{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T16:00:40Z","timestamp":1780675240581,"version":"3.54.1"},"reference-count":21,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T00:00:00Z","timestamp":1758931200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.mdpi.com"],"crossmark-restriction":true},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: With a 17.9 million annual mortality rate, cardiovascular disease is the leading global cause of death. As such, early detection and disease diagnosis are critical for effective treatment and symptom management. Cardiac auscultation, the process of listening to the heartbeat, often provides the first indication of underlying cardiac conditions. This practice allows for the identification of heart murmurs caused by turbulent blood flow. In this exploratory research paper, we propose an AI model to streamline this process to improve diagnostic accuracy and efficiency. Methods: We utilized data from the 2022 George Moody PhysioNet Heart Sound Classification Challenge, comprising phonocardiogram recordings of individuals under 21 years of age in Northeast Brazil. Only patients who had recordings from all four heart valves were included in our dataset. Audio files were synchronized across all recordings and converted to Mel spectrograms before being passed into a pre-trained Vision Transformer, and finally a MiniROCKET model. Additionally, data augmentation was conducted on audio files and spectrograms to generate new data, extending our total sample size from 928 spectrograms to 14,848. Results: Compared to the existing methods in the literature, our model yielded significantly enhanced quality assessment metrics, including Weighted Accuracy, Sensitivity, and F-Score, and resulted in a fast evaluation speed of 0.02 s per patient. Conclusions: The implementation of our method for the detection of heart murmurs can supplement physician diagnosis and contribute to earlier detection of underlying cardiovascular conditions, fast diagnosis times, increased scalability, and enhanced adaptability.<\/jats:p>","DOI":"10.3390\/diagnostics15192471","type":"journal-article","created":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T10:49:34Z","timestamp":1759142974000},"page":"2471","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Heart Murmur Detection in Phonocardiogram Data Leveraging Data Augmentation and Artificial Intelligence"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7389-9800","authenticated-orcid":false,"given":"Melissa","family":"Valaee","sequence":"first","affiliation":[{"name":"Faculty of Health Sciences, McMaster University, Hamilton, ON L8N 3Z5, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7217-3467","authenticated-orcid":false,"given":"Shahram","family":"Shirani","sequence":"additional","affiliation":[{"name":"Department of Electrical & Computer Engineering, Faculty of Engineering, McMaster University, Hamilton, ON L8S 4K1, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,27]]},"reference":[{"key":"ref_1","unstructured":"(2025, August 06). World Health Organization: Cardiovascular Diseases. Available online: https:\/\/www.who.int\/health-topics\/cardiovascular-diseases#tab=tab_1."},{"key":"ref_2","unstructured":"Dornbush, S., and Turnquest, A.E. (2025, August 05). Physiology, Heart Sounds, StatPearls, Available online: https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK541010\/."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Reyna, M.A., Kiarashi, Y., Elola, A., Oliveira, J., Renna, F., Gu, A., Perez Alday, E.A., Sadr, N., Sharma, A., and Kpodonu, J. (2023). Heart murmur detection from phonocardiogram recordings: The George B. Moody PhysioNet Challenge 2022. PLoS Digit. Health, 2.","DOI":"10.1371\/journal.pdig.0000324"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1080\/13645706.2019.1575882","article-title":"Introduction to artificial intelligence in medicine","volume":"2","author":"Mintz","year":"2019","journal-title":"Minim. Invasive Ther. Allied Technol."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Fetzer, J.H. (1990). What is Artificial Intelligence?. Artificial Intelligence: Its Scope and Limits, Springer Netherlands. Available online: http:\/\/link.springer.com\/10.1007\/978-94-009-1900-6_1.","DOI":"10.1007\/978-94-009-1900-6_1"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Dempster, A., Schmidt, D.F., and Webb, G.I. (2021, January 14). MiniRocket: A Very Fast (Almost) Deterministic Transform for Time Series Classification. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Virtual Event, Singapore.","DOI":"10.1145\/3447548.3467231"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2524","DOI":"10.1109\/JBHI.2021.3137048","article-title":"The CirCor DigiScope Dataset: From Murmur Detection to Murmur Classification","volume":"26","author":"Oliveira","year":"2022","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"e215","DOI":"10.1161\/01.CIR.101.23.e215","article-title":"PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals","volume":"101","author":"Goldberger","year":"2000","journal-title":"Circulation"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"6874","DOI":"10.1109\/JBHI.2024.3458430","article-title":"PCGmix: A Data-Augmentation Method for Heart-Sound Classification","volume":"28","author":"Gams","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Moles, L., Andres, A., Echegaray, G., and Boto, F. (2024). Exploring Data Augmentation and Active Learning Benefits in Imbalanced Datasets. Mathematics, 12.","DOI":"10.3390\/math12121898"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.gltp.2022.04.020","article-title":"A review: Data pre-processing and data augmentation techniques","volume":"3","author":"Maharana","year":"2022","journal-title":"Glob. Transit. Proc."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1369","DOI":"10.1098\/rstb.2007.2122","article-title":"Heart valve function: A biomechanical perspective","volume":"362","author":"Sacks","year":"2007","journal-title":"Phil. Trans. R Soc. B"},{"key":"ref_13","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2025, August 05). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. Available online: http:\/\/arxiv.org\/abs\/2010.11929."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1080\/00401706.1970.10488634","article-title":"Ridge Regression: Biased Estimation for Nonorthogonal Problems","volume":"12","author":"Hoerl","year":"1970","journal-title":"Technometrics"},{"key":"ref_15","first-page":"1","article-title":"Detection of Heart Murmurs in Phonocardiograms with Parallel Hidden Semi-Markov Models","volume":"498","author":"McDonald","year":"2022","journal-title":"2022 Comput. Cardiol."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Manshadi, O.D., and Mihandoost, S. (2024). Murmur identification and outcome prediction in phonocardiograms using deep features based on Stockwell transform. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-58274-6"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1016\/j.dsp.2015.07.003","article-title":"A new optimized Stockwell transform applied on synthetic and real non-stationary signals","volume":"46","author":"Moukadem","year":"2015","journal-title":"Digit. Signal Process."},{"key":"ref_18","first-page":"1","article-title":"A Lightweight Robust Approach for Automatic Heart Murmurs and Clinical Outcomes Classification from Phonocardiogram Recordings","volume":"498","author":"Lu","year":"2022","journal-title":"2022 Comput. Cardiol."},{"key":"ref_19","first-page":"1","article-title":"Hierarchical multi-scale convolutional network for murmurs detection on pcg signals","volume":"498","author":"Xu","year":"2022","journal-title":"2022 Comput. Cardiol."},{"key":"ref_20","first-page":"1","article-title":"Dual Bayesian ResNet: A Deep Learning Approach to Heart Murmur Detection","volume":"498","author":"Walker","year":"2022","journal-title":"2022 Comput. Cardiol."},{"key":"ref_21","first-page":"1","article-title":"Deep Learning Based Heart Murmur Detection using Frequency-time Domain Features of Heartbeat Sounds","volume":"498","author":"Lee","year":"2022","journal-title":"2022 Comput. Cardiol."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/19\/2471\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T11:19:37Z","timestamp":1759144777000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/19\/2471"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,27]]},"references-count":21,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["diagnostics15192471"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics15192471","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,27]]}}}