Publications by authors named "Tyler Blevins"
There exist significant clinical and basic research needs for accurate, automated seizure detection algorithms. These algorithms have translational potential in responsive neurostimulation devices and in automatic parsing of continuous intracranial electroencephalography data. An important barrier to developing accurate, validated algorithms for seizure detection is limited access to high-quality, expertly annotated seizure data from prolonged recordings.
View Article and Find Full Text PDFArticle Synopsis
- The FDA has approved a closed-loop intracranial device for epilepsy treatment, but high sensitivity can lead to false positives and reduced battery life.
- A new seizure detection model utilizing a Bayesian nonparametric Markov switching process has been developed to improve accuracy by focusing on specific event states in iEEG data, effectively reducing false positive detections.
- The novel method showed better performance in a pilot study, with no missed seizures and a significantly lower false positive rate, making it a promising advancement for real-time, implantable epilepsy monitoring.