm via Multi-Feature Input and Neural Network with Attention Mechanism. Biomed Phys Eng Express, 9(1): 015012. DOI: 10.1088/2057-1976/ac9da6.
Fernando T, Ghaemmaghami H, Denman S, et al., 2020, Heart Sound Segmentation Using Bidirectional LSTMs With Attention. IEEE J Biomed Health Inform, 24(6): 1601–1609. DOI: 10.1109/jbhi.2019.2949516.
Renna F, Oliveira J, Coimbra MT, 2019, Deep Convolutional Neural Networks for Heart Sound Segmentation. IEEE J Biomed Health Inform, 23(6): 2435–2445. DOI: 10.1109/jbhi.2019.2894222.
NivithaVarghees V, Ramachandran KI, 2017, Effective Heart Sound Segmentation and Murmur Classification Using Empirical Wavelet Transform and Instantaneous Phase for Electronic Stethoscope. IEEE Sens J, 17(12): 3861–3872. DOI: 10.1109/jsen.2017.2694970.
Springer D, Tarassenko L, Clifford G, 2016, Logistic Regression-HSMM-Based Heart Sound Segmentation. IEEE T Bio-Med Eng, 63 4: 822–832.
Papadaniil CD, Hadjileontiadis LJ, 2014, Efficient Heart Sound Segmentation and Extraction Using Ensemble Empirical Mode Decomposition and Kurtosis Features. IEEE J Biomed Health Inform, 18(4): 1138–1152. DOI: 10.1109/jbhi.2013.2294399.
Kay E, Agarwal A, 2017, DropConnected Neural Networks Trained on Time-Frequency and Inter-Beat Features for Classifying Heart Sounds. Physiol Meas, 38(8): 1645–1657.DOI: 10.1088/1361-6579/aa6a3d.
Nogueira DM, Ferreira CA, Gomes EF, et al., 2019, Classifying Heart Sounds Using Images of Motifs, MFCC and Temporal Features. J Med Syst, 43(6): 1–13. DOI: 10.1007/s10916-019-1286-5.
Zeng W, Yuan J, Yuan C, et al., 2020, A New Approach for the Detection of Abnormal Heart Sound Signals Using TQWT, VMD and Neural Networks. Artif Intell Rev, 54(3): 1613–1647. DOI: 10.1007/s10462-020-09875-w.
Li F, Zhang Z, Wang L, et al., 2022, Heart Sound Classification Based on Improved Mel-Frequency Spectral Coefficients and Deep Residual Learning. Front Physiol, 13: 1–16. DOI: 10.3389/fphys.2022.1084420.
Aziz S, Khan MU, Alhaisoni M, et al., 2020, Phonocardiogram Signal Processing for Automatic Diagnosis of Congenital Heart Disorders through Fusion of Temporal and Cepstral Features. Sensors, 20 (13): 3790. DOI: 10.3390/s20133790.
Potes C, Parvaneh S, Rahman A, et al., 2016, Ensemble of Feature-Based and Deep Learning-Based Classifiers for Detection of Abnormal Heart Sounds. CinC, 43 : 182–399. DOI: 10.22489/CinC.2016.182-399
Deng SW, Han JQ, 2016, Towards Heart Sound Classification Without Segmentation via Autocorrelation Feature and Diffusion Maps. Future Gener Comput Syst, 60: 13–21. DOI: 10.1016/j.future.2016.01.010.
Yaseen, Son GY, Kwon S, 2018, Classification of Heart Sound Signal Using Multiple Features. Appl Sci, 8 (12): 2344. DOI: 10.3390/app8122344.
Lili ZHU, Jiahua PAN, Jihong SHI, et al. 2019, Research on Recognition of CHD Heart Sound Using MFCC and LPCC. J Phys Conf Ser, 1169: 1–8. DOI: 10.1088/1742-6596/1169/1/012011.
Chen W, Sun Q, Chen X, et al., 2021, Deep Learning Methods for Heart Sounds Classification: A Systematic Review. Entropy, 23 (6): 667. DOI: 10.3390/e23060667.
Hinton G, Osindero S, Welling M, et al., 2006, Unsupervised Discovery of Nonlinear Structure Using Contrastive Backpropagation. Cogn Sci, 30 (4): 725–731. DOI: 10.1207/s15516709cog0000_76.
