A comprehensive survey on heart sound analysis in the deep learning era

This repository is a collection of academic articles, publiched methodologies, and datasets during 2017–2022, on the topic of heart sound analysis.

Content

• Surveys
• Taxonomy
• Datasets
• Publicly-available codes

🔖 News!!!

📌 We are actively tracking the latest research and welcome contributions to our repository and survey paper. If your studies are relevant, please feel free to create an issue or a pull request.

📰 2024-05-05: Our paper A comprehensive survey on heart sound analysis in the deep learning era was accepted by IEEE Computational Intelligence Magazine (IF 2024: 9) in 2024.

🔍 Citation

If you find this work helpful in your research, welcome to cite the paper and give a ⭐.

Please read and cite our paper:

Ren, Z., Chang, Y., Nguyen, T. T., Tan, Y., Qian, K., & Schuller, B. W. (2023). A comprehensive survey on heart sound analysis in the deep learning era. IEEE Computational Intelligence Magazine, accepted, to appear.

@article{ren2023comprehensive,
  title={A comprehensive survey on heart sound analysis in the deep learning era},
  author={Ren, Zhao and Chang, Yi and Nguyen, Thanh Tam and Tan, Yang and Qian, Kun and Schuller, Bj{\"o}rn W},
  journal={IEEE Computational Intelligence Magazine},
  year={2024}
  note={accepted, to appear}
}

OR

Ren, Z., Chang, Y., Nguyen, T. T., Tan, Y., Qian, K., & Schuller, B. W. (2023). A comprehensive survey on heart sound analysis in the deep learning era. arXiv preprint arXiv:2301.09362.

@article{ren2023comprehensive,
  title={A comprehensive survey on heart sound analysis in the deep learning era},
  author={Ren, Zhao and Chang, Yi and Nguyen, Thanh Tam and Tan, Yang and Qian, Kun and Schuller, Bj{\"o}rn W},
  journal={arXiv preprint arXiv:2301.09362},
  year={2023}
}

Newest Works on Heart Sound Anaylsis

• Exploring Pre-trained General-purpose Audio Representations for Heart Murmur Detection

Existing Surveys

Paper Title	Venue	Year
Multidimensional analytical study of heart sounds: A review	International Journal Bioautomation	2015
Phonocardiogram signal analysis-practices, trends and challenges: A critical review	IEMCON	2015
A review of intelligent systems for heart sound signal analysis	Journal of Medical Engineering & Technology	2017
Recent advances in heart sound analysis	Physiological Measurement	2017
Heart sound data acquisition and preprocessing techniques: A review	IGI Global	2020
Application of soft computing techniques to heart sound classification: A review of the decade	Soft Computing Applications and Techniques in Healthcare	2020
Algorithms for automatic analysis and classification of heart sounds – A systematic review	IEEE Access	2018

Taxonomy

Datasets

Dataset	Challenge	Task
PASCAL Database	PASCAL Challenge	Dataset A: Normal, Murmur, Extra Heart Sound, Artifact; Dataset B: Normal, Murmur, Extrasystole
PhysioNet/CinC Database	PhysioNet/CinC Challenge 2016	Normal, Abnormal, Too noisy or ambiguous
HSS	ComParE Challenge 2018	Normal, Mild, Moderate/Severe
Data on GitHub	--	Normal, AS, MR, MS, MVP
Michigan Heart Sound Database, link 1 and 2	--	Normal, Pathological
CirCor DigiScope Database	George B. Moody PhysioNet Challenge 2022	Normal, abnormal; presence, absence, or unclear cases of murmurs

Publicly-available codes

Paper Title	Code Link	Program Language	Model
Classification of heart sound signal using multiple features	https://github.com/yaseen21khan/Classification-of-Heart-Sound-Signal-Using-Multiple-Features-	Matlab	DNN
Towards domain invariant heart sound abnormality detection using learnable filterbanks	https://github.com/mhealthbuet/heartnet	Python	CNN
A robust interpretable deep learning classifier for heart anomaly detection without segmentation	https://github.com/mHealthBuet/CepsNET	Python	ResNet
Algorithm for predicting valvular heart disease from heart sounds in an unselected cohort	https://github.com/uit-hdl/heart-sound-classification	Matlab	--

---

Disclaimer

Feel free to contact us if you have any queries or exciting news on this topic. In addition, we welcome all researchers to contribute to this repository and further contribute to the knowledge of the field.

If you have some other related references, please feel free to create a Github issue with the paper information. We will glady update the repos according to your suggestions. (You can also create pull requests, but it might take some time for us to do the merge)