PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
March 26, 2026Keisan Rikigaku Koenkai koen ronbunshu/Keisan Rikigaku Kouenkai kouen rombunshuu0 citationsOpen Access

Basic Studies on Development of an Automatic Heart Sound Diagnosis System

View Full Paper
THTakuma HosakaHHHirotoshi Hishida

Key Points

  • The aim is to develop an automatic heart sound diagnosis system to aid in early diagnosis and training.
  • Applied fast Fourier transform to heart sound data from the CirCor DigiScope dataset.
  • Generated color map images of heart sounds for analysis.
  • Utilized a convolutional neural network for classification of normal versus abnormal heart sounds.
  • Involved 962 cases (511 normal and 451 abnormal) of heart sounds.
  • Processed each heart sound as approximately 10 seconds of audio.
  • Achieved an overall classification accuracy of 69%.
  • Reached 76% accuracy for normal heart sounds.
  • Attained only 53% accuracy for abnormal heart sounds.
  • Indicated potential for significant improvement in detecting abnormalities.

Abstract

Heart disease is one of the leading causes of death in Japan, and the importance of early diagnosis through noninvasive auscultation is increasing, especially in rural areas. However, diagnosing heart sounds requires a high level of expertise, and physician shortages and aging populations are major challenges. Therefore, this study aims to develop an “automatic heart sound diagnosis system” that would complement doctors' diagnoses and could be applied to the training of young doctors and home care. Specifically, the authors apply a fast Fourier transform to heart sound data using the CirCor DigiScope dataset and generate color map images. This image is input into a CNN (Convolutional Neural Network), and a two-class classification is performed to distinguish between normal and abnormal images. 962 cases (511 normal and 451 abnormal) are used for learning, and each heart sound is processed as approximately 10 seconds of audio. As a result, the overall classification accuracy is 69 %, with 76 % for normal heart sounds and 53% for abnormal heart sounds, suggesting room for improvement, particularly in the detection of abnormalities.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Hosaka et al. (2025) studied this question.

synapsesocial.com/papers/69c4ccc9fdc3bde448918587https://doi.org/10.1299/jsmecmd.2025.38.os22-11
Ask AI
Helpful
Bookmark
Share
View Full Paper