{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:45:21Z","timestamp":1760060721301,"version":"build-2065373602"},"reference-count":29,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Institute of Information &amp; communications Technology Planning &amp; Evaluation (IITP)","award":["IITP-2023-RS-2023-00256629","23-CM-DI-11"],"award-info":[{"award-number":["IITP-2023-RS-2023-00256629","23-CM-DI-11"]}]},{"name":"Institute of Civil-Military Technology Cooperation","award":["IITP-2023-RS-2023-00256629","23-CM-DI-11"],"award-info":[{"award-number":["IITP-2023-RS-2023-00256629","23-CM-DI-11"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Children"],"abstract":"<jats:p>Introduction: Advanced identification and intervention for Congenital Heart Defects (CHDs) in pediatric populations are crucial, as approximately 1% of neonates worldwide present with these conditions. Traditional methods of diagnosing CHDs often rely on stethoscope auscultation, which heavily depends on the clinician\u2019s expertise and may lead to the oversight of subtle acoustic indicators. Objectives: This study introduces an innovative deep-learning framework designed for the early diagnosis of congenital heart disease. It utilizes time-series data obtained from cardiac auditory signals captured through stethoscopes. Methods: The audio signals were processed into time\u2013frequency representations using Mel-Frequency Cepstral Coefficients (MFCCs). The architecture of the model combines Convolutional Neural Networks (CNNs) for effective feature extraction with Long Short-Term Memory (LSTM) networks to accurately model temporal dependencies. Impressively, the model achieved an accuracy of 98.91% in the early detection of CHDs. Results: While traditional diagnostic tools like Electrocardiograms (ECG) and Phonocardiograms (PCG) remain indispensable for confirming diagnoses, many AI studies have primarily targeted ECG and PCG datasets. This approach emphasizes the potential of cardiac acoustics for the early diagnosis of CHDs, which could lead to improved clinical outcomes for infants. Notably, the dataset used in this research is publicly available, enabling wider application and model training within the research community.<\/jats:p>","DOI":"10.3390\/children12091221","type":"journal-article","created":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T12:08:16Z","timestamp":1757678896000},"page":"1221","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep Learning for Heart Sound Abnormality of Infants: Proof-of-Concept Study of 1D and 2D Representations"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1342-3651","authenticated-orcid":false,"given":"Eashita","family":"Wazed","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju 61186, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9994-6549","authenticated-orcid":false,"given":"Jimin","family":"Lee","sequence":"additional","affiliation":[{"name":"SW Convergence Education Institute, Chosun University, Gwangju 61452, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8135-8252","authenticated-orcid":false,"given":"Hieyong","family":"Jeong","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju 61186, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1994","DOI":"10.1109\/JIOT.2019.2961132","article-title":"Follow the Sound of Children\u2019s Heart: A Deep-Learning-Based Computer-Aided Pediatric CHDs Diagnosis System","volume":"7","author":"Xiao","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Islam, R., Hassan, M., Raihan, M., Datto, S.K., Shahriar, A., and More, A. (2019, January 18\u201320). A Wireless Electronic Stethoscope to Classify Children Heart Sound Abnormalities. Proceedings of the 22nd International Conference on Computer and Information Technology (ICCIT), Dhaka, Bangladesh.","DOI":"10.1109\/ICCIT48885.2019.9038406"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Tao, Z., Ren, Z., Yang, X., Liang, Y., and Shi, X. (2023, January 5\u20138). 2D ViT and 1D CRNN-based Heart Sound Signals Detection Model. Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Istanbul, Turkiye.","DOI":"10.1109\/BIBM58861.2023.10385779"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Lu, K., Zhao, F., Gu, P., Wang, H., Zang, T., and Wang, H. (2023, January 5\u20138). TetraCVD: A Temporal-Textual Transformer based Model for Cardiovascular Disease Diagnosis. Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine, Istanbul, Turkiye.","DOI":"10.1109\/BIBM58861.2023.10385761"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"3811","DOI":"10.1007\/s00371-023-03031-5","article-title":"PCTMF-Net: Heart sound classification with parallel CNNs-transformer and second-order spectral analysis","volume":"39","author":"Wang","year":"2023","journal-title":"Vis. Comput."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Ren, Z., Qiao, Y., Yuan, Y., Zhou, Y., Liang, Y., and Shi, X. (2022, January 6\u20138). Time and time-frequency features integrated cnn model for heart sound signals detection. Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Las Vegas, NV, USA.","DOI":"10.1109\/BIBM55620.2022.9995295"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"13986","DOI":"10.1109\/ACCESS.2024.3356075","article-title":"Raw Waveform-Based Custom Scalogram CRNN in Cardiac Abnormality Diagnosis","volume":"12","author":"Radha","year":"2024","journal-title":"IEEE Access"},{"key":"ref_8","unstructured":"Islam, M.R., Rakib, M.h., and Raihan, M. (2024, March 01). Children Heart Sound\u2014Normal & Abnormal. Mendeley Data. 2023. v1. Available online: https:\/\/data.mendeley.com\/datasets\/5447z7m2rr\/1."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1007\/s00034-022-02124-1","article-title":"Heart sound classification using deep learning techniques based on log-mel spectrogram","volume":"42","author":"Nguyen","year":"2023","journal-title":"Circuits Syst. Signal Process."