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

NCT04738552 | Completed FDA Device

• 1 other identifier: TJU-20D.009
• Study Type: observational
• Target: 233
• Locations: 1 country
• Sites: 1

Brief Summary

Increased computational power has made it possible to implement complex image recognition tasks and machine learning to be implemented in every day usage. The computer vision and machine learning based solution used in this project (Nelli) is an automatic seizure detection and reporting method that has a CE mark for this specific use. The present study will provide data to expand the utility and detection capability of NELLI and enhance the accuracy and clinical utility of automated computer vision and machine learning based seizure detection.

Conditions

Epilepsy

Outcome Measures

Primary Outcomes (1)

• Sensitivity of a seizure detection system

  The primary outcome measure will be the sensitivity of the Nelli system to detect seizrues with a positive motor component in comparison to independent Neurologist review of vEEG collected in an epilepsy monitoring unit. This is a blinded comparison to the clinical gold standard (vEEG)

  During routine seizure monitoring in the hospital - up to one week

Interventions

Nelli DEVICE

Nelli detects and registers activity that is indicative of seizure events. Nelli captures, stores, and processes video and audio recordings from each patient. Biomarker data is collected during periods of rest for the length of an examination period, which may span several days or months (when used inside and outside of a hospital setting, respectively), as prescribed by a treating physician.

Eligibility Criteria

• Age: 18 Years - 99 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

Patients with suspected motor seizures that are undergoing video-EEG monitoring for routine clinical care.

You may qualify if:

• All patients undergoing video-EEG monitoring for clinical purposes who are suspected of having seizures.

Sponsors & Collaborators

• Neuro Event Labs Inc.: lead

Study Sites (1)

Thomas Jefferson University

Philadelphia, Pennsylvania, 19107, United States

Location

MeSH Terms

Conditions

Epilepsy

Condition Hierarchy (Ancestors)

Brain Diseases; Central Nervous System Diseases; Nervous System Diseases

Study Officials

• Michael Sperling, MD

  Jefferson University

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: PROSPECTIVE
• Sponsor Type: INDUSTRY
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: January 29, 2021
• First Posted: February 4, 2021
• Study Start: January 9, 2020
• Primary Completion: November 27, 2022
• Study Completion: November 27, 2022
• Last Updated: November 25, 2024

Record last verified: 2024-11

Data Sharing

• IPD Sharing: Will not share

Locations

US (1)