Related Experiment Videos
Application of the ARMA method to acoustic detection of coronary artery disease
M Akay1, W Welkowitz, J L Semmlow
1Biomedical Engineering Department, Rutgers University, NJ 08855.
Insights
Advanced signal processing of diastolic heart sounds using autoregressive moving average (ARMA) modeling can noninvasively detect coronary artery disease. This method accurately distinguished between normal and abnormal heart sounds, and pre- and post-angioplasty cases.
Area of Science:
- Biomedical Engineering
- Cardiovascular Research
- Signal Processing
Background:
- Noninvasive detection of coronary artery disease (CAD) remains a clinical challenge.
- Diastolic heart sounds offer potential insights into coronary blood flow dynamics.
- Turbulent blood flow in partially occluded coronary arteries may generate detectable acoustic signals during diastole.
Purpose of the Study:
- To apply advanced signal processing, specifically autoregressive moving average (ARMA) modeling, to diastolic heart sound data for noninvasive CAD detection.
- To differentiate between normal and abnormal cardiac states.
- To assess the effectiveness of ARMA modeling in distinguishing between pre- and post-angioplasty patient records.
Main Methods:
- Utilized autoregressive moving average (ARMA) modeling on diastolic heart sound recordings from 30 patients (10 post-angioplasty, 20 normal/abnormal).
- Analyzed model parameters, including power spectral density (PSD) functions and ARMA poles, for diagnostic classification.
- Performed blind assessments without prior knowledge of patient disease status or angioplasty timing.
Main Results:
- Correctly distinguished pre- and post-angioplasty records in 8 out of 10 cases.
- Accurately classified normal and abnormal records in 17 out of 20 cases.
- Identified high-frequency energy (above 400 Hz) in heart sounds as potentially indicative of coronary stenosis.
Conclusions:
- ARMA modeling of diastolic heart sounds shows promise for noninvasive detection and assessment of coronary artery disease.
- The technique can effectively differentiate between healthy and diseased states, and evaluate the impact of interventions like angioplasty.
- Further research into high-frequency acoustic markers may enhance diagnostic accuracy for coronary stenosis.
Abstract:
To further explore the application of advanced signal processing techniques to the noninvasive detection of coronary artery disease, 30 patients (10 angioplasty and 20 normal or abnormal) were tested using autoregressive moving average (ARMA) modelling of the diastolic heart sound data. It is during diastole that coronary blood flow is maximum and sounds associated with turbulent blood flow through partially occluded coronary arteries would be loudest. Model parameters (the power spectral density (PSD) functions and the poles of the ARMA method) were used to separate the normal patients from the abnormal patients in the normal/abnormal study, or to decide whether the recordings were made before or after angioplasty in the angioplasty study. The decisions were made 'blind', without knowledge of the actual disease states of the patients for the normal/abnormal study and without prior knowledge of whether a given recording was made before or after angioplasty for the angioplasty study. Results from the angioplasty and the normal/abnormal studies showed that pre- and post-angioplasty records were correctly distinguished in 8 out of 10 cases, and normal and abnormal records were correctly distinguished in 17 of 20 cases. These results also confirmed that high frequency energy above 400 Hz is probably associated with coronary stenosis.