A team of researchers have developed a computational tool to predict heart attacks.
This tool will help to find slight changes in the electrical activity in the heart and is developed by data mining and machine learning techniques.
Researchers from University of Michigan, MIT, Harvard Medical school and Brigham Women’s Hospital in Boston have worked on 4557 heart attack patients and measured the electrical activity of their heart to find defective patterns, which were previously considered as noise or were undetectable. Many of these activities are considered as computational markers which can help doctors to check the patients which are at higher risk.
[hana-code-insert name=’Adsense’ /]
Almost, 1 million Americans have heart attack each year. And according to American Heart Association, more than ¼ of those die of the complications of initial attack within a year.
These biomarkers, as used by researchers, have helped researchers to predict 50% more deaths.
Zeeshan Syed, Assistant professor of the University of Michigan Department of Electrical Engineering and Computer Science, has said,
“There’s information buried in the noise, and it’s almost invisible because of the sheer volume of the data. But by using sophisticated computational techniques, we can separate what is truly noise from what is actually abnormal behavior that tells us how unstable the heart is.”
Zeeshan Syed et. al. (2011). Computationally Generated Cardiac Biomarkers for Risk Stratification After Acute Coronary Syndrome. Science Translational Medicine, 3(102), 102ra95