Antiseizure medication withdrawal in adult patients with idiopathic generalized epilepsy: Performance of two seizure recurrence prediction models

PURPOSE

Currently, there is a limited availability of tools to predict seizure recurrence after discontinuation of antiseizure medications (ASMs). This study aimed to establish the seizure recurrence rate following ASM cessation in adult patients with idiopathic generalized epilepsy (IGE) and to assess the predictive performance of the Lamberink and the Stevelink prediction models using real-world data.

METHODS

Retrospective longitudinal study in IGE patients who underwent ASM withdrawal in a tertiary epilepsy clinic since June 2011, with the latest follow up in January 2024. The minimum follow-up period was 12 months. Clinical and demographic variables were collected, and the seizure recurrence prediction models proposed by Lamberink and Stevelink were applied and evaluated.

RESULTS

Forty-seven patients (mean age 33.15 ± 8 [20-55] years; 72.35 % women) were included. During the follow-up period, seizures recurred in 25 patients (53.2 %). Median time to recurrence was 8 months [IQR 3-13.5 months], and 17 patients (68 %) relapsed within the first year. None of the relapsing patients developed drug-resistant epilepsy. The only significant risk factor associated with recurrence was a seizure-free period of less than 2 years before discontinuing medication (91.7 % vs 40 %, p =.005). The Stevelink prediction model at both 2 (p =.015) and 5 years (p =.020) achieved statistical significance, with an AUC of 0.72 (95 % CI 0.56-0.88), while the Lamberink model showed inadequate prognostic capability.

CONCLUSION

In our real-world cohort, a seizure-free period of at least 2 years was the only factor significantly associated with epilepsy remission after ASM withdrawal. Larger studies are needed to accurately predict seizure recurrence in IGE patients.

Prediction of antiepileptic drug treatment outcomes of patients with newly diagnosed epilepsy by machine learning

OBJECTIVE

The objective of this study was to build a supervised machine learning-based classifier, which can accurately predict the outcomes of antiepileptic drug (AED) treatment of patients with newly diagnosed epilepsy.

METHODS

We collected information from 287 patients with newly diagnosed epilepsy between 2009 and 2017 at the Second Affiliated Hospital of Zhejiang University. Patients were prospectively followed up for at least 3 years. A number of features, including demographic features, medical history, and auxiliary examinations (electroencephalogram [EEG] and magnetic resonance imaging [MRI]) are selected to distinguish patients with different remission outcomes. Seizure outcomes classified as remission and never remission. In addition, remission is further divided into early remission and late remission. Five classical machine learning algorithms, i.e., Decision Tree, Random Forest, Support Vector Machine, XGBoost, and Logistic Regression, are selected and trained by our dataset to get classification models.

RESULTS

Our study shows that 1) compared with the other four algorithms, the XGBoost algorithm based machine learning model achieves the best prediction performance of the AED treatment outcomes between remission and never remission patients with an F1 score of 0.947 and an area under the curve (AUC) value of 0.979; 2) The best discriminative factor for remission and never remission patients is higher number of seizures before treatment (>3); 3) XGBoost-based machine learning model also offers the best prediction between early remission and later remission patients, with an F1 score of 0.836 and an AUC value of 0.918; 4) multiple seizure type has the highest dependence to the categories of early and late remission patients.

SIGNIFICANCES

Our XGBoost-based machine learning classifier accurately predicts the most probable AED treatment outcome of a patient after he/she finishes all the standard examinations for the epilepsy disease. The classifier's prediction result could help disease guide counseling and eventually improve treatment strategies.

A prospective observational longitudinal study of new-onset seizures and newly diagnosed epilepsy in dogs

Background

Seizures are common in dogs and can be caused by non-epileptic conditions or epilepsy. The clinical course of newly diagnosed epilepsy is sparsely documented.

The objective of this study was to prospectively investigate causes for seizures (epileptic and non-epileptic) in a cohort of dogs with new-onset untreated seizures, and for those dogs with newly diagnosed epilepsy to investigate epilepsy type, seizure type and the course of disease over time, including the risk of seizure recurrence. Untreated client-owned dogs experiencing new-onset seizures were prospectively enrolled in a longitudinal observational study including clinical investigations and long-term monitoring at the Copenhagen University Hospital for Companion Animals. A baseline clinical assessment was followed by investigator/owner contact every eight weeks from inclusion to death or end of study. Inclusion of dogs was conducted from November 2010 to September 2012, and the study terminated in June 2014.

Results

One hundred and six dogs were included in the study. Seventy-nine dogs (74.5%) were diagnosed with epilepsy: 61 dogs (77.2%) with idiopathic epilepsy, 13 dogs (16.5%) with structural epilepsy and five dogs (6.3%) with suspected structural epilepsy. A non-epileptic cause for seizures was identified in 13 dogs and suspected in 10 dogs. Four dogs in which no cause for seizures was identified experienced only one seizure during the study. In dogs with idiopathic epilepsy 60% had their second epileptic seizure within three months of seizure onset. Twenty-six dogs with idiopathic epilepsy (43%) completed the study without receiving antiepileptic treatment. The natural course of idiopathic epilepsy (uninfluenced by drugs) was illustrated by highly individual and fluctuating seizure patterns, including long periods of remission. Cluster seizures motivated early treatment. In a few dogs with a high seizure frequency owners declined treatment against the investigators advice.

Conclusions

Epilepsy is the most likely diagnosis in dogs presenting with new-onset seizures. The course of idiopathic epilepsy is highly individual and might not necessarily require long-term treatment. This must be considered when advising owners about what to expect with regard to treatment and prognosis.

Cerebral white matter integrity in children with active versus remitted epilepsy 5 years after diagnosis

INTRODUCTION

Diffusion tensor imaging (DTI) studies have reported white matter abnormalities in childhood-onset epilepsy, but the mechanisms and timing underlying these abnormalities, and their resolution, are not well understood. This study examined white matter integrity in children with active versus remitted epilepsy.

METHODS

Tract-based spatial statistics (TBSS) was used to examine whole-brain DTI indices of fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD) and radial diffusivity (RD) in 20 children with epilepsy 5-6 years after diagnosis, compared to 29 healthy controls. To determine the status of white matter following cessation of seizures, participants with epilepsy were classified as active versus remitted and comparisons included: (1) controls versus all children with epilepsy, (2) controls versus children with remitted seizures, (3) controls versus children with active seizures, and (4) children with active versus remitted epilepsy.

RESULTS

In the active compared to remitted epilepsy group, significantly higher FA and lower MD, AD and RD values were dispersed in the internal capsule, cingulum, body of the corpus callosum, superior corona radiata and superior fronto-occipital fasciculus. Similar differences were found between the active epilepsy and the control group. There were no significant differences between the remitted epilepsy and control groups.

CONCLUSION

Children with active epilepsy differed in white matter integrity compared to children with remitted epilepsy and healthy controls. It remains to be determined whether these findings represent the outcomes of seizure remission versus an initial biomarker for those children who will ultimately have intractable epilepsy.