Abstract
Coronary artery disease (CAD) remains a major contributor to morbidity and mortality worldwide. Heart sound analysis has been investigated as a noninvasive approach to CAD detection, although existing evidence has been inconsistent. This systematic review evaluated the diagnostic performance of heart sound analysis for identifying CAD (ā„50% stenosis). A search of four databases identified 1082 records, among which 40 studies involving 13,814 participants met the inclusion criteria. Among the 21 studies using signal processing methods, all but one of the larger studies (>50 participants, nā=ā15) reported diagnostic accuracy below 75%. The majority of signal processing studies lacked validation on independent datasets, thereby limiting confidence in the reliability of their reported performance. In contrast, 15 of the 19 studies applying machine learning-based methods reported accuracy, sensitivity, and specificity consistently above 80%. Moreover, 15 of these 19 studies conducted independent dataset validation, indicating comparatively stronger generalizability. Studies that used the full heart sound signal as model input also tended to achieve higher sensitivity than those using only the diastolic component, suggesting that utilizing the complete waveform preserves diagnostically informative features. These findings indicate that machine learning-based heart sound analysis may have diagnostic value for CAD, and larger multicenter studies are needed to further assess its clinical applicability and robustness.
Similar content being viewed by others
Data availability
All data analyzed in this study were obtained from published literature and are fully presented in the tables and figures within the manuscript.
References
Mensah, G. A. et al. Global burden of cardiovascular diseases and risks, 1990-2022. J. Am. Coll. Cardiol. 82, 2350ā2473 (2023).
Vrints, C. et al. 2024 ESC guidelines for the management of chronic coronary syndromes. Eur. Heart J. 45, 3415ā3537 (2024).
Tavakol, M., Ashraf, S. & Brener, S. J. Risks and complications of coronary angiography: a comprehensive review. Glob. J. Health Sci. 4, 65ā93 (2012).
Knuuti, J. et al. 2019 ESC guidelines for the diagnosis and management of chronic coronary syndromes the task force for the diagnosis and management of chronic coronary syndromes of the European Society of Cardiology (ESC). Eur. Heart J. 41, 407ā477 (2020).
Ku, D. N. Blood flow in arteries. Annu. Rev. Fluid Mech. 29, 399ā434 (1997).
Mahalingam, A. et al. Numerical analysis of the effect of turbulence transition on the hemodynamic parameters in human coronary arteries. Cardiovasc. Diagn. Ther. 6, 208ā220 (2016).
Carvalho, V., Rodrigues, N., Lima, R. A. & Teixeira, S. Numerical simulation of blood pulsatile flow in stenotic coronary arteries: the effect of turbulence modeling and non-Newtonian assumptions. In 2020 24th International Conference on Circuits, Systems, Communications and Computers (CSCC) 112ā116 (IEEE, 2020).
Semmlow, J. & Rahalkar, K. Acoustic Detection of Coronary Artery Disease. Annu. Rev. Biomed. Eng. 9, 449ā469 (2007).
Adolph, R. J., Stephens, J. F. & Tanaka, K. The clinical value of frequency analysis of the first heart sound in myocardial infarction. Circulation 41, 1003ā1014 (1970).
Cohn, P. F., Fox, K. M. & Daly, C. Silent myocardial ischemia. Circulation 108, 1263ā1277 (2003).
Lee, E., Michaels, A. D., Selvester, R. H. & Drew, B. J. Frequency of diastolic third and fourth heart sounds with myocardial ischemia induced during percutaneous coronary intervention. J. Electrocardiol. 42, 39ā45 (2009).
Semmlow, J., Welkowitz, W., Kostis, J. & Mackenzie, J. W. Coronary artery diseaseācorrelates between diastolic auditory characteristics and coronary artery stenoses. IEEE Trans. Biomed. Eng. BME-30, 136ā139 (1983).
Lehmacher, J. et al. Diagnostic performance of a device for acoustic heart sound analysis in patients with suspected myocardial infarction. Open Heart 10, e002090 (2023).
