Noise detection in heart sound recordings

Area of Science:

• Cardiology
• Biomedical Engineering
• Acoustic Signal Processing

Background:

• Coronary artery disease (CAD) is a leading cause of mortality, often detected late.
• Current diagnostic methods for CAD are invasive, costly, and unsuitable for early screening.
• Early detection of CAD is crucial for timely intervention and improved patient outcomes.

Purpose of the Study:

• To develop a noninvasive and cost-effective acoustic system for early CAD detection.
• To address the challenge of clinical noise interfering with faint acoustic signals from narrowed coronary arteries.
• To propose and validate a novel noise detection and elimination method for acoustic CAD diagnosis.

Main Methods:

• Utilizing an acoustic approach to identify sounds generated by turbulent blood flow in narrowed coronary arteries.
• Implementing a reference channel-based method for detecting and eliminating ambient clinical noise.
• Evaluating the effectiveness of the proposed noise reduction technique in preserving faint CAD-related acoustic signals.

Main Results:

• The developed acoustic method shows promise for noninvasive CAD detection.
• The proposed noise detection and elimination technique effectively mitigates interference from clinical noise.
• Successful identification of noise is demonstrated as critical for the acoustic approach's viability.

Conclusions:

• A noninvasive acoustic system using noise reduction shows potential for early coronary artery disease screening.
• The developed noise cancellation method is essential for the success of the acoustic CAD detection approach.
• This technology could offer a cost-effective and accessible alternative to current invasive diagnostic tools.