No abstract

Because pediatric cardiologists can accurately diagnose innocent murmurs by physical exam alone, the authors developed a system for remote cardiac auscultation. They hypothesized that their system could accurately classify auscultatory findings as normal/innocent or pathologic. Patients undergoing evaluation underwent examination, echocardiography, and heart sound recording. Pediatric cardiologists evaluated the heart sounds and classified the case as either normal/innocent or pathologic. They reviewed103 heart sound data sets; 85% of the cases were accurately classified as either normal/innocent or pathologic, with a sensitivity of 82% and specificity of 86%. However, when accounting for clinical diagnosis, reviewer uncertainty, and ECG abnormalities, the sensitivity and specificity improved to 91% and 88% (accuracy 89%), respectively. Degree of certainty with the telecardiology diagnosis correlated with correct interpretation (P < .005). Digital heart sound recordings evaluated via telemedicine can distinguish normal/innocent murmurs from pathologic ones. Such a system could improve the use of pediatric cardiology services.