{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T08:16:43Z","timestamp":1758615403712,"version":"3.44.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T00:00:00Z","timestamp":1758585600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T00:00:00Z","timestamp":1758585600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100007102","name":"Zagazig University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100007102","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Big Data"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Machine learning techniques in healthcare applications have seen rapid growth. However, the use of sensitive health data raises significant privacy concerns. In this paper, we present the application of various deep learning models (CNN, LSTM, GRU, and RNN) to classify heartbeat abnormalities while preserving privacy through differential privacy. We achieve this by adding Gaussian noise to the gradients during stochastic gradient descent training, ensuring that individual patient data cannot be identified or traced from the model\u2019s results. We trained and evaluated these models on the multimodal MIT-BIH polysomnographic dataset. The data was preprocessed using noise reduction filters, heartbeat segmentation through frequency-based sampling, and resampling. Our results show that, even with differential privacy constraints, the GRU model achieved the highest accuracy of 99.5%, followed by CNN (99.12%), LSTM (98.89%), and RNN (79.60%). These findings provide practical guidance for selecting effective and privacy-preserving deep learning models for heartbeat abnormality detection in real-world healthcare scenarios.<\/jats:p>","DOI":"10.1186\/s40537-025-01292-6","type":"journal-article","created":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T07:09:16Z","timestamp":1758611356000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring differential privacy in CNNs, LSTMs, GRUs, and RNNs for heartbeat detection from multimodal data"],"prefix":"10.1186","volume":"12","author":[{"given":"Osama M.","family":"ElKomy","sequence":"first","affiliation":[]},{"given":"Ehab","family":"Rushdy","sequence":"additional","affiliation":[]},{"given":"Sohaila","family":"Nasser","sequence":"additional","affiliation":[]},{"given":"Marwa M.","family":"Khashaba","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,23]]},"reference":[{"key":"1292_CR1","unstructured":"Organization WH. Cardiovascular diseases (CVDs). Accessed: 2024-11-20 2021. https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/cardiovascular-diseases-(cvds)"},{"issue":"25","key":"1292_CR2","doi-asserted-by":"publisher","first-page":"2982","DOI":"10.1016\/j.jacc.2020.11.010","volume":"76","author":"GA Roth","year":"2020","unstructured":"Roth GA, Mensah GA, Johnson CO, Addolorato G, Ammirati E, Baddour LM, et al. Global burden of cardiovascular diseases and risk factors, 1990\u20132019: update from the gbd 2019 study. J Am Coll Cardiol. 2020;76(25):2982\u20133021.","journal-title":"J Am Coll Cardiol"},{"key":"1292_CR3","doi-asserted-by":"crossref","unstructured":"Coronado F, Melvin SC, Bell RA, Zhao G. Peer reviewed: global responses to prevent, manage, and control cardiovascular diseases. Preventing chronic disease 2022;19.","DOI":"10.5888\/pcd19.220347"},{"issue":"3","key":"1292_CR4","doi-asserted-by":"publisher","first-page":"221","DOI":"10.4236\/ojepi.2022.123018","volume":"12","author":"S Al-Gahtani","year":"2022","unstructured":"Al-Gahtani S, Abozaid T, Al-Gahtani S, Shoukri MM, Aleid M. Investigating trend in cardiovascular disease mortality and its association with obesity in the gulf cooperative council (gcc) countries from 1990 to 2019. Open J Epidemiol. 2022;12(3):221\u201330.","journal-title":"Open J Epidemiol"},{"key":"1292_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.102628","volume":"68","author":"J Chromik","year":"2021","unstructured":"Chromik J, Pirl L, Beilharz J, Arnrich B, Polze A. Certainty in qrs detection with artificial neural networks. Biomed Signal Process Control. 