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"303","DOI":"10.3109\/03091902.2012.684831","article-title":"A Review of signal processing techniques for heart sound analysis in clinical diagnosis","volume":"36","author":"Emmanuel","year":"2012","journal-title":"J. Med. Eng. Technol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.ijcard.2021.12.012","article-title":"Deep learning-based computer-aided heart sound analysis in children with left-to-right shunt congenital heart disease","volume":"348","author":"Liu","year":"2022","journal-title":"Int. J. Cardiol."},{"key":"ref_12","unstructured":"Rubin, J., Abreu, R., Ganguli, A., Nelaturi, S., Matei, I., and Sricharan, K. (2017). Recognizing abnormal heart sounds using deep learning. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.cmpb.2009.10.006","article-title":"Novel method for pediatric heart sound segmentation without using the ECG","volume":"99","author":"Sepehri","year":"2010","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.neucom.2020.01.019","article-title":"Toward improving ECG biometric identification using cascaded convolutional neural networks","volume":"391","author":"Li","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhao, Q., Geng, S., Wang, B., Sun, Y., Nie, W., Bai, B., Yu, C., Zhang, F., Tang, G., and Zhang, D. (2023). Deep Learning for Heart Sound Analysis: A Literature Review. medRxiv.","DOI":"10.1101\/2023.09.16.23295653"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"936","DOI":"10.1109\/TCBB.2023.3247433","article-title":"A robust deep learning framework based on spectrograms for heart sound classification","volume":"21","author":"Chen","year":"2023","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2322","DOI":"10.1542\/peds.2006-1557","article-title":"Assessing children\u2019s heart sounds at a distance with digital recordings","volume":"118","author":"Finley","year":"2006","journal-title":"Pediatrics"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2711","DOI":"10.1161\/01.CIR.103.22.2711","article-title":"Artificial neural network\u2013based method of screening heart murmurs in children","volume":"103","author":"DeGroff","year":"2023","journal-title":"Circulation"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1016\/j.procs.2015.08.045","article-title":"Classification of heart sound signals using multi-modal features","volume":"58","author":"Randhawa","year":"2023","journal-title":"Procedia Comput. Sci."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1007\/s13534-021-00192-x","article-title":"Hidden Markov model-based heartbeat detector using electrocardiogram and arterial pressure signals","volume":"11","author":"Altuve","year":"2021","journal-title":"Biomed. Eng. Lett."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Shukla, S., Singh, S.K., and Mitra, D. (2020). An efficient heart sound segmenta tion approach using kurtosis and zero frequency filter features. Biomed. Signal Process. Control, 57.","DOI":"10.1016\/j.bspc.2019.101762"},{"key":"ref_22","unstructured":"Sound, M.H. (2024, March 01). Murmur Library. University of Michigan Heart Sound and Murmur Library, Available online: https:\/\/open.umich.edu\/find\/open-educational-resources\/medical\/heart-sound-murmur-library."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Qian, K., Bao, Z., Zhao, Z., Koike, T., Dong, F., Schmitt, M., Dong, Q., Shen, J., Jiang, W., and Jiang, Y. (2024). Learning Representations from Heart Sound: A Comparative Study on Shallow and Deep Models. Cyborg Bionic Syst. AAAS, 5.","DOI":"10.34133\/cbsystems.0075"},{"key":"ref_24","unstructured":"Dissanayake, T., Fernando, T., Denman, S., Sridharan, S., Ghaemmaghami, H., and Fookes, C. (2020). Understanding the importance of heart sound segmentation for heart anomaly detection. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Chen, W., Zhou, Z., Bao, J., Wang, C., Chen, H., Xu, C., and Wu, H. (2023). Classifying heart-sound signals based on cnn trained on melspectrum and log-melspectrum features. Bioengineering, 10.","DOI":"10.3390\/bioengineering10060645"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"2181","DOI":"10.1088\/0967-3334\/37\/12\/2181","article-title":"An open access database for the evaluation of heart sound algorithms","volume":"37","author":"Liu","year":"2016","journal-title":"Physiol. Meas."},{"key":"ref_27","first-page":"e215","article-title":"Physionet: Components of a new research resource for complex physiologic signals","volume":"101","author":"PhysioBank","year":"2000","journal-title":"Circulation"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1149","DOI":"10.1007\/s11760-018-1261-5","article-title":"Phonocardiogram signals processing approach for PASCAL classifying heart sounds challenge","volume":"12","author":"Chakir","year":"2018","journal-title":"Signal Image Video Process."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Wazed, E., Lee, J., Shin, C., and Jeong, H. (2024, January 3\u20136). CHSD-Net: Children Heart Sound Abnormality Detection Network. Proceedings of the 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Lisbon, Portugal.","DOI":"10.1109\/BIBM62325.2024.10821804"}],"container-title":["Children"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2227-9067\/12\/9\/1221\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:44:32Z","timestamp":1760035472000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2227-9067\/12\/9\/1221"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,12]]},"references-count":29,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["children12091221"],"URL":"https:\/\/doi.org\/10.3390\/children12091221","relation":{},"ISSN":["2227-9067"],"issn-type":[{"type":"electronic","value":"2227-9067"}],"subject":[],"published":{"date-parts":[[2025,9,12]]}}}