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.

Related Concept Videos