Statistics show that epileptic seizures affect 60 million people around the world, including about 60,000 in Massachusetts. About a third of patients continue to have seizures despite available therapies.
Many clinicians in the field say that using non-invasive technology to detect the onset of seizures in time to minimize consequences is a major unmet challenge.
Steven Schachter, MD, was one speaker at the July 17 Forum that focused on epilepsy and other ailments associated with neurotechnology. It was the second in a four part series, “Neurotechnology: Translating Basic Discoveries into Clinical Promise.”
Dr. Schachter addressed the subject of “Decoding Cortical Electrophysiology for the Detection of Seizures.” He is a professor of neurology at Harvard Medical School; director of research, Department of Neurology, Beth Israel Deaconess Medical Center; associate director, clinical research, Harvard Medical School Osher Institute; founder and editor of “Epilepsy and Behavior,” a periodical and Epilepsy.com; CIMIT program leader for neurotechnology; and CIMIT site miner for BIDMC.
His research involves using vagus nerve stimulation, which is an adjunctive treatment for certain types of intractable forms of epilepsy. VNS uses a stimulator that sends electric impulses to the left vagus nerve in the neck via a lead implanted under the skin.
Dr. Schachter is using his skill as a clinician to develop a system that will help patients and doctor to identify the onset of a seizure.
Dr. John Guttag, is Dugald C. Jackson Professor, Department of Electrical Engineering and Computer Science at MIT. He is working closely with Dr. Schachter to determine the statistically most accurate approach to determine the success of their methods.
The team is considering looking into other diseases that result in seizures or neuro-episodes. Dr. Guttag said they are seeking collaborators in their upcoming work.
Throughout the world, epilepsy is a common and dangerous problem. One in every hundred people has the disease, and one out of three epileptics continue to have intermittent seizures despite taking medication. Most epileptics seize without warning, and their seizures can have dangerous or fatal consequences, if they come at a bad time and lead to an accident. In the brain, identifiable electrical changes precede the clinical onset of a seizure by tens of seconds, and these changes can be recorded in an electroencephalogram (EEG). Many people have wondered if EEG’s might be used to predict seizures minutes or even hours ahead of time, but as of now, this sort of prediction has not been feasible. Many researchers are working, however, to create a system capable of detecting seizures before they clinically manifest themselves.
The early detection of a seizure has many potential benefits. Advanced warning would allow patients to take action to minimize their risk of injury and, in some circumstances, would allow them to summon help. An automatic detection system could also be made to trigger pharmacological intervention in the form of fast-acting drugs or electrical stimulation.
It is relatively easy to place the electrodes needed to record an EEG, but it has not been so easy to develop an algorithm to detect the onset of a seizure. For any given patient, assuming his or her seizures originate in one focus, seizure-onset EEG patterns are largely conserved from one seizure episode to the next. Unfortunately, there is great EEG variation between patients, both in terms of baseline and seizure-onset patterns. This variation has made the development of a generic, “one-size-fits-all” algorithm difficult.
Patient-specific algorithms based on machine learning have shown more promise. Machine learning algorithms compute binary decision trees from manually labeled training sets of data. EEG data must be translated into a format that a computer can interpret. Important information must be kept while superfluous information must be discarded. Although there are many conceivable ways of performing this “feature extraction,” wavelet decomposition seems to be an effective way of extracting pertinent information from EEG signals.
The training set for the machine-learning algorithm must be labeled by hand. For an algorithm being developed by Dr. Schachter and Prof. Guttag of MIT, EEG recordings are split into two-second time windows, and each window is labeled as “seizure onset” or “not seizure onset.”
The algorithm then takes the labeled training set and uses it to construct a decision tree capable of classifying unlabeled EEG patterns as “seizure onset” or “not seizure onset.” The training set is unavoidably unbalanced because most time windows do not involve seizures. Certain algorithms, such as the support vector machine algorithm chosen by Schachter and Guttag, are better suited than others to handle this unbalanced training set.
In the hospital, the patient-specific algorithm of Schachter and Guttag has worked fairly well. In one trial, it detected 131 out of 139 seizures in 36 patients. In another, it caught 53 out of 58 seizures. The algorithm outperformed generic algorithms, but the investigators still had to carefully balance tradeoffs between sensitivity and specificity. They also considered latency, which they defined as the time lag between the point at which a physician was retrospectively able to detect a seizure from an EEG and the time at which the algorithm detected the seizure. Latency was correlated with specificity. Studies are underway to look at whether patient-specific algorithms can be used to trigger vagus-nerve stimulation, a therapeutic technique that has been shown to reduce the severity of seizures if administered early enough.In the future, Dr. Schachter and Prof. Guttag hope to improve their algorithm so that it is less sensitive to electrode placement and so that it functions effectively with input from fewer electrodes and with smaller training sets. Their goal is to create an unobtrusive device that can be worn continually by epileptics to detect impending seizures. Such a device would greatly enhance the ability of these people to safely go about their lives.
Start or edit a Neurotechnology encyclopedia article on Wikipedia.
You can link to this page from the article using the following URL:
Learn more about Wikipedia.
Post a comment / start a discussion on the Forum Blog regarding this Forum.
EMBED THIS VIDEO:
Cut and paste the code below to embed this video on your site:
LINK TO THIS FORUM: