Forecasting Seizures in Dogs with Naturally Occurring Epilepsy

Abstract

Seizure forecasting has the potential to create new therapeutic strategies for epilepsy, such as providing patient warnings and delivering preemptive therapy. Progress on seizure forecasting, however, has been hindered by lack of sufficient data to rigorously evaluate the hypothesis that seizures are preceded by physiological changes, and are not simply random events. We investigated seizure forecasting in three dogs with naturally occurring focal epilepsy implanted with a device recording continuous intracranial EEG (iEEG). The iEEG spectral power in six frequency bands: delta (0.1–4 Hz), theta (4–8 Hz), alpha (8–12 Hz), beta (12–30 Hz), low-gamma (30–70 Hz), and high-gamma (70–180 Hz), were used as features. Logistic regression classifiers were trained to discriminate labeled pre-ictal and inter-ictal data segments using combinations of the band spectral power features. Performance was assessed on separate test data sets via 10-fold cross-validation. A total of 125 spontaneous seizures were detected in continuous iEEG recordings spanning 6.5 to 15 months from 3 dogs. When considering all seizures, the seizure forecasting algorithm performed significantly better than a Poisson-model chance predictor constrained to have the same time in warning for all 3 dogs over a range of total warning times. Seizure clusters were observed in all 3 dogs, and when the effect of seizure clusters was decreased by considering the subset of seizures separated by at least 4 hours, the forecasting performance remained better than chance for a subset of algorithm parameters. These results demonstrate that seizures in canine epilepsy are not randomly occurring events, and highlight the feasibility of long-term seizure forecasting using iEEG monitoring.

Towards Improved Design and Evaluation of Epileptic Seizure Predictors

“…The contestants used a variety of machine learning models applied to a wide range of features from the time and frequency domains. The general approach, however, was much the same as in many previous studies, confirming that spectral power in discrete frequency bands is a valuable feature for seizure forecasting [5], [6], [11]. Moreover, SVM [12] was the most commonly used algorithm, which follows the trends in the seizure prediction research community [13].…”

“…Likely, this is the reason why many works cease to compare their approaches against the existing methods [4], [5], [11]. In this paper, we tried to fill this evaluation gap by benchmarking two common classifiers, namely LDA and SVM, against our novel CNN approach on a dataset available in the Kaggle Seizure Prediction Challenge [8].…”

“…Simple features from the frequency domain have been shown to be discriminative between preictal and interictal states [5], [11]. We further expanded upon these ideas, so firstly, the 10 minute clips were resampled to 400 Hz and filtered with a band-pass filter between 0.1 and 180 Hz.…”

“…Recently, several datasets of long-term intracranial EEG (iEEG) recordings from canine subjects have become available and found their usage in a few studies [5], [6]. The reason behind exploiting canine data is that epilepsy in dogs and humans is proven to be highly similar [7] and it is easier to obtain relatively long iEEG recordings from canines.…”

Dismantling standard cognitive science: it’s time the dog has its day

“…I will attempt to navigate this perilous dichotomy by noting carefully what the particular umwelt-or 'lifeworld'-of the dog is and why that ecological niche likely implies a different type of cognitive process. As Horowitz (2010) has argued, canine science needs to be sensitive to the specific umwelt of dogs, but it must also recognize that this umwelt always already involves human interaction. In line with this tension, therefore, I will discuss at various points throughout the paper what I think are limits to particular studies in terms of extrapolating a 'canid-centric' account of cognition.…”