MedPath

CT Biomarkers Identification by Artificial Intelligence for COVID-19 Prognosis

Withdrawn
Conditions
Covid-19
Interventions
Diagnostic Test: Imaging by thoracic scanner
Registration Number
NCT04418245
Lead Sponsor
Centre Hospitalier Universitaire de Nīmes
Brief Summary

The study hypothesis is that low-dose computed tomography (LDCT) coupled with artificial intelligence by deep learning would generate imaging biomarkers linked to the patient's short- and medium-term prognosis.

The purpose of this study is to rapidly make available an early decision-making tool (from the first hospital consultation of the patient with symptoms related to SARS-CoV-2) based on the integration of several biomarkers (clinical, biological, imaging by thoracic scanner) allowing both personalized medicine and better anticipation of the patient's evolution in terms of care organization.

Detailed Description

Not available

Recruitment & Eligibility

Status
WITHDRAWN
Sex
All
Target Recruitment
1000
Inclusion Criteria
  • Patients positive for SARS-CoV-2 according to RT-PCR test between 1st March and 31st May 2020
  • Patients undergoing low dose CT scan to establish Covid-19 lung damage
  • Available for at least 8 days follow-up
Exclusion Criteria

• Patients opposing the retrospective use of their data

Study & Design

Study Type
OBSERVATIONAL
Study Design
Not specified
Arm && Interventions
GroupInterventionDescription
Patients positive for SARS-CoV-2Imaging by thoracic scanner-
Primary Outcome Measures
NameTimeMethod
Patient requiring more than 3 liters of oxygen to maintain a saturation >95% (intensive care unit or resuscitation department)Day 8

Yes/no

Percentage of lung affected by condensation on scanDay 0

% calculated by deep learning

Percentage of lung affected by ground glass opacity on scanDay 0

% calculated by deep learning

Vital statusDay 8

Dead/alive

Percentage of lung affected on CTDay 0

% ground glass and condensation calculated by deep learning

Secondary Outcome Measures
NameTimeMethod
C-reactive protein levelsAdmission Day 0

mg/L

Time until onset of symptomsAdmission Day 0

Days

Vital statusDay 30

Dead/alive

Length of hospitalizationMaximum 30 days

Days

Percentage of lung affected by ground glass opacity on scanDay 16

% calculated by deep learning

Percentage of lung affected by condensation on scanDay 16

% calculated by deep learning

rehospitalizationDay 30

Yes/no

Duration of intubationDay 30

Days

D Dimers levelAdmission Day 0

µg/L

Time between RT-PCR positive results and first scanAdmission Day 0

Hours

Medical history of cardiovascular diseaseAdmission Day 0

Yes/no: hypertension, coronary artery disease, congestive heart failure, cardiac arrhythmia

Percentage of lung affected on CTDay 16

% ground glass and condensation calculated by deep learning

BMI> 30Admission Day 0

Yes/no:

Software operating timeEnd of study (August 2020)

Speed of image loading and image processing depending of brand of scanner

lymphocytemiaAdmission Day 0

g/L

DiabetesAdmission Day 0

Yes/no

Medical history of immunosuppressed conditionAdmission Day 0

Yes/no: steroid use, pre-existing immunological condition, current chemotherapy for cancer

Calculate a prognostic score from clinical, biological and CT parametersDay 8

Deep learning algorithm

lactate dehydrogenaseAdmission Day 0

U/L

Calculate a prognostic score from clinical and biological parameters onlyDay 8

Deep learning algorithm

Medical history of respiratory diseaseAdmission Day 0

Yes/no: Chronic obstructive pulmonary disease, chronic respiratory failure

Current or previous history of smokingAdmission Day 0

Yes/no:

AgeAdmission Day 0

Years

Compare receiver operating curves of prognostic scores with and without CT parametersDay 8

Trial Locations

Locations (6)

CHU la Timone

🇫🇷

Marseille, France

CHU Montpellier

🇫🇷

Montpellier, France

CHU Strasbourg

🇫🇷

Strasbourg, France

CHU Poitiers

🇫🇷

Poitiers, France

CHU de Nimes

🇫🇷

Nîmes, France

CHU Martinique

🇲🇶

Fort-de-France, Martinique

© Copyright 2025. All Rights Reserved by MedPath