Johns Hopkins Group Boosts Epilepsy Algorithm to Help Reduce Needless Brain Stimulation

Johns Hopkins Group Boosts Epilepsy Algorithm to Help Reduce Needless Brain Stimulation

Epilepsy affects 50 million people worldwide, but in a third of these cases, medication cannot keep seizures from occurring. One solution is to shoot a short pulse of electricity to the brain to stamp out the seizure just as it begins to erupt. But brain implants designed to do this have run into a stubborn problem: too many false alarms, triggering unneeded treatment. To solve this, a Johns Hopkins biomedical engineer has devised new seizure detection software that, in early testing, significantly cuts the number of unneeded pulses of current that an epilepsy patient would receive.

Sridevi V. Sarma, an assistant professor of biomedical engineering, is leading this effort to improve anti-seizure technology that sends small amounts of current into the brain to control seizures. “These devices use algorithms—a series of mathematical steps—to figure out when to administer the treatment,” Sarma said. “They’re very good at detecting when a seizure is about to happen, but they also produce lots of false positives, sometimes hundreds in one day. If you introduce electric current to the brain too often, we don’t know what the health impacts might be. Also, too many false alarms can shorten the life of the battery that powers the device, which must be replaced surgically.”

Her new software was tested on real-time brain activity recordings collected from four patients with drug-resistant epilepsy who experienced seizures while being monitored. In a study published recently in the journal Epilepsy & Behavior, Sarma’s team reported that its system yielded superior results, including flawless detection of actual seizures and up to 80 percent fewer alarms when a seizure was not occurring. Although the testing was not conducted on patients in a clinical setting, the results were promising.

Sridevi Sarma, assistant professor of biomedical engineering at The Johns Hopkins University. Photo by Will Kirk/Homewoodphoto.jhu.edu

Sridevi Sarma, assistant professor of biomedical engineering at The Johns Hopkins University. Photo by Will Kirk/Homewoodphoto.jhu.edu

“We’re making great progress in developing software that is sensitive enough to detect imminent seizures without setting off a large number of false alarms,” she said. Further fine-tuning is under way, using brain recordings from more than 100 epilepsy patients at Johns Hopkins Hospital, where several epilepsy physicians have joined in the research. Sarma said that within two to four years she hopes to see her system incorporated into a brain implant that can be tested on people with drug-resistant epilepsy.

“There is growing interest in applying responsive, or closed-loop, therapy for the treatment of epileptic seizures,” said Gregory K. Bergey, M.D., professor of neurology and director of the Johns Hopkins Epilepsy Center. “Devices to do this have been tested in humans, but for this therapy to be useful for the patient with epilepsy requires early detection of abnormal brain activity that is destined to become a seizure. Detection has to be within seconds of seizure onset, before the seizure spreads to cause disabling symptoms such as alteration of consciousness.”

He added, “Developing detection methods that can both provide this early detection and yet not be triggered by brain activity that will not become a clinical seizure has been a real challenge. Dr. Sarma’s group appreciates how important this is. The application of their detection algorithms has produced promising preliminary results that warrant further study of more seizures in more patients.”

Sridevi Sarma’s research focuses on a system with three components: electrodes implanted in the brain, which are connected by wires to a neurostimulator or battery pack, and a sensing device, also located in the brain implant, which detects when a seizure is starting and activates the current to stop it.

Sridevi Sarma’s research focuses on a system with three components: electrodes implanted in the brain, which are connected by wires to a neurostimulator or battery pack, and a sensing device, also located in the brain implant, which detects when a seizure is starting and activates the current to stop it. (Illustration by Greg Stanley/JHU)

In trying to solve the seizure false-alarm problem, Sarma drew on her training in electrical engineering, particularly a discipline called control theory. “We decided to start with the origin of the signal in the brain,” she said.

Sarma’s team compared electrical data from the brains of epilepsy patients before, during and after seizures. The researchers looked at how this activity changed over time, particularly when a seizure began. “We wanted to figure out when would be the optimal time to step in with treatment to stop the seizure,” she said. The team members “trained” their system to look for that moment without setting off false alarms.

Ideally, Sarma would someday like to see her software embedded in a microchip that would continually check electrical activity in the brain and launch electrical stimulation whenever a seizure is just beginning to form. The device would operate as a closed loop system, resembling a thermostat that keeps a room’s temperature at a constant, comfortable level.

Sarma’s interest in brain disorders developed relatively late in her education. She earned a bachelor’s degree from Cornell University in electrical engineering, then master’s and doctoral degrees at MIT, both in electrical engineering and computer science. During her doctoral studies, however, she pursued a minor in neuroscience. For a class, she conducted a case study of her aunt, who had developed Parkinson’s disease at age 29 and had trouble managing it with medication. Watching her aunt’s condition was an emotionally draining experience, Sarma said, and she wondered if anything in her own training could help. “I really wanted to understand the neurobiological circuitry of this disease,” she said.

