Kwan, Patrick

Artificial intelligence, machine learning, and deep learning are increasingly being used in all medical fields including for epilepsy research and clinical care. Already there have been resultant cutting-edge applications in both the clinical and research arenas of epileptology. Because there is a need to disseminate knowledge about these approaches, how to use them, their advantages, and their potential limitations, the goal of the 2023 Merritt-Putnam Symposium and of this synopsis review of that symposium has been to present the background and state of the art and then to draw conclusions on current and future applications of these approaches through the following: (1) Initially provide an explanation of the fundamental principles of artificial intelligence, machine learning, and deep learning. These are presented in the first section of this review by Dr Wesley Kerr. (2) Provide insights into their cutting-edge applications in screening for medications in neural organoids, in general, and for epilepsy in particular. These are presented by Dr Sandra Acosta. (3) Provide insights into how artificial intelligence approaches can predict clinical response to medication treatments. These are presented by Dr Patrick Kwan. (4) Finally, provide insights into the expanding applications to the detection and analysis of EEG signals in intensive care, epilepsy monitoring unit, and intracranial monitoring situations, as presented below by Dr Gregory Worrell. The expectation is that, in the coming decade and beyond, the increasing use of the above approaches will transform epilepsy research and care and supplement, but not replace, the diligent work of epilepsy clinicians and researchers.

Abstract Aims The causes of distinct patterns of reduced cortical thickness in the common human epilepsies, detectable on neuroimaging and with important clinical consequences, are unknown. We investigated the underlying mechanisms of cortical thinning using a systems‐level analysis. Methods Imaging‐based cortical structural maps from a large‐scale epilepsy neuroimaging study were overlaid with highly spatially resolved human brain gene expression data from the Allen Human Brain Atlas. Cell‐type deconvolution, differential expression analysis and cell‐type enrichment analyses were used to identify differences in cell‐type distribution. These differences were followed up in post‐mortem brain tissue from humans with epilepsy using Iba1 immunolabelling. Furthermore, to investigate a causal effect in cortical thinning, cell‐type‐specific depletion was used in a murine model of acquired epilepsy. Results We identified elevated fractions of microglia and endothelial cells in regions of reduced cortical thickness. Differentially expressed genes showed enrichment for microglial markers and, in particular, activated microglial states. Analysis of post‐mortem brain tissue from humans with epilepsy confirmed excess activated microglia. In the murine model, transient depletion of activated microglia during the early phase of the disease development prevented cortical thinning and neuronal cell loss in the temporal cortex. Although the development of chronic seizures was unaffected, the epileptic mice with early depletion of activated microglia did not develop deficits in a non‐spatial memory test seen in epileptic mice not depleted of microglia. Conclusions These convergent data strongly implicate activated microglia in cortical thinning, representing a new dimension for concern and disease modification in the epilepsies, potentially distinct from seizure control.

SummaryObjectiveTo evaluate safety, tolerability, seizure frequency, and regional variations in treatment responses with the AMPA antagonist, perampanel, in a large extension study during up to 3 years of treatment.MethodsPatients ≥12 years old with partial‐onset seizures despite treatment with 1–3 antiepileptic drugs at baseline completed a perampanel phase III trial and entered extension study 307 (NCT00735397). Patients were titrated to 12 mg/day (or their individual maximum tolerated dose) during the blinded conversion period, followed by open‐label maintenance. Exposure, safety (adverse events [AEs], vital signs, weight, electrocardiography [ECG], laboratory values) and seizure outcomes were analyzed; key measures were assessed by geographic regions.ResultsAmong 1,216 patients, median exposure was 1.5 years (range 1 week to 3.3 years), with >300 patients treated for >2 years. Treatment retention was 58.5% at cutoff. AEs reported in ≥10% of patients were dizziness, somnolence, headache, fatigue, irritability, and weight increase. Only dizziness and irritability caused discontinuation in >1% of patients (3.9% and 1.3%, respectively). The only serious AEs reported in >1% of patients were epilepsy‐related (convulsion, 3.0%; status epilepticus, 1.1%). No clinically relevant changes in vital signs, ECG or laboratory parameters were seen. After titration/conversion, responder rate and median percentage change from baseline in seizure frequency were stable: 46% for both measures at 9 months (in 980 patients with ≥9 months' exposure) and 58% and 60%, respectively, at 2 years (in the 337 patients with 2 years' exposure). Median percentage reduction in frequency of secondarily generalized (SG) seizures ranged from 77% at 9 months (N = 422) to 90% at 2 years (N = 141). Among the 694 patients with maintenance data ≥1 year, 5.3% were seizure‐free for the entire year.SignificanceNo new safety signals emerged during up to 3 years of perampanel exposure in 39 countries. Seizure responses remained stable, with marked reductions, particularly in SG seizures.A PowerPoint slide summarizing this article is available for download in the Supporting Information section here.

SummaryObjectiveTo better understand the relationship between efficacy and perampanel dose, integrated actual (last) dose data from three phase III trials and an extension study (blinded Conversion Period; open‐label Maintenance Period) were analyzed.MethodsSeizure frequency data were analyzed in patients who were randomized to and completed the 13‐week Maintenance Period of the phase III studies on perampanel 8 mg, and who received an actual (last) dose of 12 mg during (1) the extension 16‐week blinded Conversion Period or (2) weeks 1–13 of the extension Maintenance Period. Due to a treatment‐by‐region interaction (p = 0.042), analyses excluded patients from the Latin America region (n = 162/1,480; 10.9% of the treated cohort).ResultsOf 372 patients randomized to 8 mg in the phase III studies, 273 completed the Maintenance Period at 8 mg and 267 entered the extension study. In patients who then had an actual (last) dose of 12 mg during the extension blinded Conversion Period (n = 217), median percent change in seizure frequency per 28 days improved from −32.4% (8 mg, phase III Maintenance Period) to −44.2% (12 mg, extension blinded Conversion Period); 50% responder rates increased slightly from 37.3% to 42.9%. In patients who completed the phase III studies on 8 mg and had an actual (last) dose of 12 mg during weeks 1–13 of the extension Maintenance Period (n = 181), median percent change in seizure frequency per 28 days improved from −34.1% (phase III Maintenance Period) to −46.0% (weeks 1–13 extension Maintenance Period); 50% responder rates were 39.2% and 46.4%. Seizure control remained substantially unchanged in patients who completed the phase III studies at 12 mg and continued on that dose during the extension.SignificanceIncreasing perampanel dose from 8 to 12 mg can produce additional benefits in seizure control in at least some patients who tolerate the higher dose.