Acoustic Features for the Identification of Coronary Artery Disease

• Published in: IEEE transactions on biomedical engineering Vol. 62; no. 11; pp. 2611 - 2619
• Main Authors: Schmidt, Samuel E., Holst-Hansen, Claus, Hansen, John, Toft, Egon, Struijk, Johannes J.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.11.2015; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Acoustics; Autoregressive processes; Cardiovascular disease; Complexity theory; Coronary artery disease; Coronary Artery Disease - diagnosis; Design automation; Diagnosis; Electronics; Feature extraction; Feature selection; Female; Gain; Heart; Heart Auscultation - methods; Heart sounds; Heart Sounds - physiology; Humans; Male; Medical instruments; Physical examinations; Receiving; Recording; Resonant frequency; Signal processing; Signal Processing, Computer-Assisted; Solid modeling; Stethoscopes; signal processing; Coronary artery disease; heart sounds; feature selection
• ISSN: 0018-9294; 1558-2531
• DOI: 10.1109/TBME.2015.2432129

Goal: Earlier studies have documented that coronary artery disease (CAD) produces weak murmurs, which might be detected through analysis of heart sounds. An electronic stethoscope with a digital signal processing unit could be a low cost and easily applied method for diagnosis of CAD. The current study is a search for heart sound features which might identify CAD. Methods: Nine different types of features from five overlapping frequency bands were obtained and analyzed using 435 recordings from 133 subjects. Results: New features describing an increase in low-frequency power in CAD patients were identified. The features of the different types were relatively strongly correlated. Using a quadratic discriminant function, multiple features were combined into a CAD-score. The area under the receiving operating characteristic for the CAD score was 0.73 (95% CI: 0.69-0.78). Conclusion: The result confirms that there is a potential in heart sounds for the diagnosis of CAD, but that further improvements are necessary to gain clinical relevance.