<h4>Introduction</h4>Application of Deep Learning (DL) methods is being increasingly appreciated by researchers from the biomedical engineering domain in which heart sound analysis is an important topic of study. Diversity in methodology, results, and complexity causes uncertainties in obtaining a realistic picture of the methodological performance from the reported methods.<h4>Methods</h4>This survey paper provides the results of a broad retrospective study on the recent advances in heart sound analysis using DL methods. Representation of the results is performed according to both methodological and applicative taxonomies. The study method covers a wide span of related keywords using well-known search engines. Implementation of the observed methods along with the related results is pervasively represented and compared.<h4>Results and discussion</h4>It is observed that convolutional neural networks and recurrent neural networks are the most commonly used ones for discriminating abnormal heart sounds and localization of heart sounds with 67.97% and 33.33% of the related papers, respectively. The convolutional neural network and the autoencoder network show a perfect accuracy of 100% in the case studies on the classification of abnormal from normal heart sounds. Nevertheless, this superiority against other methods with lower accuracy is not conclusive due to the inconsistency in evaluation.

Timely and reliable fetal monitoring is crucial to prevent adverse events during pregnancy and delivery. Fetal phonocardiography, i.e., the recording of fetal heart sounds, is emerging as a novel possibility to monitor fetal health status. Indeed, due to its passive nature and its noninvasiveness, the technique is suitable for long-term monitoring and for telemonitoring applications. Despite the high share of literature focusing on signal processing, no previous work has reviewed the technological hardware solutions devoted to the recording of fetal heart sounds. Thus, the aim of this scoping review is to collect information regarding the acquisition devices for fetal phonocardiography (FPCG), focusing on technical specifications and clinical use. Overall, PRISMA-guidelines-based analysis selected 57 studies that described 26 research prototypes and eight commercial devices for FPCG acquisition. Results of our review study reveal that no commercial devices were designed for fetal-specific purposes, that the latest advances involve the use of multiple microphones and sensors, and that no quantitative validation was usually performed. By highlighting the past and future trends and the most relevant innovations from both a technical and clinical perspective, this review will represent a useful reference for the evaluation of different acquisition devices and for the development of new FPCG-based systems for fetal monitoring.

<h4>Introduction</h4>Pre-test probability stratification of individuals with suspected obstructive coronary artery disease (CAD) has remained suboptimal for many years. Consequently, the majority of diagnostic tests used to rule out CAD exhibit normal results. An acoustic device capable of measuring micro bruits caused by stenosis-induced turbulence in the coronary circulation has showcased potential for stratifying CAD. The aim of this meta-analysis was to investigate the conceivable diagnostic value of phonocardiogram (PCG) in detecting the presence of CAD.<h4>Methods</h4>We conducted a comprehensive search of PubMed, EuropePMC, and ScienceDirect for articles published through January 2025. Studies were eligible if they assessed the accuracy of PCG using the CADScor® system in predicting CAD and provided enough data to construct a 2 × 2 contingency table.<h4>Results</h4>A total of 4 studies involving 4,050 patients were included for the final analysis. The pooled sensitivity and specificity were 87% (95% CI, 80%-92%) and 35% (95% CI, 21%-52%), respectively. The pooled positive likelihood ratio (PLR) was 1.34 (95% CI, 1.09-1.64) and the pooled negative likelihood ratio (NLR) was 0.37 (95% CI, 0.25-0.55). The area under the receiver operating characteristic curve (AUC) was 0.79 (95% CI, 0.75-0.82) in predicting CAD. Fagan's nomogram showed that the posterior probability of PCG with the CADScor® system for the detection of CAD was 19% when the CAD-score was above the cut-off value, and 6% in those with CAD-score below the cut-off value.<h4>Conclusion</h4>Phonocardiography shows promise as a rule-out tool for patients with suspected CAD.<h4>Systematic review registration</h4>https://www.crd.york.ac.uk/PROSPERO/view/CRD42024550526, PROSPERO CRD42024550526.

[Comparative assessment of data of echocardiography and phonocardiography in the diagnosis of heart diseases]. A comparison was made between the echo- and phonocardiographic examinations and the final clinical diagnosis of 85 patients with various cardiac pathology. Echo- and phonocardiography were found to be not alternative, and the less -- contradictory, but mutually supplementing methods. Echocardiography has certain advantages over phonocardiography in the diagnosis of mitral valve defects -- in evaluating the degree of its stenosis and in characterizing the morphological changes of the valve, but it is somewhat inferior in diagnosing mitral insufficiency. In the diagnosis of aortic valve defects phonocardiography appears to be more informative since echocardiography does not always permit to record the state of the aortic valve. Indisputable advantages of echocardiography in the diagnosis of the tricuspid valve defects were revealed. The comparison of the data of echocardiography and phonocardiography permitted to decypher the syndrome of "a late systolic click with a late systolic murmur" that was previously interpreted as a pericardium sound.

[Possibilities of intracardiac phonocardiography in congenital defects with left-right shunt]. The author shares his experience from intracardial phonocardiography of 48 patients with congenital heart defects with leftright shunt. The importance of the method is stressed upon, particularly in cases with interauricular and interventricular defect, not only for the diagnosis of the disease but for the differential diagnosis in difficult cases as well. The characteristic murmurs are presented, recorded intracardially in the three of the basic congenital heart defect with left-right shunt--interauricular defect, interventricular defect, and open Botal's duct. Published in Vutreshni bolesti (1978)

