Secure and Decentralized Heart Sound Analysis Using Federated Learning and Blockchain Technology
Research Article  ·  Published: 16 November 2025
Issue cover
ICCK Transactions on Machine Intelligence
Volume 2, Issue 1, 2026: 1-11
Research Article Free to Read

Secure and Decentralized Heart Sound Analysis Using Federated Learning and Blockchain Technology

1 Ajay Kumar Garg Engineering College, Ghaziabad, Uttar Pradesh, India
2 Odisha University of Technology and Research, Bhubaneswar, Odisha, India
3 Amity School of Engineering & Technology, Amity University Punjab, Mohali, Punjab, India
4 University of Petroleum and Energy Studies, Dehradun, Uttarakhand, India
5 VIT Bhopal University, Kothrikalan, Sehore, Madhya Pradesh, India
* Corresponding Author: Vishan Kumar Gupta, [email protected]
Volume 2, Issue 1
You have access to this article · Limited-Time Free Access

Article Information

Abstract

Early diagnosis of cardiac abnormalities depends on accurate classification of heart sounds, but centralized training methods run the danger of violating patient privacy. We thus propose a privacy-preserving and reliable heart sound abnormality detection system combining Blockchain Technology with Federated Learning (FL). Training is spread among seven clients, each simulating an independent data source, using a preprocessed dataset from the PhysioNet Challenge 2016 to enable distributed learning without sharing raw data. CNN-LSTM model using FedAvg achieved the best performance: 94% accuracy, 0.91 precision, 0.95 recall, and an AUC of 0.98 among five deep learning architectures evaluated with FedAvg and FedProx strategies. Along with metadata including client ID and round number, SHA-256 hashes of local and global model weights were recorded on a local Ethereum blockchain following every communication round to guarantee model integrity. The hash of the final model is revalidated against the blockchain to confirm authenticity prior to deployment. It then guarantees safe, distributed, clinically valuable AI-based diagnostics by real-time classification of heart sounds as normal or abnormal.

Graphical Abstract

Secure and Decentralized Heart Sound Analysis Using Federated Learning and Blockchain Technology

Keywords

federated learning blockchain-based model validation heart sound classification privacy-preserving artificial intelligence CNN-LSTM architecture SHA-256 model integrity decentralized healthcare diagnostics

Data Availability Statement

Data will be made available on request.

Funding

This work was supported without any funding.

Conflicts of Interest

The authors declare no conflicts of interest.

Ethical Approval and Consent to Participate

Not applicable.

