A Study of Detection of Paroxysmal Events Utilizing Computer Vision and Machine Learning - Nelli

Recruiting

• Conditions: Epilepsy

• Registration Number: NCT05606575
• Lead Sponsor: Neuro Event Labs Inc.

Brief Summary

Nelli is a video-based non-EEG physiological seizure monitoring system. This study is a blinded comparison of Nelli's identified events to gold-standard video EEG review in at-rest pediatric subjects with suspected motor seizures.

Detailed Description

Automated analysis of video recordings to detect seizures, assisted by modern methods of machine learning, holds great promise to address this issue. Increased computational power has made it possible to implement complex image recognition tasks and machine learning in everyday use. Nelli® software is designed to use computer vision and machine learning-based algorithms to automatically detect seizure events. This study will provide evidence that Nelli software can identify seizure events and deliver objective data to clinicians for evaluation of seizure management.

This study is being conducted to validate the Nelli Software's ability to identify periods of audio

/video data that contain recordings of patients experiencing seizures (or seizure-like events) during periods of rest. The software's performance will be compared to the gold standard, expert review of video EEG data.

Nelli Software will review the audio and video data and independently identify events with positive motor manifestations. The outcomes of event identification will be compared between epileptologists and the Nelli Software. For each category of event captured the positive percent agreement will be calculated using the exact binomial method. The primary endpoint of this study is to demonstrate that Nelli is able to identify seizures that have a positive motor component with a sensitivity of \>70% (lower 95% CI) and with a false discovery rate (FDR) comparable to similar devices on the market.

Study Timeline

• Study Start: 2022-08-01
• Study First Submitted: 2022-10-25
• Study First Submitted QC: 2022-11-03
• Study First Posted: 2022-11-04
• Status Verified: 2025-05
• Last Update Submitted: 2025-05-20
• Last Update Posted: 2025-05-23
• Primary Completion: 2025-12
• Study Completion: 2026-03

Recruitment & Eligibility

• Status: RECRUITING
• Sex: All
• Target Recruitment: 104

Inclusion Criteria

• Subject shall sign informed consent.
• Subject is between 6 and 21 years.
• Subjects shall be undergoing video-EEG monitoring for routine clinical purposes.
• Subjects shall have a suspected history of motor seizures.
• Subject shall be able to understand and sign written informed consent or have a legally authorized representative (LAR) who can do so, prior to the performance of any study assessments.

Exclusion Criteria

• None identified.

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Primary Outcome Measures

Name	Time	Method
Sensitivity of a seizure detection system	During routine video-EEG monitoring, up to 14 days	To show that Nelli is able to correctly identify each category of seizures separately (Category I, II, and III) and all seizures categories combined with a sensitivity of at least 70%. Hypotheses will be tested sequentially (all seizures combined, Category I, then Category II, then Category III), each with a significance level of 2.5%, and will continue until the first hypothesis is not rejected.; For each detected abnormal event, the probability is calculated and concluded as seizure/non- seizure using predefined threshold values, pre-trained seizure detection library, and probability of that event. The time-points are reported automatically into the Dashboard of Nelli. Statistical analyses will be performed to calculate true and false positive and negative detection rates.

Trial Locations

Locations (1)

The University of Tennessee Health Science Center; 🇺🇸 Memphis, Tennessee, United States