Artificial neural network-based method of screening heart murmurs in children

Background-Early recognition of heart disease is an important goal in pedia trics. Efforts in developing an inexpensive screening device that can assis t in the differentiation between innocent and pathological heart murmurs ha ve met with limited success. Artificial neural networks (ANNs) are valuable tools used in complex pattern recognition and classification tasks. The ai m of the present study was to train an ANN to distinguish between innocent and pathological murmurs effectively. Methods and Results-Using an electronic stethoscope, heart sounds were reco rded from 69 patients (37 pathological and 32 innocent murmurs). Sound samp les were processed using digital signal analysis and fed into a custom ANN. With optimal settings, sensitivities and specificities of 100% were obtain ed on the data collected with the ANN classification system developed. For future unknowns, our results suggest the generalization would improve with better representation of all classes in the training data. Conclusion-We demonstrated that ANNs show significant potential in their us e as an accurate diagnostic tool for the classification of heart sound data into innocent and pathological classes. This technology offers great promi se for the development of a device for high-volume screening of children fo r heart disease.