Seizure and social outcomes in patients with non-surgically treated temporal lobe epilepsy

OxcarNet: sinc convolutional network with temporal and channel attention for prediction of oxcarbazepine monotherapy responses in patients with newly diagnosed epilepsy

Objective.Monotherapy with antiepileptic drugs (AEDs) is the preferred strategy for the initial treatment of epilepsy. However, an inadequate response to the initially prescribed AED is a significant indicator of a poor long-term prognosis, emphasizing the importance of precise prediction of treatment outcomes with the initial AED regimen in patients with epilepsy.Approach. We introduce OxcarNet, an end-to-end neural network framework developed to predict treatment outcomes in patients undergoing oxcarbazepine monotherapy. The proposed predictive model adopts a Sinc Module in its initial layers for adaptive identification of discriminative frequency bands. The derived feature maps are then processed through a Spatial Module, which characterizes the scalp distribution patterns of the electroencephalography (EEG) signals. Subsequently, these features are fed into an attention-enhanced Temporal Module to capture temporal dynamics and discrepancies. A channel module with an attention mechanism is employed to reveal inter-channel dependencies within the output of the Temporal Module, ultimately achieving response prediction. OxcarNet was rigorously evaluated using a proprietary dataset of retrospectively collected EEG data from newly diagnosed epilepsy patients at Nanjing Drum Tower Hospital. This dataset included patients who underwent long-term EEG monitoring in a clinical inpatient setting.Main results.OxcarNet demonstrated exceptional accuracy in predicting treatment outcomes for patients undergoing Oxcarbazepine monotherapy. In the ten-fold cross-validation, the model achieved an accuracy of 97.27%, and in the validation involving unseen patient data, it maintained an accuracy of 89.17%, outperforming six conventional machine learning methods and three generic neural decoding networks. These findings underscore the model's effectiveness in accurately predicting the treatment responses in patients with newly diagnosed epilepsy. The analysis of features extracted by the Sinc filters revealed a predominant concentration of predictive frequencies in the high-frequency range of the gamma band.Significance. The findings of our study offer substantial support and new insights into tailoring early AED selection, enhancing the prediction accuracy for the responses of AEDs.

Is the left hemisphere more prone to epilepsy and poor prognosis than the right hemisphere?

Objective: The central nervous system is known to have asymmetric immune system modulation. Thus far, no clinical study has examined asymmetric immune modulation between hemispheres in focal epilepsy patients. We aimed to compare the prognosis of epilepsy patients lateralized to the right hemisphere with epilepsy patients lateralized to the left hemisphere using clinic and demographic data.Method: Ninety-nine patients with focal epilepsy with all seizures originating in only one hemisphere, between the ages of 18-and 86 years were included. We included patients with focal epilepsy whose seizures were lateralized to only one hemisphere. Age, gender, marital status, education, mental retardation, hand dominance, etiology, trauma, central nervous system infection, febrile convulsion, parental relationships, seizure onset age, seizure frequency (per month), systemic disease, and biochemical parameters were recorded. To evaluate lateralization, we used positron emission tomography (PET/CT), long-term video-electroencephalography (EEG), and magnetic resonance imaging (MRI) investigations.Results: Thirty-seven patients (37.4%) patients were right-lateralized, whereas 62 patients (62.6%) were left-lateralized (p = 0.01). Seizures frequency seizures were higher in patients lateralized to the left hemisphere than in the right. (p = 0.001). In patients with epilepsy lateralized to the left hemisphere, epilepsy onset age was lower (p = 0.003), numbers of antiepileptic medicines were higher (p = 0.04), and epilepsy durations and longest seizure-free periods were longer (p = 0.001 and p = 0.04, respectively).Conclusion: We have shown that compared to the right hemisphere, the left hemisphere is far more prone to seizures and has a poorer prognosis.

Early identification of seizure freedom with medical treatment in patients with mesial temporal lobe epilepsy and hippocampal sclerosis

BACKGROUND

Mesial temporal lobe epilepsy with hippocampal sclerosis (MTLE-HS) is usually associated with a poor response to antiseizure medications. We focused on MTLE-HS patients who were seizure free on medication to: (1) determine the clinical factors associated with seizure freedom and (2) develop a machine-learning classifier to better earlier identify those patients.

METHODS

We performed a retrospective, multicentric study comparing 64 medically treated seizure-free MTLE-HS patients with 200 surgically treated drug-resistant MTLE-HS patients. First, we collected medical history and seizure semiology data. Then, we developed a machine-learning classifier based on clinical data.

RESULTS

Medically treated seizure-free MTLE-HS patients were seizure-free for at least 2 years, and for a median time of 7 years at last follow-up. Compared to drug-resistant MTLE-HS patients, they exhibited: an older age at epilepsy onset (22.5 vs 8.0 years, p < 0.001), a lesser rate of: febrile seizures (39.0% vs 57.5%, p = 0.035), focal aware seizures (previously referred to as aura)(56.7% vs 90.0%, p < 0.001), autonomic focal aware seizures in presence of focal aware seizure (17.6% vs 59.4%, p < 0.001), dystonic posturing of the limbs (9.8% vs 47.0%, p < 0.001), gestural (27.4% vs 94.0%, p < 0.001), oro-alimentary (32.3% vs 75.5%, p < 0.001) or verbal automatisms (12.9% vs 36.0%, p = 0.001). The classifier had a positive predictive value of 0.889, a sensitivity of 0.727, a specificity of 0.962, a negative predictive value of 0.893.

CONCLUSIONS

Medically treated seizure-free MTLE-HS patients exhibit a distinct clinical profile. A classifier built with readily available clinical data can identify them accurately with excellent positive predictive value. This may help to individualize the management of MTLE-HS patients according to their expected pharmacosensitivity.

Optimization of closed-loop electrical stimulation enables robust cerebellar-directed seizure control

Additional treatment options for temporal lobe epilepsy are needed, and potential interventions targeting the cerebellum are of interest. Previous animal work has shown strong inhibition of hippocampal seizures through on-demand optogenetic manipulation of the cerebellum. However, decades of work examining electrical stimulation-a more immediately translatable approach-targeting the cerebellum has produced very mixed results. We were therefore interested in exploring the impact that stimulation parameters may have on seizure outcomes. Using a mouse model of temporal lobe epilepsy, we conducted on-demand electrical stimulation of the cerebellar cortex, and varied stimulation charge, frequency and pulse width, resulting in over 1000 different potential combinations of settings. To explore this parameter space in an efficient, data-driven, manner, we utilized Bayesian optimization with Gaussian process regression, implemented in MATLAB with an Expected Improvement Plus acquisition function. We examined three different fitting conditions and two different electrode orientations. Following the optimization process, we conducted additional on-demand experiments to test the effectiveness of selected settings. Regardless of experimental setup, we found that Bayesian optimization allowed identification of effective intervention settings. Additionally, generally similar optimal settings were identified across animals, suggesting that personalized optimization may not always be necessary. While optimal settings were effective, stimulation with settings predicted from the Gaussian process regression to be ineffective failed to provide seizure control. Taken together, our results provide a blueprint for exploration of a large parameter space for seizure control and illustrate that robust inhibition of seizures can be achieved with electrical stimulation of the cerebellum, but only if the correct stimulation parameters are used.