Assessing Comorbidities in Epilepsy Using Eye Movement Recordings

Eysz, Inc.60 enrolled

Overview

This study wants to make it easier to find kids with a type of epilepsy called childhood absence epilepsy (CAE) who might have problems with ongoing seizures and thinking. Right now, doctors use tests that can be expensive and take a long time. Eysz is developing a system that looks at how kids move their eyes which might help find CAE more quickly and accurately. This study will compare Eysz with the usual tests to see if it can predict seizures and thinking problems in kids with CAE. The goal is to find these problems earlier and help kids do better in school and life.

This study addresses the challenges in managing childhood absence epilepsy (CAE), a condition that poses risks of injury and cognitive issues despite normal intelligence levels. Current management relies heavily on subjective reporting and costly, time-consuming tests such as neuropsychiatric assessments and EEGs. However, these methods often underestimate seizure burden and neurocognitive comorbidities, leading to missed opportunities for early intervention. Eysz, a novel system analyzing eye movements, has shown promise in identifying CAE features through passive analysis. Building upon this, the study aims to validate Eysz against established tests like EEGs and questionnaires to develop a rapid and objective tool for identifying CAE in children at risk of poor outcomes due to ongoing seizures or cognitive issues. By evaluating eye-movement features in comparison with hyperventilation, EEG results, and various assessments, the goal is to enable earlier diagnosis, quicker attainment of seizure freedom, and identification of at-risk children who may benefit from interventions to improve cognitive outcomes during critical developmental periods. The study will assess features such as saccade frequency, fixation duration, and eye blink frequency measured by the Eysz system and correlate them with clinical outcomes. By improving the accuracy and efficiency of CAE diagnosis, the study aims to reduce the burden on patients and caregivers while enhancing overall treatment outcomes. Additionally, the findings may contribute to a better understanding of the relationship between eye movements and neurological conditions, potentially opening avenues for future research and intervention strategies. Through collaboration with clinicians and researchers, this study seeks to address the unmet needs in CAE management and ultimately improve the quality of life for affected children and their families.

Study Type

OBSERVATIONAL

Enrollment

Eligibility

Sex: ALLMin age: 4 YearsMax age: 12 YearsHealthy volunteers:

Medical Language ↔ Plain English

Inclusion Criteria: Diagnosis of Childhood Absence Epilepsy by Treating Neurologist or a Healthy control Fluent in English Exclusion Criteria: History of subarachnoid hemorrhage, sickle cell anemia, recent cerebrovascular accident or myocardial infarction, significant cardiopulmonary disease, active asthma, known aneurysm, known moyamoya disease, or pregnancy. Known diagnosis of strabismus or amblyopia Any vision abnormalities that prevent the participant from viewing the screen clearly People who have a history of generalized tonic clonic convulsions To participate as a healthy control the participant must have no personal history of epilepsy, ADHD or other developmental disorder, no first degree relatives with the above diagnosis

Outcomes

Primary Outcomes

Eye Movements to Diagnose CAE

Use machine learning algorithms based on eye movement feature analysis (e.g., saccade frequency and velocity, fixation duration, and eye blink frequency) to identify people with CAE, and those with ongoing seizure activity with \> 75% sensitivity and specificity.

Time frame: 1 year

Secondary Outcomes

Eye Movements to Diagnose Attention challenges

Use machine learning algorithms based on eye movement feature analysis to identify people with epilepsy whose CPT score indicates attention deficits and those with PESQ score \> 34 (1 standard deviation from mean) with \> 75% sensitivity and specificity.