Heart Sound Abnormality Detection From Multi-Institutional Collaboration: Introducing a Federated Learning Framework

Wanyong Qiu, Chen Quan, Lixian Zhu, Yongzi Yu, Zhihua Wang, Yu Ma, Mengkai Sun, Yi Chang, Kun Qian, Bin Hu, Yoshiharu Yamamoto, Bjorn W. Schuller

Research output: Contribution to journalArticlepeer-review


<italic>Objective:</italic> Early diagnosis of cardiovascular diseases is a crucial task in medical practice. With the application of computer audition in the healthcare field, artificial intelligence (AI) has been applied to clinical non-invasive intelligent auscultation of heart sounds to provide rapid and effective pre-screening. However, AI models generally require large amounts of data which may cause privacy issues. Unfortunately, it is difficult to collect large amounts of healthcare data from a single centre. <italic>Methods:</italic> In this study, we propose federated learning (FL) optimisation strategies for the practical application in multi-centre institutional heart sound databases. The horizontal FL is mainly employed to tackle the privacy problem by aligning the feature spaces of FL participating institutions without information leakage. In addition, techniques based on deep learning have poor interpretability due to their &#x201C;black-box&#x201D; property, which limits the feasibility of AI in real medical data. To this end, vertical FL is utilised to address the issues of model interpretability and data scarcity. <italic>Conclusion:</italic> Experimental results demonstrate that, the proposed FL framework can achieve good performance for heart sound abnormality detection by taking the personal privacy protection into account. Moreover, using the federated feature space is beneficial to balance the interpretability of the vertical FL and the privacy of the data. <italic>Significance:</italic> This work realises the potential of FL from research to clinical practice, and is expected to have extensive application in the federated smart medical system.

Original languageEnglish
Pages (from-to)1-12
Number of pages12
JournalIEEE Transactions on Biomedical Engineering
StateAccepted/In press - 2024
Externally publishedYes


  • Artificial intelligence
  • Computer audition
  • Data models
  • Heart
  • Hospitals
  • Medical diagnostic imaging
  • Medical services
  • Privacy
  • federated learning
  • healthcare
  • heart sound
  • information security


Dive into the research topics of 'Heart Sound Abnormality Detection From Multi-Institutional Collaboration: Introducing a Federated Learning Framework'. Together they form a unique fingerprint.

Cite this