IIT Kharagpur researchers develop technique for better analysis of heart soundsJuly 12th, 2008 - 2:02 pm ICT by ANI
Washington , July 12 (ANI): The age-old method of using the stethoscope for analysing the sounds of the heart to diagnose heart problems involves a high error of judgment, as it is not possible to identify murmurs, palpitations, and other anomalies quickly and then carry out appropriate in-depth tests.
But now, researchers at the Indian Institute of Technology in Kharagpur have developed a new technique that could circumvent the problem of the failing stethoscope skills of medical graduates and reduce errors of judgment
This analytical method developed by Samit Ari and Goutam Saha can automatically classify a much wider range of heart sounds than is possible even by the most skilled stethoscope-wielding physician.
The technique is based on a mathematical analysis of the sound waves produced by the beating heart known as Empirical Mode Decomposition (EMD). This method breaks down the sounds of each heart cycle into its component parts, enabling 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 thus produces a signal based on twenty five different sound qualities and variables, which can then be fed into a computer-based classification system. The classification uses an Artificial Neural Network (ANN) and a Grow and Learn (GAL) network. These are trained with standardized sounds associated with a specific diagnosis.
Later, the team 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. They found that the EMD system performs more effectively in all cases than conventional electronic, wavelet-based, approaches to heart sound classification.
The researchers explained that a large number of medical graduates cannot properly diagnose heart conditions using a stethoscope, and the poor sensitivity of the human ear to low frequency heart sounds makes this task even more difficult. And this fallacy may be averted by using the automatic classification of heart sounds based on Ari and Saha’’s technique.
The study is published in the inaugural issue of the International Journal of Medical Engineering and Informatics looks. (ANI)
- Now, a bionic speech enhancement system to cut unwanted 'white noise' - Sep 10, 2010
- HD Medical developing hand-held ultra sound equipment - Nov 03, 2010
- Seeing forest and trees could help detect heart problems - Jul 27, 2010
- Stethoscope helps doctors win patients' trust - Aug 13, 2012
- Shrinking ultrasound device will be handy as stethoscope - Feb 24, 2011
- New technique uses alcohol to save heart - Feb 01, 2011
- Fuzzy thinking could detect heart disease risk - Sep 16, 2010
- Doctors diagnose patients within moments of meeting - Dec 15, 2011
- Digital signal processing technique sheds light on memory and learning - Feb 08, 2011
- Noisy knees could help diagnose osteoarthritis - Aug 31, 2010
- Lighting up your innards for incision-less surgery - Jun 27, 2012
- New angiography technique a boon for many - Feb 03, 2012
- 'Earprint' touch sensors to improve sound quality in iPhones - Oct 01, 2010
- 'NoiseTube': cell phone app that maps noise pollution - Nov 19, 2009
- After court rap, doctor's group unsure about PIL on Ketan Desai - Dec 21, 2010
Tags: artificial neural network, background noises, beating heart, emd system, empirical mode decomposition, gurgles, heart conditions, heart cycle, heart problems, heart sound, indian institute of technology, mathematical analysis, medical graduates, sound classification, sound qualities, sound waves, sounds of the heart, stethoscope skills, trained networks, valve problems