Automated Phonocardiographic Screening for Heart Disease in Children

Mass screening for heart disease in children can be accomplished by automatic analysis of phonocardiograms (PCG) obtained from five routine auscultation points. An ECG signal serves as reference. PCG signals exceeding 20% of the amplitude of the first heart sound S<sub>1</sub> in the diastolic interval and 40% of S<sub>1</sub> in the systolic interval are considered as abnormal. Signals in the systolic interval with an amplitude between 20 and 40% of S<sub>1</sub> are classified as normal if their duration is less than two-thirds of the interval from the first to second heart sound. Thus, the method takes into account innocent murmurs and classifies them as normal. The splitting of the second sound is detected by monitoring its duration at a level of 20% of S<sub>1</sub>. This method was tested on 2,583 children aged from 3 to 14 years and on 345 children with proven heart disease. The results obtained showed a sensitivity of 96.5% and a specificity of 92.4%.