Artificial intelligence in epilepsy phenotyping

Artificial Intelligence in Pediatric Epilepsy Detection: Balancing Effectiveness With Ethical Considerations for Welfare

BACKGROUND AND AIM

Epilepsy is a major neurological challenge, especially for pediatric populations. It profoundly impacts both developmental progress and quality of life in affected children. With the advent of artificial intelligence (AI), there's a growing interest in leveraging its capabilities to improve the diagnosis and management of pediatric epilepsy. This review aims to assess the effectiveness of AI in pediatric epilepsy detection while considering the ethical implications surrounding its implementation.

METHODOLOGY

A comprehensive systematic review was conducted across multiple databases including PubMed, EMBASE, Google Scholar, Scopus, and Medline. Search terms encompassed "pediatric epilepsy," "artificial intelligence," "machine learning," "ethical considerations," and "data security." Publications from the past decade were scrutinized for methodological rigor, with a focus on studies evaluating AI's efficacy in pediatric epilepsy detection and management.

RESULTS

AI systems have demonstrated strong potential in diagnosing and monitoring pediatric epilepsy, often matching clinical accuracy. For example, AI-driven decision support achieved 93.4% accuracy in diagnosis, closely aligning with expert assessments. Specific methods, like EEG-based AI for detecting interictal discharges, showed high specificity (93.33%-96.67%) and sensitivity (76.67%-93.33%), while neuroimaging approaches using rs-fMRI and DTI reached up to 97.5% accuracy in identifying microstructural abnormalities. Deep learning models, such as CNN-LSTM, have also enhanced seizure detection from video by capturing subtle movement and expression cues. Non-EEG sensor-based methods effectively identified nocturnal seizures, offering promising support for pediatric care. However, ethical considerations around privacy, data security, and model bias remain crucial for responsible AI integration.

CONCLUSION

While AI holds immense potential to enhance pediatric epilepsy management, ethical considerations surrounding transparency, fairness, and data security must be rigorously addressed. Collaborative efforts among stakeholders are imperative to navigate these ethical challenges effectively, ensuring responsible AI integration and optimizing patient outcomes in pediatric epilepsy care.

Quantitative EEG Spectral Features Differentiate Genetic Epilepsies and Predict Neurologic Outcomes

EEG plays an integral part in the diagnosis and management of children with genetic epilepsies. Nevertheless, how quantitative EEG features differ between genetic epilepsies and neurological outcomes remains largely unknown. Here, we aimed to identify quantitative EEG biomarkers in children with epilepsy and a genetic diagnosis in STXBP1, SCN1A, or SYNGAP1, and to assess how quantitative EEG features associate with neurological outcomes in genetic epilepsies more broadly. We analyzed individuals with pathogenic variants in STXBP1 (95 EEGs, n=20), SCN1A (154 EEGs, n=68), and SYNGAP1 (46 EEGs, n=21) and a control cohort of individuals without epilepsy or known cerebral disease (847 EEGs, n=806). After removing artifacts and epochs with excess noise or altered state from EEGs, we extracted spectral features. We validated our preprocessing pipeline by comparing automatically-detected posterior dominant rhythm (PDR) to annotations from clinical EEG reports. Next, as a coarse measure of pathological slowing, we compared the alpha-delta bandpower ratio between controls and the different genetic epilepsies. We then trained random forest models to predict a diagnosis of STXBP1, SCN1A, and SYNGAP1. Finally, to understand how EEG features vary with neurological outcomes, we trained random forest models to predict seizure frequency and motor function. There was strong agreement between the automatically-calculated PDR and clinical EEG reports (R 2=0.75). Individuals with STXBP1-related epilepsy have a significantly lower alpha-delta ratio than controls (P<0.001) across all age groups. Additionally, individuals with a missense variant in STXBP1 have a significantly lower alpha-delta ratio than those with a protein-truncating variant in toddlers (P<0.001), children (P=0.02), and adults (P<0.001). Models accurately predicted a diagnosis of STXBP1 (AUC=0.91), SYNGAP1 (AUC=0.82), and SCN1A (AUC=0.86) against controls and from each other in a three-class model (accuracy=0.74). From these models, we isolated highly correlated biomarkers for these respective genetic disorders, including alpha-theta ratio in frontal, occipital, and parietal electrodes with STXBP1, SYNGAP1, and SCN1A, respectively. Models were unable to predict seizure frequency (AUC=0.53). Random forest models predicted motor scores significantly better than age-based null models (P<0.001), suggesting spectral features contain information pertinent to gross motor function. In summary, we demonstrate that STXBP1-, SYNGAP1-, and SCN1A-related epilepsies have distinct quantitative EEG signatures. Furthermore, EEG spectral features are predictive of some functional outcome measures in patients with genetic epilepsies. Large-scale retrospective quantitative analysis of clinical EEG has the potential to discover novel biomarkers and to quantify and track individuals' disease progression across development.

