Indian Institute of Technology in Kharagpur investigators have developed an analytical method that can automatically classify a much wider range of heart sounds than is possible by the most skilled stethoscope-wielding physician, according to research published in the inaugural issue of the International Journal of Medical Engineering and Informatics.
Samit Ari and Goutam Saha from the Indian Institute have based their approach on mathematical analysis of the sound waves produced by the beating heart, known as empirical mode decomposition (EMD). The method breaks down the sounds of each heart cycle into its component parts, allowing them to isolate the sound of interest from background noise, such as the movements of the patient, internal body gurgles and ambient sounds.
The analysis produces a signal based on 25 different sound qualities and variables, which can then be fed into a computer-based classification system, according to the researchers. The classification uses an Artificial Neural Network and a Grow and Learn network, which are trained with standardized sounds associated with a specific diagnosis.
The team said they tested the trained networks using more than 100 different recordings of normal heart sounds, sounds from hearts with a variety of valve problems and different background noises.
Ari and Saha found that the EMD system performs more effectively in all cases than conventional electronic, wavelet-based, approaches to heart sound classification.
A disturbing percentage of medical graduates cannot properly diagnose heart conditions using a stethoscope, the researchers wrote, and the poor sensitivity of the human ear to low frequency heart sounds makes this task even more difficult. The automatic classification of heart sounds based on Ari and Saha's technique could remedy the failings.