Clincosm LogoSign in Get a demo

Deep Learning for the Discrimination Among Different Types of Keratits: a Nationwide Study

Sponsor
Ningbo Eye Hospital (Other)
Overall Status
Recruiting
CT.gov ID
NCT05538793
Collaborator
(none)
5,000
Enrollment
2
Locations
29
Anticipated Duration (Months)
2500
Patients Per Site
86.2
Patients Per Site Per Month

Study Details

Study Description

Brief Summary

Detecting the cause of keratitis fast is the premise of providing targeted therapy for reducing vision loss and preventing severe complications. Due to overlapping inflammatory features, even expert cornea specialists have relatively poor performance in the identification of causative pathogen of infectious keraitis. In this project, the investigators aim to develop an automated and accurate deep learning system to discriminate among bacterial, fungal, viral, amebic and noninfectious keratitis based on slit-lamp images and evaluated this system using the datasets obtained from mutiple independent clinical centers across China.

Condition or Disease Intervention/Treatment Phase

    Study Design

    Study Type:
    Observational
    Anticipated Enrollment :
    5000 participants
    Observational Model:
    Other
    Time Perspective:
    Other
    Official Title:
    Deep Learning for the Discrimination Among Bacterial, Fungal, Viral, Amebic and Noninfectious Keratitis: a Nationwide Study
    Actual Study Start Date :
    Jul 1, 2020
    Anticipated Primary Completion Date :
    Nov 1, 2022
    Anticipated Study Completion Date :
    Dec 1, 2022

    Outcome Measures

    Primary Outcome Measures

    1. Area under the receiver operating characteristic curve of the deep learning system [2020-2022]

    Secondary Outcome Measures

    1. Accuracy of the deep learning system [2020-2022]

    2. Sensitivity of the deep learning system [2020-2022]

    3. Specificity of the deep learning system [2020-2022]

    Eligibility Criteria

    Criteria

    Ages Eligible for Study:
    1 Week to 100 Years
    Sexes Eligible for Study:
    All
    Accepts Healthy Volunteers:
    No
    Inclusion Criteria:

    Slit-lamp images with sufficient diagnostic certainty and showing keratitis at the active phase.

    Exclusion Criteria:

    • Poor-quality images

    • Images presenting mixed infections (i.e., cornea infected by two or more causative pathogens)

    Contacts and Locations

    Locations

    Site City State Country Postal Code
    1 Ningbo Eye Hospital Ningbo Zhejiang China
    2 Eye Hospital of Wenzhou Medical University Wenzhou China

    Sponsors and Collaborators

    • Ningbo Eye Hospital

    Investigators

    None specified.

    Study Documents (Full-Text)

    None provided.

    More Information

    Publications

    None provided.
    Responsible Party:
    Ningbo Eye Hospital
    ClinicalTrials.gov Identifier:
    NCT05538793
    Other Study ID Numbers:
    • NEH2022091015
    First Posted:
    Sep 14, 2022
    Last Update Posted:
    Sep 14, 2022
    Last Verified:
    Sep 1, 2022
    Studies a U.S. FDA-regulated Drug Product:
    No
    Studies a U.S. FDA-regulated Device Product:
    No
    Keywords provided by Ningbo Eye Hospital
    Keratitis
    Slit-lamp Image
    Deep Learning
    Additional relevant MeSH terms:
    Keratitis

    Study Results

    No Results Posted as of Sep 14, 2022