Graeme D. Jackson

A 25-year-old construction worker presented with “dizzy spells” triggered by actual motion (using escalators or waterslides, eyes open or closed) or perceived movement (watching first-person roller coaster videos). He experiences a sensation of falling backwards, remains aware, and extends his arms as if to keep balance. Scalp video-EEG of 32 stereotyped events confirmed they were focal seizures with a subtle ictal rhythm over the midline centroparietal region. MRI brain and FDG-PET were negative. Ictal SPECT, using a tilting chair to trigger a typical event, showed right medial parietal hyperperfusion

A leading cause of surgically remediable, drug-resistant focal epilepsy is focal cortical dysplasia (FCD). FCD is challenging to visualize and often considered magnetic resonance imaging (MRI) negative. Existing automated methods for FCD detection are limited by high numbers of false-positive predictions, hampering their clinical utility. To evaluate the efficacy and interpretability of graph neural networks in automatically detecting FCD lesions on MRI scans. In this multicenter diagnostic study, retrospective MRI data were collated from 23 epilepsy centers worldwide between 2018 and 2022, as part of the Multicenter Epilepsy Lesion Detection (MELD) Project, and analyzed in 2023. Data from 20 centers were split equally into training and testing cohorts, with data from 3 centers withheld for site-independent testing. A graph neural network (MELD Graph) was trained to identify FCD on surface-based features. Network performance was compared with an existing algorithm. Feature analysis, saliencies, and confidence scores were used to interpret network predictions. In total, 34 surface-based MRI features and manual lesion masks were collated from participants, 703 patients with FCD-related epilepsy and 482 controls, and 57 participants were excluded during MRI quality control. Sensitivity, specificity, and positive predictive value (PPV) of automatically identified lesions. In the test dataset, the MELD Graph had a sensitivity of 81.6% in histopathologically confirmed patients seizure-free 1 year after surgery and 63.7% in MRI-negative patients with FCD. The PPV of putative lesions from the 260 patients in the test dataset (125 female [48%] and 135 male [52%]; mean age, 18.0 [IQR, 11.0-29.0] years) was 67% (70% sensitivity; 60% specificity), compared with 39% (67% sensitivity; 54% specificity) using an existing baseline algorithm. In the independent test cohort (116 patients; 62 female [53%] and 54 male [47%]; mean age, 22.5 [IQR, 13.5-27.5] years), the PPV was 76% (72% sensitivity; 56% specificity), compared with 46% (77% sensitivity; 47% specificity) using the baseline algorithm. Interpretable reports characterize lesion location, size, confidence, and salient features. In this study, the MELD Graph represented a state-of-the-art, openly available, and interpretable tool for FCD detection on MRI scans with significant improvements in PPV. Its clinical implementation holds promise for early diagnosis and improved management of focal epilepsy, potentially leading to better patient outcomes.

A 22-year-old female presented with drug-resistant focal motor seizures with onset at age 14. This manifested as daily episodes of right facial dystonia triggered by toothbrushing, but also by eating, talking, and strenuous exercise. On ictal scalp EEG, there was low-voltage fast activity over the left pericentral area. Structural MRI did not identify a definite lesion. Functional MRI (fMRI) of a reflex seizure, as well as task-based fMRI during toothbrushing, both demonstrated focal activation at the left low pericentral cortex. Stereoelectroencephalography (sEEG) showed recurrent ictal trains of focal spiking concordant with the fMRI activation. Radiofrequency (RF) thermocoagulation was applied at the posterior bank of the left low pre-central gyrus, with post-operative MRI confirming small ablative lesions immediately deep to the ictal fMRI activation, and the patient remains seizure-free more than 3 years after this treatment. Toothbrushing epilepsy is a rare form of reflex epilepsy where seizures are induced by toothbrushing. In this unique case, ictal fMRI assisted targeting of the sEEG implantation, to confirm seizure onset and enable minimally invasive treatment via RF thermocoagulation, resulting in seizure freedom.

Epilepsy is recognised as one of the leading targets for precision medicine, following on from the successes in cancer therapy, due to its substantial clinical heterogeneity and divergent therapeutic options. To bring personalised care to the epilepsies, there is a need for appropriate precision biomarkers that can identify disease processes or predict treatment outcomes at the individual patient level. Neuroimaging techniques, including magnetic resonance imaging (MRI), have been transformative for clinical practice, particularly in medically refractory focal epilepsies. Advanced MRI techniques have the potential to bring precision medicine clearly into view for epileptology; however, there are challenges that must be overcome before cutting-edge neuroimaging tools can be used in clinical practice. In this Review article, we communicate our view that implementation of normative modelling frameworks will help to deliver robust quantitative MRI biomarkers for individualized prediction. Here, we provide recommendations for researchers and clinicians alike, from careful research design to clinical applications, that will help to identify diagnostic and predictive imaging biomarkers. Such precision markers will be key to delivering personalised medicine for the epilepsies.

Objective: To examine the neuropsychological morbidity across the spectrum of patients presenting to a First Seizure Clinic, and test the hypothesis that cognitive and psychological compromise is especially prominent in those diagnosed with epilepsy. Methods: A sample of 201 patients referred to the Austin Hospital First Seizure Clinic (FSC) underwent cognitive screening via telephone and psychological screening via online questionnaire, all prior to their diagnostic evaluation (and any attendant treatment recommendation) at the FSC. Rates of cognitive (i.e., scores <10th percentile) and psychological impairment (using established clinical cut scores) were compared against 35 demographically matched controls. Cognitive differences were explored between the most frequently encountered patient subgroups (epilepsy, n = 48; first unprovoked seizure, n = 24; acute symptomatic seizure, n = 24; syncope, n = 35) via a multivariate analysis of variance, with diagnostic labels applied retrospectively after a period of follow-up. Results: People with epilepsy were most likely to show cognitive impairments, particularly in learning and memory, with performances worse than all other FSC groups (F [3127] = 2.44, p = 0.03). Clinically significant depressive symptoms were similarly prevalent in all patient groups, with one in three at risk for Major Depressive Disorder. Elevated anxiety symptoms were common across patient groups; however, not significantly different to controls. Conclusions: Cognitive impairment in epilepsy and mood problems in all FSC groups are detectable via remote screening as early as the first seizure. Learning and memory difficulties are particularly prevalent in new-onset epilepsy and may lend diagnostic information when paired with clinical factors. Conclusions: This study explored cognitive and psychological differences between various patient groups attending an Australian First Seizure Clinic. We found that learning and memory abilities were poorer in people with epilepsy than other patient groups including those with non-epileptic seizures, and seizure-mimics (fainting episodes). Therefore, along with standard epilepsy investigations, memory performances could help to predict which patients have epilepsy versus a non-epileptic condition after a first suspected seizure. Further, approximately one in three from each patient group showed high symptoms of depression and anxiety. The findings highlight the importance of evaluating cognition and mood in people with first seizures.