Visual detection of seizures in mice using supervised machine learning

Seizures are caused by abnormally synchronous brain activity that can result in changes in muscle tone, such as twitching, stiffness, limpness, or rhythmic jerking. These behavioral manifestations are clear on visual inspection and the most widely used seizure scoring systems in preclinical models, such as the Racine scale in rodents, use these behavioral patterns in semiquantitative seizure intensity scores. However, visual inspection is time-consuming, low-throughput, and partially subjective, and there is a need for rigorously quantitative approaches that are scalable. In this study, we used supervised machine learning approaches to develop automated classifiers to predict seizure severity directly from noninvasive video data. Using the PTZ-induced seizure model in mice, we trained video-only classifiers to predict ictal events, combined these events to predict an univariate seizure intensity for a recording session, as well as time-varying seizure intensity scores. Our results show, for the first time, that seizure events and overall intensity can be rigorously quantified directly from overhead video of mice in a standard open field using supervised approaches. These results enable high-throughput, noninvasive, and standardized seizure scoring for downstream applications such as neurogenetics and therapeutic discovery.

Automated analysis and detection of epileptic seizures in video recordings using artificial intelligence

Introduction

Automated seizure detection promises to aid in the prevention of SUDEP and improve the quality of care by assisting in epilepsy diagnosis and treatment adjustment.

Methods

In this phase 2 exploratory study, the performance of a contactless, marker-free, video-based motor seizure detection system is assessed, considering video recordings of patients (age 0-80 years), in terms of sensitivity, specificity, and Receiver Operating Characteristic (ROC) curves, with respect to video-electroencephalographic monitoring (VEM) as the medical gold standard. Detection performances of five categories of motor epileptic seizures (tonic-clonic, hyperkinetic, tonic, unclassified motor, automatisms) and psychogenic non-epileptic seizures (PNES) with a motor behavioral component lasting for >10 s were assessed independently at different detection thresholds (rather than as a categorical classification problem). A total of 230 patients were recruited in the study, of which 334 in-scope (>10 s) motor seizures (out of 1,114 total seizures) were identified by VEM reported from 81 patients. We analyzed both daytime and nocturnal recordings. The control threshold was evaluated at a range of values to compare the sensitivity (n = 81 subjects with seizures) and false detection rate (FDR) (n = all 230 subjects).

Results

At optimal thresholds, the performance of seizure groups in terms of sensitivity (CI) and FDR/h (CI): tonic-clonic- 95.2% (82.4, 100%); 0.09 (0.077, 0.103), hyperkinetic- 92.9% (68.5, 98.7%); 0.64 (0.59, 0.69), tonic- 78.3% (64.4, 87.7%); 5.87 (5.51, 6.23), automatism- 86.7% (73.5, 97.7%); 3.34 (3.12, 3.58), unclassified motor seizures- 78% (65.4, 90.4%); 4.81 (4.50, 5.14), and PNES- 97.7% (97.7, 100%); 1.73 (1.61, 1.86). A generic threshold recommended for all motor seizures under study asserted 88% sensitivity and 6.48 FDR/h.

Discussion

These results indicate an achievable performance for major motor seizure detection that is clinically applicable for use as a seizure screening solution in diagnostic workflows.