In the months after a heart attack, certain patients are particularly vulnerable to sudden death due to irregular heart rhythms. The problem is not a shortage of information about those heart rhythms, but rather, that doctors need a better way to sift through the patterns to detect danger signals. "We've reached a point in medicine where our ability to collect data has far out-stripped our ability to analyze or digest it," said John Guttag, a professor at MIT.
Zeeshan Seyd, an assistant professor in the University of Michigan Department of Electrical Engineering and Computer Science, is working with Guttag and Collin Stultz, another MIT professor, to find "computational biomarkers" in ECG data that may indicate defects in the heart muscle and nervous system that evolve over time.
The researchers looked at these biomarkers — specifically, morphologic variability, heart rate motifs, and symbolic mismatch — and found that patients in the study whose EKG signals had at least one of these abnormalities were between two and three times more likely to die within 12 months. They also found that by adding all three of these techniques to doctors' current assessment tools, they could predict 50 percent more deaths with fewer false positives.
Since these techniques use data already routinely collected during hospital visits, implementation should not add any costs or further burden caregivers or patients.
Click here for the full story.
