Researchers Tap Health IT To Study Epilepsy, Predict Seizures

December 12, 2014 in News

A team of mathematicians and engineers developed an algorithm that can predict epileptic seizures 82% of the time, NPR’s “Shots” reports (Hamilton, “Shots,” NPR, 12/10).

According to “Shots,” epilepsy affects about 1% of the population. Treatments include:

  • An implantable device that prevents seizures using electrical pulses;
  • Medication, which can make patients tired or dizzy; and
  • Surgery.

The team developed the algorithm as part of an online competition, in which teams used crowdsourced data on epilepsy to develop methods for seizure detection and prevention (American Epilepsy Society release, 12/8).

An algorithm with a high rate of successful seizure predictions could make implanted devices more effective, according to “Shots.” The method would allow the devices to work like heart defibrillators that only deliver electrical currents when necessary.

Walter Koroshetz — acting director of the National Institute of Neurological Disorders and Stroke, which is a sponsor of the contest — said, “[The algorithm] has real clinical potential,” adding, “We’d like to develop therapies that come in when they are needed instead of people taking medicine all the time” (“Shots,” NPR, 12/10).

Project To Study Epilepsy Using Health IT

In related news, a group of several research centers has received $27.3 million to use big data analytics to examine the causes of sudden unexpected death in epilepsy, or SUDEP, Health IT Analytics reports.

The initiative, called the Center Without Walls for Collaborative Research, is funded by NIH and includes 15 institutions in the U.S. and United Kingdom.

GQ Zhang, principal investigator of informatics and data analytics core at the center, said, “Only through collaboration among multiple sites can clinicians and scientists gather enough physiological, imaging, genomic and other data to learn the causes and develop treatment strategies to prevent SUDEP.”

Members of the initiative will develop several strategies to research SUDEP, including algorithms and other models to identify risk factors of the condition (Bresnick, Health IT Analytics, 12/9).

Be the first to like.
VN:F [1.9.22_1171]
Rating: 0.0/5 (0 votes cast)

Article source:

Be Sociable, Share!
Bookmark and Share

Leave a reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>