That led Sarma to learn more about deep brain stimulation—the use of electric pulses to treat brain disorders such as Parkinson’s and epilepsy. She completed a postdoctoral fellowship in MIT’s Brain and Cognitive Sciences Department and became a neuroscience research associate affiliated with Massachusetts General Hospital and Harvard Medical School.

In 2009, Sarma joined the faculty of Johns Hopkins’ Department of Biomedical Engineering, which is shared by the School of Medicine and the Whiting School of Engineering. She also is a core faculty member in the university’s Institute for Computational Medicine. In 2011, Sarma was named a recipient of a Faculty Early Career Development Award from the National Science Foundation.

Her team’s new system for seizure detection with reduced false alarms is protected by a patent obtained through the Johns Hopkins Technology Transfer office.

Lead author of the Epilepsy & Behavior journal article was Sabato Santaniello, a postdoctoral fellow in Sarma’s lab. Along with Sarma, co-authors were Samuel P. Burns of the Johns Hopkins Department of Biomedical Engineering; Alexandra J. Golby of Brigham and Women’s Hospital in Boston; Jedediah M. Singer of Children Hospital, Boston; and William S. Anderson of the Johns Hopkins Department of Neurosurgery.

Epilepsy affects 50 million people worldwide, and seizures in 30% of the cases remain drug resistant. This has

increased interest in responsive neurostimulation, which is most effective when administered during seizure

onset. We propose a novel framework for seizure onset detection that involves (i) constructing statistics

from multichannel intracranial EEG (iEEG) to distinguish nonictal versus ictal states; (ii) modeling the dynamics

of these statistics in each state and the state transitions; you can remove this word if there is no room.

(iii) developing an optimal control-based “quickest detection” (QD) strategy to estimate the transition times

from nonictal to ictal states from sequential iEEG measurements. The QD strategy minimizes a cost function of

detection delay and false positive probability. The solution is a threshold that non-monotonically decreases

over time and avoids responding to rare events that normally trigger false positives. We applied QD to four

drug resistant epileptic patients (168 hour continuous recordings, 26–44 electrodes, 33 seizures) and achieved

100% sensitivity with low false positive rates (0.16 false positive/hour).

This article is part of a Supplemental Special Issue entitled The Future of Automated Seizure Detection and

Prediction.

Automatic online seizure detection (AOSD) in intractable epilepsy

has generated great interest in the last 20 years and is a fundamental

step toward the development of neurostimulation-based responsive

antiepileptic therapies [1–3]. Pioneering works in the late 1970s

and early 1980s by Gotman et al. [4,5] showed that seizures can be

automatically separated from interictal activity, and since then,

several approaches to AOSD have been proposed by exploiting either

scalp or intracranial EEG recordings, single or multichannel analysis,

linear or nonlinear features.

Osorio et al. [6–9] used a wavelet-based decomposition of selected

intracranial EEG recordings (iEEGs) to (i) separate the seizure-related

component from the background noise, (ii) track the ratio between

these components in the time–frequency domain, and (iii) detect a

seizure when such a ratio crosses a .xed threshold for a suf.ciently

long time. Parameters of the detection method (e.g., threshold,

Researchers at Johns Hopkins have been working on a way to improve the precision and effectiveness of seizure controlling brain implants by trying to eliminate false positives that needlessly trigger electrical pulses.

Sridevi V. Sarma, an an assistant professor of biomedical engineering at Hopkins with a background in electrical engineering and computer science, led the team that developed new algorithms that so far have been tested on brain recordings taken from four drug-resistant epileptics. The hope is that soon this algorithm will be tested in implanted devices of real patients in a proper clinical study.

From a Hopkins press release:

In a study published recently in the journal Epilepsy & Behavior, Sarma’s team reported that its system yielded superior results, including flawless detection of actual seizures and up to 80 percent fewer alarms when a seizure was not occurring. Although the testing was not conducted on patients in a clinical setting, the results were promising.

Further fine-tuning is under way, using brain recordings from more than 100 epilepsy patients at Johns Hopkins Hospital, where several epilepsy physicians have joined in the research. Sarma said that within two to four years she hopes to see her system incorporated into a brain implant that can be tested on people with drug-resistant epilepsy.

Sarma’s team compared electrical data from the brains of epilepsy patients before, during and after seizures. The researchers looked at how this activity changed over time, particularly when a seizure began. “We wanted to figure out when would be the optimal time to step in with treatment to stop the seizure,” she said. The team members “trained” their system to look for that moment without setting off false alarms.

source : http://releases.jhu.edu/2012/04/02/new-early-warning-system-for-seizures-could-lead-to-fewer-false-alarms/

Related Posts Plugin for WordPress, Blogger...
Be Sociable, Share!

About the Author

has written 1822 posts on this blog.

Copyright © 2017 Medical Technology & Gadgets Blog MedicalBuy.net. All rights reserved.
Proudly powered by WordPress. Developed by Deluxe Themes