[Cardiac Doppler in the selection of patients for aortic valvuloplasty. Comparison with data of phonomecanograms]. Between December 1986 and August 1987, 34 patients referred for aortic valvuloplasty, undergo before catheterization an ultrasonocardiography with continuous and pulsed Doppler study and a phonocardiography for 22 of them. They all present functional and physical signs of aortic stenosis. The cardiac Doppler enables a positive diagnosis in all patients, while the phonocardiography recordings fail to recognize a tight aortic stenosis. On the other hand, the Doppler enables a diagnosis of severity well correlated with the catheterization (r = 0.88 for maximum instantaneous gradients) in 30 patients: in four patients, the correlation could not be calculated because of technical problems related to the catheterization (2 patients) or the ultrasonic examination (2 patients). From this study, it results that the cardiac Doppler may perfectly select patients who are to undergo an aortic valvuloplasty, unlike phonocardiography. Published in Annales de cardiologie et d'angeiologie (1988)

<h4>Background and objective</h4>Artificial intelligence (AI) is increasingly embedded across cardiovascular care, serving as a powerful adjunct for symptom assessment, bedside examination, electrocardiography, and multimodality imaging interpretation. We aim to thoroughly review current evidence for AI applications across the cardiovascular diagnostic pathway and to highlight key considerations for clinical integration.<h4>Methods</h4>We performed a narrative review of clinical trials and observational studies retrieved from MEDLINE/PubMed, Embase, and Google Scholar (January 1^st 2000-July 10^th 2025), limited to publications in English, using AI- and cardiovascular diagnostic specific search terms. Regulatory resources [e.g., U.S. Food and Drug Administration (FDA) clearance databases and publicly available summaries] were also reviewed to identify cardiovascular AI software with regulatory authorization.<h4>Key content and findings</h4>Across diagnostic domains, AI has demonstrated potential to improve diagnostic performance and workflow efficiency. Large language models and other AI systems can support structured history-taking, triage, and automated clinical documentation. Digital stethoscope and phonocardiography algorithms enable scalable screening for murmurs and valvular disease with a higher sensitivity for murmur detection compared with conventional auscultation. Electrocardiography-based AI models have been reported for rapid detection of arrhythmias, ischemia, and heart failure with reduced ejection fraction (EF). In echocardiography, AI enables automated view classification, chamber quantification, EF estimation, and valve assessment, while substantially reducing acquisition and processing time. Advanced imaging tools support coronary computed tomography (CT) angiography plaque characterization, calcium scoring, and CT-derived fractional flow reserve (FFR), as well as cardiac magnetic resonance segmentation and scar/late gadolinium enhancement (LGE) quantification. However, much of the evidence remains retrospective with heterogeneous endpoints, and outcome-improving, prospective, real-world integration studies remain limited.<h4>Conclusions</h4>Future work should prioritize multicenter prospective validation and implementation studies that address model generalizability, quality control, bias, data drift, and governance. Multimodal, workflow-embedded AI systems that fuse clinical and imaging signals may ultimately enable individualized risk prediction and improve access and cardiovascular outcomes.

Do you hear what you see? Utilizing phonocardiography to enhance proficiency in cardiac auscultation | Perspectives on Medical Education | Springer Nature Link # Do you hear what you see? Utilizing phonocardiography to enhance proficiency in cardiac auscultation - Original Article - Open access - Published: 12 January 2021 - Volume 10, pages 148–154 (2021) - Cite this article You have full access to this open access article Perspectives on Medical Education ## Abstract ### Introduction Cardiac auscultation skills have proven difficult to train and maintain. The authors investigated whether using phonocardiograms as visual adjuncts to audio cases improved first-year medical students’ cardiac auscultation performance. ### Methods The authors randomized 135 first-year medical students using an email referral link in 2018 and 2019 to train using audio-only cases (audio group) or audio with phonocardiogram tracings (combined group). Training included 7 cases with normal and abnormal auscultation findings. The assessment included feature identification and diagnostic accuracy using 14 audio-only cases, 7 presented during training, and 7 alternate versions of the same diagnoses.

Effects of precise cardio sounds on the success rate of phonocardiography - PMC PLoS One . 2024 Jul 15;19(7):e0305404. doi: 10.1371/journal.pone.0305404 # Effects of precise cardio sounds on the success rate of phonocardiography 1,* Editor: Ali Mohammad Alqudah3 - Author information - Article notes - Copyright and License information 1Department of Mechanical Engineering, Pohang University of Science and Technology, Pohang, Gyeongbuk, Republic of Korea 2Department of Thoracic and Cardiovascular Surgery, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea 3University of Manitoba, CANADA Competing Interests: The authors have declared that no competing interests exist. ✉ * E-mail: wkmoon@postech.ac.kr #### Roles Youngsin Kim: Conceptualization, Formal analysis, Investigation, Methodology, Resources, Software, Validation, Visualization, Writing – original draft Mihyung Moon: Conceptualization, Data curation, Funding acquisition, Investigation, Resources, Supervision, Validation, Writing – review & editing Seokwhwan Moon: Conceptualization, Data curation, Funding acquisition, Investigation, Project administration, Re

The Effect of Signal Duration on the Classification of Heart Sounds: A Deep Learning Approach - PMC[Skip to main content](#main-content)  An official website of the United States government Here's how you know Here's how you know  **Official websites use .gov** A**.gov**website belongs to an official government organization in the United States.  **Secure .gov websites use HTTPS** A**lock**(LockLocked padlock icon) or**https://**means you've safely connected to the .gov website. Share sensitive information only on official, secure websites. [](https://www.ncbi.nlm.nih.gov/) Search Log in * [Dashboard](https://www.ncbi.nlm.nih.gov/myncbi/) * [Publications](https://www.ncbi.nlm.nih.gov/myncbi/collections/bibliography/) * [Account settings](https://www.ncbi.nlm.nih.gov/account/settings/) * Log out Search…Search NCBI [](https://pmc.ncbi.nlm.nih.gov/) Search PMC Full-Text ArchiveSearch in PMC![Search](https://pmc.ncbi.nl