More Like this

1. Towards Interpretable Seizure Detection Using Wearables

   https://doi.org/10.1109/ICASSP49357.2023.10097091  

   Al-Hussaini, Irfan; Mitchell, Cassie S. (June 2023, IEEE)
2. Absence Seizure Detection Using Ramanujan Filter Banks

   https://doi.org/10.1109/ACSSC.2018.8645492  

   Tenneti, Srikanth V.; Vaidyanathan, P. P. (October 2018, Asilomar Conf. on Sig., Sys., and Computers)

   Absence seizures are a type of generalized seizures characterized by a 3 Hz periodic spike and wave discharge pattern in the Electroencephalogram (EEG). The most common way to diagnose them is by detecting such periodic patterns in a patient’s EEG. Recently, a new method known as Ramanujan Filter Bank (RFB) was proposed for identifying, estimating and localizing periodicities in data. The RFB was shown to offer important advantages over traditional period estimation techniques in DSP. In this work, we demonstrate that the RFB offers very useful diagnostic information when applied to EEG signals from absence-seizure patients. 

   more » « less
3. Forecasting seizure clusters from chronic ambulatory electrocorticography

   https://doi.org/10.1111/epi.17347  

   Ilyas, Adeel; Hoffman, Clarissa; Vakilna, Yash; Chaliyeduth, Sreekanth; Muhlhofer, Wolfgang; Riley, Kristen O; Dabaghian, Yuri; Lhatoo, Samden D; Pati, Sandipan (September 2022, Epilepsia)

   Abstract Seizure clusters are seizures that occur in rapid succession during periods of heightened seizure risk and are associated with substantial morbidity and sudden unexpected death in epilepsy. The objective of this feasibility study was to evaluate the performance of a novel seizure cluster forecasting algorithm. Chronic ambulatory electrocorticography recorded over an average of 38 months in 10 subjects with drug‐resistant epilepsies was analyzed pseudoprospectively by dividing data into training (first 85%) and validation periods. For each subject, the probability of seizure clustering, derived from the Kolmogorov–Smirnov statistic using a novel algorithm, was forecasted in the validation period using individualized autoregressive models that were optimized from training data. The primary outcome of this study was the mean absolute scaled error (MASE) of 1‐day horizon forecasts. From 10 subjects, 394 ± 142 (mean ± SD) electrocorticography‐based seizure events were extracted for analysis, representing a span of 38 ± 27 months of recording. MASE across all subjects was .74 ± .09, .78 ± .09, and .83 ± .07 at .5‐, 1‐, and 2‐day horizons. The feasibility study demonstrates that seizure clusters are quasiperiodic and can be forecasted to clinically meaningful horizons. Pending validation in larger cohorts, the forecasting approach described herein may herald chronotherapy during imminent heightened seizure vulnerability. 

   more » « less
4. Applicability of Hyperdimensional Computing to Seizure Detection

   https://doi.org/10.1109/OJCAS.2022.3163075  

   Ge, Lulu; Parhi, Keshab K. (January 2022, IEEE Open Journal of Circuits and Systems)
5. Epileptic Seizure Detection and Experimental Treatment: A Review

   https://doi.org/10.3389/fneur.2020.00701  

   Kim, Taeho; Nguyen, Phuc; Pham, Nhat; Bui, Nam; Truong, Hoang; Ha, Sangtae; Vu, Tam (July 2020, Frontiers in Neurology)