Optimizing Pharmacotherapy in Epilepsy using Seizure Forecasts via EEG and Wearables

Overview

About this study

The purpose of this study is to evaluate the safety & feasibility of using seizure forecasts based on subscalp EEG.

Participation eligibility

Participant eligibility includes age, gender, type and stage of disease, and previous treatments or health concerns. Guidelines differ from study to study, and identify who can or cannot participate. There is no guarantee that every individual who qualifies and wants to participate in a trial will be enrolled. Contact the study team to discuss study eligibility and potential participation.

Inclusion Criteria:

Adults with epilepsy involving the temporal lobe will be candidates. All subjects will have undergone prior video-EEG monitoring to be included in this study.

Focal epilepsy, including complex partial, and secondarily generalized seizures, including:
- disabling seizure counts >2 per month, established by verbal history or caregiver report.
- For 3 months prior to enrollment, subject’s AEDS dosages have been stable (less than a 25% change in dosage) and subject has had at least two seizures per month, on average, with a seizure-free interval not to exceed 60 days. Seizures must be separated by a minimum of four hours not to be considered part of a cluster. A cluster, for the purpose of this criterion, shall be considered a single seizure.
Except for epilepsy, subject must be medically and neurologically stable.
Age 18 to 75.
Ability and willingness to provide informed consent and participate in the study protocol. Subject can interpret and to respond, in accordance with the study protocol, to the advisory indicators provided by the device.
Subject has seizures that are distinct, stereotypical events that can be reliably counted by the subject or caregiver and have a distinct EEG pattern that can be recorded using subscalp EEG over the frontotemporal head region.
Subject can reasonably be expected to maintain a seizure diary alone or with the assistance of a competent individual.
Subject can complete regular office visits and telephone [MCL1] appointments in accordance with the study protocol requirements.
Subject’s seizure focus, based upon clinical semiology, intracranial electroencephalographic (iEEG) findings, and/or neuroimaging, shall demonstrate temporal lobe involvement.
Subject speaks and reads English.
Subject has no reason to anticipate requiring a brain magnetic resonance imaging (MRI) epilepsy evaluation within the next two years.
Subject has EEG documentation of ictal events consistent with his or her predominant current seizure type.
Subject’s anatomy will permit implantation of the UNEEG SubQ device.

Exclusion Criteria:

Subjects shall not be enrolled if any of the following criteria apply:

For 3 months prior to enrollment, subject’s AED dosages have not been stable (greater than 25% change in dosage), or subject has had more than 30 disabling seizures per month, on average.
Subject needs to have magnetic resonance imaging during the study period.
Subject has a substance abuse history (alcohol, prescription, or illicit medications) within the preceding two years.
Subject participated in another drug or device trial within the preceding 30 days.
Subject has been hospitalized for a psychiatric condition within the preceding two years or has had a history of psychosis within the preceding two years (excluding post-ictal psychosis).
Subject is implanted with pacemaker, implantable cardiac defibrillator, cardiac management product, brain stimulator, or another medical device that would interfere with the UNEEG device. This includes, but is not limited to, direct brain neurostimulators, spinal cord stimulators, and cochlear implants. Vagus nerve stimulators are not expected to interfere with the subscalp EEG device and will be permitted, as long as stimulation parameters can be reasonably expected to remain stable (25% or less change in amplitude) throughout the study.
Subject has experienced unprovoked status epilepticus in the preceding year.
Subject has had therapeutic surgery to treat epilepsy that may interfere with electrode placement in the judgement of the neurosurgeon.
Subject is on anticoagulants and is unable to discontinue them presurgically, as required by the neurosurgeon or Investigator.
Subject has significant platelet dysfunction from medical conditions or medications (including, particularly, aspirin or sodium valproate). If platelet dysfunction is suspected, subject can be enrolled only if a hematologist, the Investigator, and the neurosurgeon judge it to be advisable.
Subject is otherwise ineligible for cranial surgery, or the Investigators identify other medical or psychosocial factors that would counter indicate participation in the study.

Note: Other protocol defined Inclusion/Exclusion criteria may apply.

Eligibility last updated 5/17/23. Questions regarding updates should be directed to the study team contact.

Participating Mayo Clinic locations

Study statuses change often. Please contact the study team for the most up-to-date information regarding possible participation.

Mayo Clinic Location	Status	Contact
Rochester, Minn. Mayo Clinic principal investigator Benjamin Brinkmann, Ph.D.	Open for enrollment	Contact information: Jeffrey Laivell (507) 538-8095 Laivell.Jeffrey@mayo.edu

Mayo Clinic Location

Status

Contact

Rochester, Minn.

Mayo Clinic principal investigator

Benjamin Brinkmann, Ph.D.

Open for enrollment

Contact information:

Jeffrey Laivell

(507) 538-8095

Laivell.Jeffrey@mayo.edu

More information

Publications

One of the most disabling aspects of living with chronic epilepsy is the unpredictability of seizures. Cumulative research in the past decades has advanced our understanding of the dynamics of seizure risk. Technological advances have recently made it possible to record pertinent biological signals, including electroencephalogram (EEG), continuously. We aimed to assess whether patient-specific seizure forecasting is possible using remote, minimally invasive ultra-long-term subcutaneous EEG. Read More on PubMed
This study describes a generalized cross-patient seizure-forecasting approach using recurrent neural networks with ultra-long-term subcutaneous EEG (sqEEG) recordings. Data from six patients diagnosed with refractory epilepsy and monitored with an sqEEG device were used to develop a generalized algorithm for seizure forecasting using long short-term memory (LSTM) deep-learning classifiers. Electrographic seizures were identified by a board-certified epileptologist. One-minute data segments were labeled as preictal or interictal based on their relationship to confirmed seizures. Data were separated into training and testing data sets, and to compensate for the unbalanced data ratio in training, noise-added copies of preictal data segments were generated to expand the training data set. The mean and standard deviation (SD) of the training data were used to normalize all data, preserving the pseudo-prospective nature of the analysis. Different architecture classifiers were trained and tested using a leave-one-patient-out cross-validation method, and the area under the receiver-operating characteristic (ROC) curve (AUC) was used to evaluate the performance classifiers. The importance of each input signal was evaluated using a leave-one-signal-out method with repeated training and testing for each classifier. Cross-patient classifiers achieved performance significantly better than chance in four of the six patients and an overall mean AUC of 0.602 ± 0.126 (mean ± SD). A time in warning of 37.386% ± 5.006% (mean ± std) and sensitivity of 0.691 ± 0.068 (mean ± std) were observed for patients with better than chance results. Analysis of input channels showed a significant contribution (p < .05) by the Fourier transform of signals channels to overall classifier performance. The relative contribution of input signals varied among patients and architectures, suggesting that the inclusion of all signals contributes to robustness in a cross-patient classifier. These early results show that it is possible to forecast seizures training with data from different patients using two-channel ultra-long-term sqEEG. Read More on PubMed

Clinical Trials