Share
Blog
Cite
Print
Email
BookmarkScienceDaily (Jun. 25, 2001) — DALLAS, June 5 – An electronic stethoscope and a personal computer were used to distinguish innocent heart murmurs from those that may indicate a serious problem, and may help doctors render better medical decisions, researchers report in today’s Circulation: Journal of the American Heart Association.
See also:
“This technology offers great promise for the development of an accurate device for high-volume, low-cost screening for heart murmurs,” says lead author Curt G. DeGroff, M.D., a pediatric cardiologist at The Children’s Hospital and assistant professor in the department of pediatrics at the University of Colorado Health Sciences Center.
Studies estimate that a heart murmur can be heard in 77 percent to 95 percent of children at some time during childhood. A heart murmur is an extra heart sound heard with each heartbeat. Less than 1 percent of heart murmurs are a sign of problems such as those caused by defective heart valves or a malformed heart.
“Early recognition of a heart murmur is important. But equally important, is to avoid identifying a child with a healthy heart as having an abnormal heart murmur,” says DeGroff.
Listening to the heart is the primary tool for distinguishing heart murmurs. But the human ear cannot appreciate many of the subtleties of heart sounds and the interpretation of the sounds is prone to error, says DeGroff.
An artificial neural network (ANN) – a computer program which can recognize complex patterns – was developed by co-investigator Roop L. Mahajan, Ph.D., a professor of mechanical engineering at the University of Colorado, Boulder, and other colleagues. ANNs are valuable tools that can learn complex interactions and identify subtle relationships that may not be apparent to humans. Studies of ANNs in cardiology have been mainly concerned with the evaluation of electrocardiogram (ECG) signals. Their use on heart sounds has been examined in a few studies with limited results and applicability.
Here, researchers used heart sound recordings from 69 patients – 37 with abnormal heart murmurs and 32 with innocent murmurs – to train the network. Using a special mathematical model, they converted the sound recordings into the energy-per-unit of frequency interval to take advantage of the computer’s pattern-recognition capabilities.
“The mathematical signature for each child and the patterns for innocent and abnormal murmurs are different,” Mahajan explains.
The researchers fed samples of the heart recordings back to the ANN model and adjusted the frequency range and sensitivity of the signals to improve the computer’s ability to differentiate between the abnormal and innocent murmurs. They also re-entered the data to mathematically mimic consultations with multiple experts. By doing so, they reached 100 percent sensitivity (the ability to identify an abnormal heart murmur) and 100 percent specificity (the ability to identify an innocent heart murmur). Training the artificial neural network is akin to the way parents teach children life lessons, Mahajan notes. “As children, we are given some examples by our parents, and from those our brain neurons learn to make distinctions.”
Although these results are encouraging, DeGroff and Mahajan stress that this is a preliminary study and more development is needed before ANNs can be used for mass screening. Even then, ANNs will never replace the judgment of physicians.
“Such a device is not seen as replacing the need for a clinician’s assessment in a child found to have a heart murmur, but it may help the doctor render a better opinion,” DeGroff says.
Currently, pediatricians who detect a heart murmur usually refer children to specialists for further testing, says DeGroff. Hence, some children with abnormal conditions receive delayed diagnoses while families of children with innocent heart murmurs may go through weeks of anxiety and costly tests to rule out heart problems. A definitive test is an ultrasound called an echocardiogram, which can cost about $1,000.
Co-authors include Sanjay Bhatikar, Ph.D.; Jean Hertzberg, Ph.D.; Robin Shandas, Ph.D.; and Lilliam Valdes-Cruz, M.D.
