Conference Paper

Intelligent Phonocardiogram Analysis and Representation Tool

Conference: HEALTHINF 2011 - Proceedings of the International Conference on Health Informatics, Rome, Italy, 26-29 January, 2011
Source: DBLP

ABSTRACT Cardiac auscultation is a highly sensitive, specific, cost effective and comfortable diagnosis technique for many cardiovascular diseases. Unfortunately, it is observed that the art of auscultation is mastered by an increasingly lower number of medical professionals. This paper presents a Matlab tool to support physicians in performing auscultation. This application enables real time signal acquisition using off-the-shelf sensors and performs several automatic annotation functions of heart sounds, such as noise contamination detection, segmentation into S1, S2 and S3, S2-split detection, murmur detection and classification, systolic time intervals measurement, contractility and stroke volume. These are related to the most pertinent clinical applications of this signal. Moreover, it can also be used for auscultation training.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We assessed the accuracy of physician trainees in identifying different cardiac sounds and examined the factors influencing their cardiac auscultation proficiency. A total of 106 physicians in the Family Medicine Training Programme were asked to identify 10 cardiac sounds played sequentially on the Littmann electronic stethoscope, which functioned as a surrogate patient. Their auscultation accuracy was scored numerically out of a maximum of 10. Demographical data of the physicians was collected prospectively. The mean (+/-SD) auscultation proficiency score of the study population was 4.0 +/- 1.7. Physicians who graduated in 1994 or earlier fared significantly poorer than those who obtained their Bachelor of Medicine and Bachelor of Surgery degrees between 1995 and 2000 (p-value equals 0.02). Auscultation proficiency was not related to current practice, previous years of primary care, cardiology, internal medicine or paediatric medicine postings, or cumulative years of postings. Normal heart sounds were most accurately identified. Prosthetic cardiac sounds were better identified than other extra-cardiac sounds while systolic murmurs were more accurately identified than diastolic murmurs. Tachycardia had the lowest identification rate. Our data suggest that cardiac auscultation skill declined with time, being significantly impaired eight years after graduation. We suggest that there is a need for retraining in the form of continuing medical education to address not only new knowledge and skills, but also basic skill competency.
    Singapore medical journal 02/2005; 46(1):11-4. · 0.63 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: A new method and application is proposed to characterize intensity and pitch of human heart sounds and murmurs. Using recorded heart sounds from the library of one of the authors, a visual map of heart sound energy was established. Both normal and abnormal heart sound recordings were studied. Representation is based on Wigner-Ville joint time-frequency transformations. The proposed methodology separates acoustic contributions of cardiac events simultaneously in pitch, time and energy. The resolution accuracy is superior to any other existing spectrogram method. The characteristic energy signature of the innocent heart murmur in a child with the S3 sound is presented. It allows clear detection of S1, S2 and S3 sounds, S2 split, systolic murmur, and intensity of these components. The original signal, heart sound power change with time, time-averaged frequency, energy density spectra and instantaneous variations of power and frequency/pitch with time, are presented. These data allow full quantitative characterization of heart sounds and murmurs. High accuracy in both time and pitch resolution is demonstrated. Resulting visual images have self-referencing quality, whereby individual features and their changes become immediately obvious.
    BioMedical Engineering OnLine 02/2007; 6:16. · 1.61 Impact Factor
  • Source


Available from
May 28, 2014