Ainiwaer, A. et al. Deep learning of heart-sound signals for efficient prediction of obstructive coronary artery disease. Heliyon 10, e23354 (2024).
Liu, T. et al. Detection of coronary artery disease using multi-domain feature fusion of multi-channel heart sound signals. Entropy 23, 642 (2021).
Akay, M., Welkowitz, W., Semmlow, J. L., Akay, Y. M. & Kostis, J. Noninvasive acoustical detection of coronary artery disease using the adaptive line enhancer method. Med. Biol. Eng. Comput. 30, 147ā154 (1992).
Akay, M., Semmlow, J. L., Welkowitz, W., Bauer, M. D. & Kostis, J. B. Detection of coronary occlusions using autoregressive modeling of diastolic heart sounds. IEEE Trans. Biomed. Eng. 37, 366ā373 (1990).
Zhao Zhidong. Noninvasive diagnosis of coronary artery disease based on instantaneous frequency of diastolic murmurs and SVM. In 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference (ed. He, B.) 5651ā5654 (IEEE, 2005).
Akay, M. et al. The assessment of stent effectiveness using a wearable beamforming MEMS microphone array system. IEEE J. Transl. Eng. Health Med. 4, 1ā10 (2016).
Akay, M., Akay, Y. M., Welkowitz, W., Semmlow, J. L. & Kostis, J. Noninvasive characterization of the sound pattern caused by coronary artery stenosis using FTF/FAEST zero tracking filters: normal/abnormal study. Ann. Biomed. Eng. 21, 175ā182 (1993).
Akay, Y. M., Akay, M., Welkowitz, W., Semmlow, J. L. & Kostis, J. B. Noninvasive acoustical detection of coronary artery disease: a comparative study of signal processing methods. IEEE Trans. Biomed. Eng. 40, 571ā578 (1993).
Hammershoi, D. & Egon, T. Coronary artery disease and low frequency heart sound signatures. Comput. Cardiol 38, 481ā484 (2011).
Zhao Zhidong. Instantaneous frequency analysis of diastolic murmurs for coronary artery disease. In 2005 International Conference on Neural Networks and Brain Vol. 2, 1097ā1100 (IEEE, 2005).
Semmlow, J. L., Akay, M. & Welkowitz, W. Noninvasive detection of coronary artery disease using parametric spectral analysis methods. IEEE Eng. Med. Biol. Mag. 9, 33ā36 (1990).
Akay, M., Welkowitz, W., Semmlow, J. L. & Kostis, J. Application of the ARMA method to acoustic detection of coronary artery disease. Med. Biol. Eng. Comput. 29, 365ā372 (1991).
Schmidt, S. E., Holst-Hansen, C., Hansen, J., Toft, E. & Struijk, J. J. Acoustic features for the identification of coronary artery disease. IEEE Trans. Biomed. Eng. 62, 2611ā2619 (2015).
Schmidt, S. E. et al. Coronary artery disease risk reclassification by a new acoustic-based score. Int. J. Cardiovasc. Imaging 35, 2019ā2028 (2019).
Winther, S. et al. Diagnostic performance of an acoustic-based system for coronary artery disease risk stratification. Heart 104, 928ā935 (2018).
Winther, S. et al. Diagnosing coronary artery disease by sound analysis from coronary stenosis induced turbulent blood flow: diagnostic performance in patients with stable angina pectoris. Int. J. Cardiovasc. Imaging 32, 235ā245 (2016).
Rasmussen, L. D. et al. Likelihood reclassification by an acoustic-based score in suspected coronary artery disease. Heart Br. Card. Soc. 109, 1223ā1230 (2023).
Akay, M., Akay, Y. M., Welkowitz, W., Semmlow, J. L. & Kostis, J. B. Application of adaptive filters to noninvasive acoustical detection of coronary occlusions before and after angioplasty. IEEE Trans. Biomed. Eng. 39, 176ā184 (1992).
