Related Experiment Videos

Noninvasive acoustical detection of coronary artery disease: a comparative study of signal processing methods

Y M Akay1, M Akay, W Welkowitz

  • 1Biomedical Engineering Department, Rutgers University, Piscataway, NJ 08855.

Insights

Heart sound analysis using signal processing techniques can detect occluded coronary arteries. The Eigenvector method demonstrated the best diagnostic performance in identifying coronary stenosis from diastolic heart sounds.

Area of Science:

  • Biomedical Engineering
  • Cardiology
  • Signal Processing

Background:

  • Heart sounds may contain diagnostic information for occluded coronary arteries.
  • Turbulent blood flow during diastole, when coronary blood flow is maximal, can generate detectable sounds.

Purpose of the Study:

  • To analyze diastolic heart sound segments for detecting occluded coronary arteries.
  • To compare the diagnostic performance of four signal processing techniques.

Main Methods:

  • Diastolic heart sound recordings were analyzed using Fast Fourier Transform (FFT), Autoregressive (AR), Autoregressive Moving Average (ARMA), and Minimum-Norm (Eigen-vector) methods.
  • An adaptive filter was employed as a preprocessor to enhance heart sounds and reduce noise.
  • Diagnostic performance was assessed using a blind protocol, analyzing power ratios (FFT) and poles (AR, ARMA, Eigen-vector).

Main Results:

  • The Eigenvector method achieved the highest diagnostic accuracy, correctly distinguishing normal and abnormal arteries in 67 out of 80 cases.
  • FFT, AR, and ARMA methods showed diagnostic accuracies of 56/80, 63/80, and 62/80, respectively.
  • High-frequency acoustic energy between 300 and 800 Hz was confirmed to be associated with coronary stenosis.

Conclusions:

  • Signal processing of diastolic heart sounds, particularly using the Eigenvector method, shows promise for non-invasive detection of coronary artery disease.
  • The Eigenvector method offers superior diagnostic performance compared to FFT, AR, and ARMA techniques for this application.
  • Acoustic characteristics in the 300-800 Hz range are significant indicators of coronary stenosis.

Related Concept Videos