References

  1. Qiu, W., Qian, K., Wang, Z., Chang, Y., Bao, Z., Hu, B., ... & Yamamoto, Y. (2022, July). A federated learning paradigm for heart sound classification. In 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (pp. 1045-1048). IEEE.
    [CrossRef] [Google Scholar]
  2. Bashir, A. K., Victor, N., Bhattacharya, S., Huynh-The, T., Chengoden, R., Yenduri, G., ... & Liyanage, M. (2023). Federated learning for the healthcare metaverse: Concepts, applications, challenges, and future directions. IEEE Internet of Things Journal, 10(24), 21873-21891.
    [CrossRef] [Google Scholar]
  3. Alasmari, S., AlGhamdi, R., Tejani, G. G., Sharma, S. K., & Mousavirad, S. J. (2025). Federated learning-based multimodal approach for early detection and personalized care in cardiac disease. Frontiers in Physiology, 16, 1563185.
    [CrossRef] [Google Scholar]
  4. Khan, R., Taj, S., Ma, X., Noor, A., Zhu, H., Khan, J., ... & Khan, S. U. (2024). Advanced federated ensemble internet of learning approach for cloud based medical healthcare monitoring system. Scientific Reports, 14(1), 26068.
    [CrossRef] [Google Scholar]
  5. Gupta, M., Kumar, M., & Gupta, Y. (2024). A blockchain-empowered federated learning-based framework for data privacy in lung disease detection system. Computers in Human Behavior, 158, 108302.
    [CrossRef] [Google Scholar]
  6. Chen, D., Xuan, W., Gu, Y., Liu, F., Chen, J., Xia, S., ... & Luo, J. (2022). Automatic classification of normal–abnormal heart sounds using convolution neural network and long-short term memory. Electronics, 11(8), 1246.
    [CrossRef] [Google Scholar]
  7. Myrzashova, R., Alsamhi, S. H., Shvetsov, A. V., Hawbani, A., & Wei, X. (2023). Blockchain meets federated learning in healthcare: A systematic review with challenges and opportunities. IEEE Internet of Things Journal, 10(16), 14418-14437.
    [CrossRef] [Google Scholar]
  8. Alsamhi, S. H., Myrzashova, R., Hawbani, A., Kumar, S., Srivastava, S., Zhao, L., ... & Curry, E. (2024). Federated learning meets blockchain in decentralized data sharing: Healthcare use case. IEEE Internet of Things Journal, 11(11), 19602-19615.
    [CrossRef] [Google Scholar]
  9. Sun, L., Wu, J., Xu, Y., & Zhang, Y. (2023). A federated learning and blockchain framework for physiological signal classification based on continual learning. Information Sciences, 630, 586-598.
    [CrossRef] [Google Scholar]
  10. Tatulli, E., Souriau, R., & Fontecave-Jallon, J. (2025). Unsupervised segmentation of heart sounds from abrupt changes detection. Computers in Biology and Medicine, 186, Article 109712.
    [CrossRef] [Google Scholar]
  11. Jimenez Gutierrez, D. M., Hassan, H. M., Landi, L., Vitaletti, A., & Chatzigiannakis, I. (2023). Application of federated learning techniques for arrhythmia classification using 12-lead ECG signals. In International Symposium on Algorithmic Aspects of Cloud Computing (pp. 38–65). Springer Nature Switzerland.
    [CrossRef] [Google Scholar]
  12. Zeng, P., Kang, S., Fan, F., & Liu, J. (2025). Enhanced heart sound anomaly detection via WCOS: a semi-supervised framework integrating wavelet, autoencoder and SVM. Frontiers in Neuroinformatics, 19, 1530047.
    [CrossRef] [Google Scholar]
  13. Qiu, W., Quan, C., Zhu, L., Yu, Y., Wang, Z., Ma, Y., ... & Schuller, B. W. (2024). Heart sound abnormality detection from multi-institutional collaboration: Introducing a federated learning framework. IEEE Transactions on Biomedical Engineering, 71(10), 2802-2813.
    [CrossRef] [Google Scholar]
  14. Karan, B., & Padhi, T. (2024). Hilbert domain characterizations of wavelet packets for automated heart sound abnormality detection. Biomedical Signal Processing and Control, 90, Article 105793.
    [CrossRef] [Google Scholar]
  15. Nia, P. S., & Hesar, H. D. (2024). Abnormal heart sound detection using time-frequency analysis and machine learning techniques. Biomedical Signal Processing and Control, 90, 105899.
    [CrossRef] [Google Scholar]
  16. Abbas, S., Ojo, S., Al Hejaili, A., Sampedro, G. A., Almadhor, A., Zaidi, M. M., & Kryvinska, N. (2024). Artificial intelligence framework for heart disease classification from audio signals. Scientific reports, 14(1), 3123.
    [CrossRef] [Google Scholar]
  17. Rückel, T., Sedlmeir, J., & Hofmann, P. (2022). Fairness, integrity, and privacy in a scalable blockchain-based federated learning system. Computer Networks, 202, 108621.
    [CrossRef] [Google Scholar]
  18. Fallah, A., Mokhtari, A., & Ozdaglar, A. (2020). Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach. Advances in neural information processing systems, 33, 3557-3568.
    [Google Scholar]
  19. Hu, F., Qiu, S., Yang, X., Wu, C., Nunes, M. B., & Chen, H. (2024). Privacy-Preserving Healthcare and Medical Data Collaboration Service System Based on Blockchain and Federated Learning. Comput. Mater. Continua, 80(2), 2897-2915. http://doi.org/10.32604/cmc.2024.052570
    [Google Scholar]
  20. Dhade, P., & Shirke, P. (2024). Federated learning for healthcare: a comprehensive review. Engineering Proceedings, 59(1), 230.
    [CrossRef] [Google Scholar]
  21. Sun, Z., Wan, J., Yin, L., Cao, Z., Luo, T., & Wang, B. (2022). A blockchain-based audit approach for encrypted data in federated learning. Digital Communications and Networks, 8(5), 614-624.
    [CrossRef] [Google Scholar]
  22. Khan, S., Khan, M., Khan, M. A., Wang, L., & Wu, K. (2025). Advancing medical innovation through blockchain-secured federated learning for smart health. IEEE Journal of Biomedical and Health Informatics, 29(9), 6482-6495.
    [CrossRef] [Google Scholar]

Cited By (5)

  1. Gaurav Dhiman, Kiran Deep Singh, Prabh Deep Singh, Norah Saleh Alghamdi, Ghadah Shukri Albakri. A novel approach to reliable and flexible distributed computing with virtualization in smart healthcare applications. Scientific Reports, 2026 , 16 (1).
    [CrossRef]
  2. Kushank, Surendra Kumar Shukla, Vishan Kumar Gupta, Subodh Mishra, Vikas Tyagi. . 2026 Fourth International Conference on Secure Cyber Computing and Communications (ICSCCC), 2026 .
    [CrossRef]
  3. İlknur Dönmez, Faruk Bulut. Multidimensional diversity in video recommender systems: a holistic framework of literature gaps and future directions. Intelligent Systems with Applications, 2026 , 31 .
    [CrossRef]
  4. Shubhani Aggarwal, Arzoo Miglani, Norah Saleh Alghamdi, Gaurav Dhiman. Resilient and decentralized demand-side management in smart grids using blockchain. Scientific Reports, 2026 , 16 (1).
    [CrossRef]
  5. Meenakshi Garg, Nor Asilah Wati Abdul Hamid, Dafik, Sunder R.. AI-driven feature descriptor design using CNNs and transfer learning for enhanced image retrieval accuracy and efficiency. Scientific Reports, 2026 , 16 (1).
    [CrossRef]
* Citation data provided by Crossref Cited-by.