2021;68:102628.","journal-title":"Biomed Signal Process Control"},{"key":"1292_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2025.107658","volume":"105","author":"S Hu","year":"2025","unstructured":"Hu S, Fang W, Bao H, Zhang T. Non-contact detection of mental fatigue from facial expressions and heart signals: a self-supervised-based multimodal fusion method. Biomed Signal Process Control. 2025;105:107658.","journal-title":"Biomed Signal Process Control"},{"key":"1292_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12938-016-0122-0","volume":"15","author":"T Jeon","year":"2016","unstructured":"Jeon T, Yu J, Pedrycz W, Jeon M, Lee B, Lee B. Robust detection of heartbeats using association models from blood pressure and eeg signals. Biomed Eng Online. 2016;15:1\u201314.","journal-title":"Biomed Eng Online"},{"issue":"1","key":"1292_CR8","first-page":"1094830","volume":"2022","author":"M Badr","year":"2022","unstructured":"Badr M, Al-Otaibi S, Alturki N, Abir T. [retracted] detection of heart arrhythmia on electrocardiogram using artificial neural networks. Comput Intell Neurosci. 2022;2022(1):1094830.","journal-title":"Comput Intell Neurosci"},{"issue":"4","key":"1292_CR9","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1016\/S0013-4694(96)96506-2","volume":"102","author":"G Dirlich","year":"1997","unstructured":"Dirlich G, Vogl L, Plaschke M, Strian F. Cardiac field effects on the eeg. Electroencephalogr Clin Neurophysiol. 1997;102(4):307\u201315.","journal-title":"Electroencephalogr Clin Neurophysiol"},{"issue":"2","key":"1292_CR10","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1161\/HYPERTENSIONAHA.119.14240","volume":"75","author":"FD Fuchs","year":"2020","unstructured":"Fuchs FD, Whelton PK. High blood pressure and cardiovascular disease. Hypertension. 2020;75(2):285\u201392.","journal-title":"Hypertension"},{"issue":"9932","key":"1292_CR11","doi-asserted-by":"publisher","first-page":"1899","DOI":"10.1016\/S0140-6736(14)60685-1","volume":"383","author":"E Rapsomaniki","year":"2014","unstructured":"Rapsomaniki E, Timmis A, George J, Pujades-Rodriguez M, Shah AD, Denaxas S, et al. Blood pressure and incidence of twelve cardiovascular diseases: lifetime risks, healthy life-years lost, and age-specific associations in 1\u00b7 25 million people. Lancet. 2014;383(9932):1899\u2013911.","journal-title":"Lancet"},{"key":"1292_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3389\/fdgth.2023.1264780","volume":"5","author":"PJ Fitzpatrick","year":"2023","unstructured":"Fitzpatrick PJ. Improving health literacy using the power of digital communications to achieve better health outcomes for patients and practitioners. Frontiers in Digital Health. 2023;5:1\u201313.","journal-title":"Frontiers in Digital Health"},{"issue":"1","key":"1292_CR13","first-page":"1","volume":"58","author":"H Javed","year":"2025","unstructured":"Javed H, El-Sappagh S, Abuhmed T. Robustness in deep learning models for medical diagnostics: security and adversarial challenges towards robust ai applications. Artif Intell Rev. 2025;58(1):1\u2013107.","journal-title":"Artif Intell Rev"},{"issue":"7","key":"1292_CR14","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1007\/s10462-024-10766-7","volume":"57","author":"S Saha","year":"2024","unstructured":"Saha S, Hota A, Chattopadhyay AK, Nag A, Nandi S. A multifaceted survey on privacy preservation of federated learning: progress, challenges, and opportunities. Artif Intell Rev. 2024;57(7):184.","journal-title":"Artif Intell Rev"},{"key":"1292_CR15","unstructured":"Jothiaruna N et al. A deep learning framework for automatic cardiovascular classification from electrocardiogram images. Res Square, 2023;1\u201315."