Winther, S. et al. Advanced heart sound analysis as a new prognostic marker in stable coronary artery disease. Eur. Heart J. Digit. Health 2, 279ā289 (2021).
Akay, M., Akay, Y. M., Welkowitz, W., Semmlow, J. L. & Kostis, J. B. Noninvasive detection of coronary artery disease using neural networks. In Proceedings of the 13th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (eds Nagel, J. H. & Smith, W. M.), 1434ā1435 (IEEE, 1991).
Akay, M. & Welkowitz, W. Acoustical detection of coronary occlusions using neural networks. J. Biomed. Eng. 15, 469ā473 (1993).
Partovi, E., Babic, A. & Gharehbaghi, A. A review on deep learning methods for heart sound signal analysis. Front. Artif. Intell. 7, 1434022 (2024).
Pathak, A., Mandana, K. & Saha, G. Ensembled transfer learning and multiple kernel learning for phonocardiogram based atherosclerotic coronary artery disease detection. IEEE J. Biomed. Health Inform. 26, 2804ā2813 (2022).
Dai, Y. et al. Deep learning fusion framework for automated coronary artery disease detection using raw heart sound signals. Heliyon 10, e35631 (2024).
Huang, Y. et al. A customized framework for coronary artery disease detection using phonocardiogram signals. Biomed. Signal Process. Control 78, 103982 (2022).
Akay, M. Noninvasive diagnosis of coronary artery disease using a neural network algorithm. Biol. Cybern. 67, 361ā367 (1992).
Iqtidar, K., Qamar, U., Aziz, S. & Khan, M. U. Phonocardiogram signal analysis for classification of coronary artery diseases using MFCC and 1D adaptive local ternary patterns. Comput. Biol. Med. 138, 104926 (2021).
Larsen, B. S. et al. Improved pre-test likelihood estimation of coronary artery disease using phonocardiography. Eur. Heart J.āDigit. Health 3, 600ā609 (2022).
Tateishi, O. Clinical significance of the acoustic detection of coronary artery stenosis. J. Cardiol. 38, 255ā262 (2001).
Korjian, S., Chrysant, G. S. & Baron, S. J. Acoustic-based systems for the evaluation of coronary artery disease: a systematic literature review. Cardiovasc. Revasc. Med 81, 137ā143 (2025).
Agnew, T., Bucher, H., McDonald, L. & Seymour, J. Delayed closure of the aortic valve in ischaemic heart disease. Br. Heart J. 29(5), 775ā777 (1967).
Dev Sharma, S., Ballantyne, F. & Goldstein, S. The relationship of ventricular asynergy in coronary artery disease to ventricular premature beats. Chest 66, 358ā362 (1974).
Liang, F. & Wang, Y. Coronary heart disease and atrial fibrillation: A vicious cycle. Am. J. Physiol.-Heart Circ. Physiol. 320, H1āH12 (2021).
Li, H. et al. A fusion framework based on multi-domain features and deep learning features of phonocardiogram for coronary artery disease detection. Comput. Biol. Med. 120, 103733 (2020).
FABER, J. J. Damping of sound on the chest surface. Circ Res. 13, 352ā358 (1963).
Griffel, B., Zia, M. K., Fridman, V., Saponieri, C. & Semmlow, J. L. Detection of coronary artery disease using automutual information. Cardiovasc. Eng. Technol. 3, 333ā344 (2012).
Buterez, D., Janet, J. P., Oglic, D. & LiĆ², P. An end-to-end attention-based approach for learning on graphs. Nat. Commun. 16, 5244 (2025).
Poterucha, T. J. et al. Detecting structural heart disease from electrocardiograms using AI. Nature 644, 221ā230 (2025).
Samanta, P., Pathak, A., Mandana, K. & Saha, G. Classification of coronary artery diseased and normal subjects using multi-channel phonocardiogram signal. Biocybern. Biomed. Eng. 39, 426ā443 (2019).
