Algorithm for automatic detection of spontaneous seizures in rats with post-traumatic epilepsy

Andrade, Pedro; Paananen, Tomi; Ciszek, Robert; Lapinlampi, Niina; Pitkänen, Asla

doi:10.1016/j.jneumeth.2018.06.015

Cited by 19 publications

(19 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Discussionsupporting

confidence: 81%

“…In records containing a large number of artifacts even after application of an artifact removal procedure, the number of FPs remaining for visual inspection was relatively high (ranging from 0 to 193/d, on average 32/d, or 1.3/h), which is comparable to what has been described in the literature. 38,39 Overall, we have shown a reliable automated tool that provides high sensitivity, detecting 100% of the EEG seizures in different animal models of genetic and acquired epilepsy. Our Assyst is versatile and a significantly time-saving seizure detection program, which can facilitate high-throughput studies.…”

Section: Discussionmentioning

confidence: 92%

See 1 more Smart Citation

A universal automated tool for reliable detection of seizures in rodent models of acquired and genetic epilepsy

Casillas‐Espinosa

Sargsyan²,

Melkonian³

et al. 2019

Epilepsia

View full text Add to dashboard Cite

Summary Objective Prolonged electroencephalographic (EEG) monitoring in chronic epilepsy rodent models has become an important tool in preclinical drug development of new therapies, in particular those for antiepileptogenesis, disease modification, and treating drug‐resistant epilepsy. We have developed an easy‐to‐use, reliable, computational tool for automated detection of electrographic seizures from prolonged EEG recordings in rodent models of epilepsy. Methods We applied a novel method based on advanced time‐frequency analysis that detects EEG episodes with excessive activity in certain frequency bands. The method uses an innovative technique of short‐term spectral analysis, the Similar Basis Function algorithm. The method was applied for offline seizure detection from long‐term EEG recordings from four spontaneously seizing, chronic epilepsy rat models: the fluid percussion injury (n = 5 rats, n = 49 seizures) and post–status epilepticus models (n = 119 rats, n = 993 seizures) of acquired epilepsy, and two genetic models of absence epilepsy, Genetic Absence Epilepsy Rats from Strasbourg and Wistar Albino Glaxo from Rijswijk (n = 41 and 14 rats, n = 8733 and 825 seizures, respectively). Results Our comparative analysis revealed that the EEG amplitude spectra of these four rat models are remarkably similar during epileptiform activity and have a single expressed peak within the 17‐ to 25‐Hz frequency range. Focusing on this band, our computer program detected all seizures in the 179 rats. A quick semiautomated user inspection of the EEGs for the period of each identified event allowed quick rejection of artifact events. The overall processing time for 12‐day‐long recordings varied from a few minutes (5‐10) to 30 minutes, depending on the number of artifact events, which was strongly correlated with the signal quality of the raw EEG data. Significance Our automated seizure detection tool provides high sensitivity, with acceptable specificity, for long‐ and short‐term EEG recordings from both acquired and genetic chronic epilepsy rat models. This tool has the potential to improve the efficiency and rigor of preclinical research and therapy development using these models.

show abstract

Section: Discussionsupporting

confidence: 81%

Section: Discussionmentioning

confidence: 92%

A universal automated tool for reliable detection of seizures in rodent models of acquired and genetic epilepsy

Casillas‐Espinosa

Sargsyan²,

Melkonian³

et al. 2019

Epilepsia

View full text Add to dashboard Cite

show abstract

“…By the end of the sixth month post-TBI, 27% of the rats had developed epilepsy, with an average seizure duration of about 1.5 minutes and a mean seizure frequency of 0.2/ day. 30,30 Previous studies in humans suggest that the severity of TBI scored using the Glasgow Coma Scale is a major risk factor for posttraumatic epileptogenesis. 4,5 In the present study, the lateral FPI-induced impact force varied between 3.09 and 3.43 atm in the TBI+ and 3.03-3.44 in TBI− groups, suggesting that there could be some variability in the severity of TBI.…”

Section: Discussionmentioning

confidence: 99%

Postinjury weight rather than cognitive or behavioral impairment predicts development of posttraumatic epilepsy after lateral fluid‐percussion injury in rats

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…and FBTCS showed a sustained increase in 32-64Hz. The peak changes in theta band (4)(5)(6)(7)(8) were seen around 26-31 seconds after seizure onset in the cortex. Also, we observed a decrease in MSE, implying that the degree of randomness of the thalamic neural activity reduced during the time of the seizures.…”

Section: Line Length (Ll) Detection Latencies and Spectral Changes Ofmentioning

confidence: 97%

“…Second, automated detectors allow quantifying seizures and circadian patterns for an electronic seizure diary that can be used to tailor therapy [4]. Third, in research, large scale automation of seizure counts can accelerate drug development and evaluate therapy responses [5] [6]. Given these translational significances, there is a continuous development of algorithms based on either machine learning or deep learning.…”

Section: Introductionmentioning

confidence: 99%

Reliable detection of focal-onset seizures in the human anterior nucleus of the thalamus using non-linear machine learning

Tóth

Kumar

Chaitanya

et al. 2020

Preprint

View full text Add to dashboard Cite

Objective: There is an unmet need to develop seizure detection algorithms from brain regions outside the epileptogenic cortex. The study aimed to demonstrate the feasibility of classifying seizures and interictal states from local field potentials (LFPs) recorded from the human thalamus- a subcortical region remote to the epileptogenic cortex. We tested the hypothesis that spectral and entropy-based features extracted from LFPs recorded from the anterior nucleus of the thalamus (ANT) can distinguish its state of ictal recruitment from other interictal states (including awake, sleep). Approach: Two supervised machine learning tools (random forest and the random kitchen sink) were used to evaluate the performance of spectral (discrete wavelet transform-DWT), and time-domain (multiscale entropy-MSE) features in classifying seizures from interictal states in patients undergoing stereo EEG evaluation for epilepsy surgery. Under the supervision of IRB, field potentials were recorded from the ANT in consenting adults with drug-resistant temporal lobe epilepsy. Seizures were confirmed in the ANT using line-length and visual inspection. Wilcoxon rank-sum (WRS) method was used to test the differences in spectral patterns between seizure and interictal (awake and sleep) states. Main Results: 79 seizures (10 patients) and 158 segments (approx. 4 hours) of interictal stereo EEG data were analyzed. The mean seizure detection latencies with line length in the ANT varied between seizure types (range 5-34 seconds). However, the DWT and MSE in the ANT showed significant changes for all seizure types within the first 20 seconds after seizure onset. The random forest (accuracy 93.9 % and false-positive 4.6%) and the random kitchen sink (accuracy 97.3% and false-positive 1.8%) classified seizures and interictal states. Significance: These results suggest that features extracted from the thalamic LFPs can be trained to detect seizures that can be used for monitoring seizure counts and for closed-loop seizure abortive interventions.

show abstract

Algorithm for automatic detection of spontaneous seizures in rats with post-traumatic epilepsy

Abstract: We present a novel seizure detection algorithm for automated detection of seizures in a rat model of post-traumatic epilepsy.

Cited by 19 publications

References 25 publications

A universal automated tool for reliable detection of seizures in rodent models of acquired and genetic epilepsy

A universal automated tool for reliable detection of seizures in rodent models of acquired and genetic epilepsy

Postinjury weight rather than cognitive or behavioral impairment predicts development of posttraumatic epilepsy after lateral fluid‐percussion injury in rats

Reliable detection of focal-onset seizures in the human anterior nucleus of the thalamus using non-linear machine learning

Contact Info

Product

Resources

About