},{"issue":"1","key":"1292_CR16","doi-asserted-by":"publisher","first-page":"8804","DOI":"10.1038\/s41598-024-59311-0","volume":"14","author":"F Zhou","year":"2024","unstructured":"Zhou F, Fang D. Multimodal ecg heartbeat classification method based on a convolutional neural network embedded with fca. Sci Rep. 2024;14(1):8804.","journal-title":"Sci Rep"},{"issue":"1","key":"1292_CR17","doi-asserted-by":"publisher","first-page":"13524","DOI":"10.1038\/s41598-021-93030-0","volume":"11","author":"A Ziller","year":"2021","unstructured":"Ziller A, Usynin D, Braren R, Makowski M, Rueckert D, Kaissis G. Medical imaging deep learning with differential privacy. Sci Rep. 2021;11(1):13524.","journal-title":"Sci Rep"},{"issue":"2","key":"1292_CR18","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1007\/s40745-023-00475-3","volume":"11","author":"W Liu","year":"2024","unstructured":"Liu W, Zhang Y, Yang H, Meng Q. A survey on differential privacy for medical data analysis. Ann Data Sci. 2024;11(2):733\u201347.","journal-title":"Ann Data Sci"},{"key":"1292_CR19","doi-asserted-by":"crossref","unstructured":"Narayana VL, Patibandla RL, Rao BT, Gopi AP. Use of Machine Learning in Healthcare, pp. 275\u2013293. Wiley, Hoboken, NJ 2022.","DOI":"10.1002\/9781119769293.ch13"},{"key":"1292_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104457","volume":"134","author":"V Jahmunah","year":"2021","unstructured":"Jahmunah V, Ng EYK, San TR, Acharya UR. Automated detection of coronary artery disease, myocardial infarction and congestive heart failure using gaborcnn model with ecg signals. Comput Biol Med. 2021;134:104457.","journal-title":"Comput Biol Med"},{"key":"1292_CR21","unstructured":"Arepalli PG, Maneesha K, Srija M, SadifBanu TS, Likhitha T, Tumati R. Parkinson\u2019s Disease Detection Using Q-LSTM. In: 2024 International Conference on IoT Based Control Networks and Intelligent Systems (ICICNIS) 2024."},{"key":"1292_CR22","unstructured":"MH F, SERTBA\u015e A. A differentially private federated learning application in privacy-preserving medical imaging. Res Square 2024."},{"issue":"1","key":"1292_CR23","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1038\/s43856-024-00462-6","volume":"4","author":"S Tayebi Arasteh","year":"2024","unstructured":"Tayebi Arasteh S, Ziller A, Kuhl C, Makowski M, Nebelung S, Braren R, et al. Preserving fairness and diagnostic accuracy in private large-scale ai models for medical imaging. Commun Med. 2024;4(1):46.","journal-title":"Commun Med"},{"key":"1292_CR24","doi-asserted-by":"publisher","first-page":"1297","DOI":"10.22214\/ijraset.2023.49632","volume":"11","author":"A Rajput","year":"2023","unstructured":"Rajput A, Tiwari S. Differential privacy preserving using tensorflow dp-sgd and 2d-cnn for large-scale image data. Int J Res Appl Sci Eng Technol. 2023;11:1297\u2013303.","journal-title":"Int J Res Appl Sci Eng Technol"},{"key":"1292_CR25","unstructured":"Fares MH, Saad AMSE. Towards privacy-preserving medical imaging: Federated learning with differential privacy and secure aggregation using a modified resnet architecture. arXiv preprint arXiv:2412.00687 2024."},{"key":"1292_CR26","doi-asserted-by":"crossref","unstructured":"Pan L, Huang M, Wang L, Qin P, Peng S. Feddp: Privacy-preserving method based on federated learning for histopathology image segmentation. arXiv preprint arXiv:2411.04509 2024.","DOI":"10.1109\/BIBM62325.2024.10822021"},{"key":"1292_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.health.2024.100329","volume":"5","author":"TN Islam","year":"2024","unstructured":"Islam TN, Imtiaz H. A robust neural network for privacy-preserving heart rate estimation in remote healthcare systems. Healthcare Anal. 2024;5:100329.","journal-title":"Healthcare Anal"},{"key":"1292_CR28","first-page":"2024","volume":"03","author":"G Moody","year":"1999","unstructured":"Moody G. The MIT-BIH Polysomnographic Database Accessed Dec. 1999;03:2024.","journal-title":"The MIT-BIH Polysomnographic Database Accessed Dec"},{"issue":"3","key":"1292_CR29","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1109\/51.932724","volume":"20","author":"GB Moody","year":"2001","unstructured":"Moody GB, Mark RG. The impact of the mit-bih arrhythmia database. IEEE Eng Med Biol Mag. 2001;20(3):45\u201350.","journal-title":"IEEE Eng Med Biol Mag"},{"issue":"2","key":"1292_CR30","doi-asserted-by":"publisher","first-page":"21","DOI":"10.3390\/computation12020021","volume":"12","author":"S Alinsaif","year":"2024","unstructured":"Alinsaif S. Unraveling arrhythmias with graph-based analysis: a survey of the mit-bih database. Computation. 