PHILADELPHIA, June 22 (UPI) — U.S. scientists say they’ve trained a computer network to create virtual heart attacks, allowing them to study how blood platelets respond during such events.
The team of bioengineers from the University of Pennsylvania’s Institute for Medicine and Engineering said their computer neural network model can accurately predict how blood platelets would respond to complex conditions found during a heart attack or stroke.
The team said it used an automated, robotic system to expose human blood platelets to hundreds of different combinations of biological stimuli, such as those experienced during a heart attack. That was accomplished, they said, by “fingerprinting” each platelet sample with 34,000 data points obtained in response to all possible pairs of stimuli.
The researchers said their model predicted platelet responses accurately, even distinguishing between 10 blood donors, thereby demonstrating an efficient approach for predicting complex chemical responses in a patient-specific disease milieu.
“With patient-specific computer models, it is now possible to predict how an individual’s platelets would respond to thousands of ‘in silico’ heart-attack scenarios,” said Professor Scott Diamond, the director of the Penn Center for Molecular Discovery, who led the study. “With this information we can identify patients at risk of thrombosis or improve upon current forms of anti-platelet therapies.”
The study that included Professor Lawrence Brass, Manash Chatterjee and Jeremy Purvis is reported in the journal Nature Biotechnology.
Copyright 2010 United Press International, Inc. (UPI). Any reproduction, republication, redistribution and/or modification of any UPI content is expressly prohibited without UPI’s prior written consent.