Yu X, Pang W, Xu Q, et al., 2020, Mammographic Image Classification with Deep Fusion Learning. Sci Rep, 10 (1): 1–11. DOI: 10.1038/s41598-020-71431-x.
Alipanahi B, Delong A, Weirauch MT, et al., 2015, Predicting the Sequence Specificities of DNA- and RNA-Binding Proteins by Deep Learning. Nat Biotechnol, 33 (8): 831–838. DOI: 10.1038/nbt.3300.
Shen D, Wu G, Suk HI, 2017, Deep Learning in Medical Image Analysis. Annu Rev Biomed Eng, 19 (1): 221–248. DOI: 10.1146/annurev-bioeng-071516-044442.
Yu D, Deng L, 2011, Deep Learning and Its Applications to Signal and Information Processing [Exploratory DSP]. IEEE Signal Process Mag, 28 (1): 145–154. DOI: 10.1109/msp.2010.939038.
Huai X, Kitada S, Choi D, et al., 2021, Heart Sound Recognition Technology Based on Convolutional Neural Network. Inform Health Soc Care, 46 (3): 320–332. DOI: 10.1080/17538157.2021.1893736.
Oh SL, Jahmunah V, Ooi CP, et al., 2020, Classification of Heart Sound Signals Using a Novel Deep WaveNet Model. Comput Methods Programs Biomed, 196: 105604. DOI: 10.1016/j.cmpb.2020.105604.
Deng M, Meng T, Cao J, et al., 2020, Heart Sound Classification Based on Improved MFCC Features and Convolutional Recurrent Neural Networks. Neural Netw, 130: 22–32.. DOI: 10.1016/j.neunet.2020.06.015.
Kui H, Pan J, Zong R, et al., 2021, Heart Sound Classification Based on Log Mel-Frequency Spectral Coefficients Features and Convolutional Neural Networks. Biomed Signal Process Control, 69: 102893. DOI: 10.1016/j.bspc.2021.102893.
Krishnan PT, Balasubramanian P, Umapathy S, 2020, Automated Heart Sound Classification System from Unsegmented Phonocardiogram (PCG) Using Deep Neural Network. Phys Eng Sci Med, 43 (2): 505–515. DOI: 10.1007/s13246-020-00851-w.
Li F, Liu M, Zhao Y, et al., 2019, Feature Extraction and Classification of Heart Sound Using 1D Convolutional Neural Networks. EURASIP J Adv Signal Process, 2019 (1): 59. DOI: 10.1186/s13634-019-0651-3.
Xiao B, Xu Y, Bi X, et al., 2020, Follow the Sound of Children’s Heart: A Deep-Learning-Based Computer-Aided Pediatric CHDs Diagnosis System. IEEE Internet Things J, 7 (3): 1994–2004. DOI: 10.1109/jiot.2019.2961132.
Xu W, Yu K, Ye J, et al., 2022, Automatic Pediatric Congenital Heart Disease Classification Based on Heart Sound Signal. Artif Intell Med, 126: 102257. DOI: 10.1016/j.artmed.2022.102257.
Chowdhury MEH, Khandakar A, Alzoubi K, et al., 2019, Real-Time Smart-Digital Stethoscope System for Heart Diseases Monitoring. Sensors, 19 (12): 2781. DOI: 10.3390/s19122781.
Leng S, Tan RS, Chai KTC, et al., 2015, The Electronic Stethoscope. Biomed Eng Online, 14 (1): 66. DOI: 10.1186/s12938-015-0056-y.
Dominguez-Morales JP, Jimenez-Fernandez AF, Dominguez-Morales MJ, et al., 2018, Deep Neural Networks for the Recognition and Classification of Heart Murmurs Using Neuromorphic Auditory Sensors. IEEE Trans Biomed Circuits Syst, 12 (1): 24–34.
Sun S, Jiang Z, Wang H, et al., 2014, Automatic Moment Segmentation and Peak Detection Analysis of Heart Sound Pattern via Short-Time Modified Hilbert Transform. Comput Methods Programs Biomed, 114 (3): 219–230. DOI: 10.1016/j.cmpb.2014.02.004.