Evaluation of a COVID-19 Pneumonia CXR AI Detection Algorithm

NCT04561024 | Unknown

• 1 other identifier: EN-092020
• Study Type: observational
• Target: 4,000
• Locations: 1 country
• Sites: 1

Brief Summary

This study investigates the diagnostic performance of an AI algorithm in the detection of COVID-19 pneumonia on chest radiographs.

Conditions

Covid19

Outcome Measures

Primary Outcomes (1)

• Diagnostic Performance of AI model

  Performance (accuracy, sensitivity, specificity, false-positive rate (FPR), false-negative rate (FNR), and Area Under the Curve (AUC)) of the AI model in detection of COVID-19 pneumonia on their baseline CXR using RT-PCR and historical controls as gold standard in a multi-center / multi-national cohort.

  9 months

Study Arms (2)

RT-PCR Positive Patients

RT-PCR confirmed patients positive for SARS-CoV-2

Diagnostic Test: AI model

Negative patients

RT-PCR confirmed patients negative for SARS-CoV-2 or patients with CXR performed before the emergence of COVID-19 pandemic

Diagnostic Test: AI model

Interventions

AI model DIAGNOSTIC_TEST

Deep Learning CNN model

Negative patients; RT-PCR Positive Patients

Eligibility Criteria

• Age: 18 Years - 120 Years
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

There will be three subsets of study population in this study; patients who were 1. RT-PCR confirmed COVID-19 positive 2. RT-PCR confirmed COVID-19 negative 3. either had a diagnosis of pneumonia before the 1st January 2020.

You may qualify if:

• All adult patients \>18 years of age
• Attended any of the participating institutes between February 1, 2020 until September, 2020
• Underwent both RT-PCR testing and frontal CXR (within 48 hours of PCR testing) for COVID-19 infection
• frontal CXR of patients pre-covid pandemic

You may not qualify if:

• Unavailability of patient demographics and clinical data
• Inconclusive RT-PCR results
• CXR considered to be of non-diagnostic quality by the clinical radiology research team at each site
• CXR not in a retrievable or processable format for AI inference

Sponsors & Collaborators

• Ensemble Group Holdings, LLC: lead

Study Sites (1)

University of Hong Kong

Hong Kong, Hong Kong

Location

MeSH Terms

Conditions

COVID-19

Condition Hierarchy (Ancestors)

Pneumonia, Viral; Pneumonia; Respiratory Tract Infections; Infections; Virus Diseases; Coronavirus Infections; Coronaviridae Infections; Nidovirales Infections; RNA Virus Infections; Lung Diseases; Respiratory Tract Diseases

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: INDUSTRY
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: September 22, 2020
• First Posted: September 23, 2020
• Study Start: March 1, 2020
• Primary Completion: October 30, 2020
• Study Completion: December 31, 2020
• Last Updated: September 24, 2020

Record last verified: 2020-09

Data Sharing

• IPD Sharing: Will not share

Locations

HK (1)