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.
Abstract:
Previous studies have indicated heart sounds may contain information useful in the detection of occluded coronary arteries. During diastole, coronary blood flow is maximum, and the sounds associated with turbulent blood flow through partially occluded coronary arteries should be detectable. In order to detect such sounds, recordings of diastolic heart sound segments were analyzed by using four signal processing techniques; the Fast Fourier Transform (FFT), the Autoregressive (AR), the Autoregressive Moving Average (ARMA), and the Minimum-Norm (Eigen-vector) methods. To further enhance the diastolic heart sounds and reduce background noise, an Adaptive filter was used as a preprocessor. The power ratios of the FFT method and the poles of the AR, ARMA, and Eigen-vector methods were used to diagnose patients as diseased or normal arteries using a blind protocol without prior knowledge of the actual disease states of the patients to guard against human bias. Results showed that normal and abnormal records were correctly distinguished in 56 of 80 cases using the Fast Fourier Transform (FFT), in 63 of 80 cases using the AR, in 62 of 80 cases using the ARMA method, and in 67 of 80 cases using the Eigenvector method. Among all four methods, the Eigenvector methods showed the best diagnostic performance when compared with the FFT, AR, and ARMA methods. These results confirm that high frequency acoustic energy between 300 and 800 Hz is associated with coronary stenosis.