Cite This Article

APA Style
Agarwal, S., Kandpal, M., Gupta, V. K., Aggarwal, S., & Jain, P. (2025). Secure and Decentralized Heart Sound Analysis Using Federated Learning and Blockchain Technology. ICCK Transactions on Machine Intelligence, 2(1), 1-11. https://doi.org/10.62762/TMI.2025.567350
Export Citation
RIS Format
Compatible with EndNote, Zotero, Mendeley, and other reference managers
TY  - JOUR
AU  - Agarwal, Shivani
AU  - Kandpal, Meenakshi
AU  - Gupta, Vishan Kumar
AU  - Aggarwal, Shubhani
AU  - Jain, Paras
PY  - 2025
DA  - 2025/11/16
TI  - Secure and Decentralized Heart Sound Analysis Using Federated Learning and Blockchain Technology
JO  - ICCK Transactions on Machine Intelligence
T2  - ICCK Transactions on Machine Intelligence
JF  - ICCK Transactions on Machine Intelligence
VL  - 2
IS  - 1
SP  - 1
EP  - 11
DO  - 10.62762/TMI.2025.567350
UR  - https://www.icck.org/article/abs/tmi.2025.567350
KW  - federated learning
KW  - blockchain-based model validation
KW  - heart sound classification
KW  - privacy-preserving artificial intelligence
KW  - CNN-LSTM architecture
KW  - SHA-256 model integrity
KW  - decentralized healthcare diagnostics
AB  - Early diagnosis of cardiac abnormalities depends on accurate classification of heart sounds, but centralized training methods run the danger of violating patient privacy. We thus propose a privacy-preserving and reliable heart sound abnormality detection system combining Blockchain Technology with Federated Learning (FL). Training is spread among seven clients, each simulating an independent data source, using a preprocessed dataset from the PhysioNet Challenge 2016 to enable distributed learning without sharing raw data. CNN-LSTM model using FedAvg achieved the best performance: 94% accuracy, 0.91 precision, 0.95 recall, and an AUC of 0.98 among five deep learning architectures evaluated with FedAvg and FedProx strategies. Along with metadata including client ID and round number, SHA-256 hashes of local and global model weights were recorded on a local Ethereum blockchain following every communication round to guarantee model integrity. The hash of the final model is revalidated against the blockchain to confirm authenticity prior to deployment. It then guarantees safe, distributed, clinically valuable AI-based diagnostics by real-time classification of heart sounds as normal or abnormal.
SN  - 3068-7403
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 
BibTeX Format
Compatible with LaTeX, BibTeX, and other reference managers
@article{Agarwal2025Secure,
  author = {Shivani Agarwal and Meenakshi Kandpal and Vishan Kumar Gupta and Shubhani Aggarwal and Paras Jain},
  title = {Secure and Decentralized Heart Sound Analysis Using Federated Learning and Blockchain Technology},
  journal = {ICCK Transactions on Machine Intelligence},
  year = {2025},
  volume = {2},
  number = {1},
  pages = {1-11},
  doi = {10.62762/TMI.2025.567350},
  url = {https://www.icck.org/article/abs/tmi.2025.567350},
  abstract = {Early diagnosis of cardiac abnormalities depends on accurate classification of heart sounds, but centralized training methods run the danger of violating patient privacy. We thus propose a privacy-preserving and reliable heart sound abnormality detection system combining Blockchain Technology with Federated Learning (FL). Training is spread among seven clients, each simulating an independent data source, using a preprocessed dataset from the PhysioNet Challenge 2016 to enable distributed learning without sharing raw data. CNN-LSTM model using FedAvg achieved the best performance: 94\% accuracy, 0.91 precision, 0.95 recall, and an AUC of 0.98 among five deep learning architectures evaluated with FedAvg and FedProx strategies. Along with metadata including client ID and round number, SHA-256 hashes of local and global model weights were recorded on a local Ethereum blockchain following every communication round to guarantee model integrity. The hash of the final model is revalidated against the blockchain to confirm authenticity prior to deployment. It then guarantees safe, distributed, clinically valuable AI-based diagnostics by real-time classification of heart sounds as normal or abnormal.},
  keywords = {federated learning, blockchain-based model validation, heart sound classification, privacy-preserving artificial intelligence, CNN-LSTM architecture, SHA-256 model integrity, decentralized healthcare diagnostics},
  issn = {3068-7403},
  publisher = {Institute of Central Computation and Knowledge}
}

Article Metrics

Citations
Views
1740
PDF Downloads
506

Publisher's Note

ICCK stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and Permissions

Institute of Central Computation and Knowledge (ICCK) or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
ICCK Transactions on Machine Intelligence
ICCK Transactions on Machine Intelligence
ISSN: 3068-7403 (Online)
Portico
Preserved at
Portico