Ayatollahi, H., Gholamhosseini, L. & Salehi, M. Predicting coronary artery disease: a comparison between two data mining algorithms. BMC Public Health 19, 448 (2019).
Zhang, J. et al. ECG-based multi-class arrhythmia detection using spatio-temporal attention-based convolutional recurrent neural network. Artif. Intell. Med. 106, 101856 (2020).
Li, Y. et al. Smartphone for heart sound measurement in hospital: Feasibility and influencing factors. Eur. Heart J.āDigit. Health 6, 486ā495 (2025).
Ren, H. et al. Smartphone-measured heart sounds for atrial fibrillation screening in community populations. Circulation 152, 283ā285 (2025).
AKAY, M. Harmonic decomposition of diastolic heart sounds associated with coronary-artery disease. Signal Process 41, 79ā90 (1995).
Akay, M. et al. Dynamics of diastolic sounds caused by partially occluded coronary arteries. IEEE Trans. Biomed. Eng. 56, 513ā517 (2009).
Griffel, B., Zia, M. K., Fridman, V., Saponieri, C. & Semmlow, J. L. Path length entropy analysis of diastolic heart sounds. Comput. Biol. Med. 43, 1154ā1166 (2013).
Makaryus, A. N. et al. Utility of an advanced digital electronic stethoscope in the diagnosis of coronary artery disease compared with coronary computed tomographic angiography. Am. J. Cardiol. 111, 786ā792 (2013).
Azimpour, F., Caldwell, E., Tawfik, P., Duval, S. & Wilson, R. F. Audible coronary artery stenosis. Am. J. Med. 129, 515ā521.e3 (2016).
Pathak, A., Samanta, P., Mandana, K. & Saha, G. Detection of coronary artery atherosclerotic disease using novel features from synchrosqueezing transform of phonocardiogram. Biomed. Signal Process. Control 62, 102055 (2020).
Renker, M. et al. Prospective validation of an acoustic-based system for the detection of obstructive coronary artery disease in a high-prevalence population. Heart Vessels 36, 1132ā1140 (2021).
Khan, M. U. et al. A two-stage classification model integrating feature fusion for coronary artery disease detection and classification. Multimed. Tools Appl. 81, 13661ā13690 (2022).
Schmidt, S. E. et al. Coronary artery disease detected by low frequency heart sounds. Cardiovasc. Eng. Technol. 13, 864ā871 (2022).
Yin, C. et al. Detection of coronary artery disease based on clinical phonocardiogram and multiscale attention convolutional compression network. IEEE J. Biomed. Health Inform. 28, 1353ā1362 (2024).
Liu, X., Lv, C., Cao, L. & Guo, X. Detection of coronary artery disease using a triplet network and hybrid loss function on heart sound signal. Biomed. Signal Process. Control 104, 107601 (2025).
Fynn, M. et al. Practicality meets precision: Wearable vest with integrated multi-channel PCG sensors for effective coronary artery disease pre-screening. Comput. Biol. Med. 189, 109904 (2025).
Acknowledgements
This study was supported by the China Scholarship Council (202308650023) and the Nederlandse Organisatie voor Wetenschappelijk Onderzoek (NWO) Take-off Fase 1 WO (No. 21431). The funding bodies had no role in the study design, data analysis, interpretation, or manuscript preparation.
Author information
Authors and Affiliations
Contributions
A.A. and H.L. conducted data collection and analysis. Together with T.K., T.D., and F.P., they contributed to the study design and manuscript drafting. H.L., T.D., and F.P. also provided supervision. K.K., X.M., and M.A. contributed to project preparation and provided input during manuscript refinement. All authors reviewed the manuscript critically and approved the final version.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisherās note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary information
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the articleās Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the articleās Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Ainiwaer, A., Konings, T.J., Kadier, K. et al. Coronary artery disease diagnosis with signal processing and machine learning of heart sound signals: a systematic review. npj Digit. Med. (2026). https://doi.org/10.1038/s41746-026-02530-8
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41746-026-02530-8