2024;12(2):21.","journal-title":"Computation"},{"key":"1292_CR31","doi-asserted-by":"crossref","unstructured":"George\u00a0Moody IS. Benjamin\u00a0Moody: PhysioNet 2014 Challenge Database. Accessed: Dec. 03, 2024 2014. https:\/\/physionet.org\/content\/challenge-2014\/1.0.0\/set-p\/#files-panel","DOI":"10.1007\/978-1-4614-7320-6_496-1"},{"issue":"1","key":"1292_CR32","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1111\/anec.12323","volume":"21","author":"AR P\u00e9rez-Riera","year":"2016","unstructured":"P\u00e9rez-Riera AR, Abreu LC, Barbosa-Barros R, Nikus KC, Baranchuk A. R-peak time: an electrocardiographic parameter with multiple clinical applications. Ann Noninvasive Electrocardiol. 2016;21(1):10\u20139.","journal-title":"Ann Noninvasive Electrocardiol"},{"key":"1292_CR33","doi-asserted-by":"publisher","first-page":"19638","DOI":"10.1038\/s41598-022-19495-9","volume":"12","author":"D Yun","year":"2022","unstructured":"Yun D, Lee HC, Jung CW. Robust r-peak detection in an electrocardiogram with stationary wavelet transformation and separable convolution. Sci Rep. 2022;12:19638.","journal-title":"Sci Rep"},{"key":"1292_CR34","doi-asserted-by":"crossref","unstructured":"Kachuee M, Fazeli S, Sarrafzadeh M. Ecg heartbeat classification: A deep transferable representation. In: 2018 IEEE International Conference on Healthcare Informatics (ICHI), 2018;443\u2013444. IEEE","DOI":"10.1109\/ICHI.2018.00092"},{"issue":"4","key":"1292_CR35","doi-asserted-by":"publisher","first-page":"707","DOI":"10.3390\/electronics14040707","volume":"14","author":"FR Navazo","year":"2025","unstructured":"Navazo FR, Sierra-Garcia JE, C\u00e1mara JM. Comparison of lstm- and gru-type rnn networks for attention and meditation prediction on raw eeg data from low-cost headsets. Electronics. 2025;14(4):707.","journal-title":"Electronics"},{"key":"1292_CR36","doi-asserted-by":"crossref","unstructured":"Abadi M, Chu A, Goodfellow I, McMahan HB, Mironov I, Talwar K, Zhang L. Deep learning with differential privacy. In: Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, 2016;308\u2013318.","DOI":"10.1145\/2976749.2978318"},{"key":"1292_CR37","doi-asserted-by":"crossref","unstructured":"Phanireddy S. Differential privacy-preserving algorithms for secure training of machine learning models. International Journal of Artificial Intelligence, Data Science, and Machine Learning(IJAIDSML) 2025;6(2)","DOI":"10.63282\/3050-9262.IJAIDSML-V6I2P110"},{"key":"1292_CR38","doi-asserted-by":"crossref","unstructured":"Dey R, Salem FM. Gate-variants of gated recurrent unit (gru) neural networks. In: 2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS) 2017.","DOI":"10.1109\/MWSCAS.2017.8053243"}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-025-01292-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40537-025-01292-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-025-01292-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T07:09:33Z","timestamp":1758611373000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-025-01292-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,23]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1292"],"URL":"https:\/\/doi.org\/10.1186\/s40537-025-01292-6","relation":{},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,23]]},"assertion":[{"value":"11 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"216"}}