The AI-based system designed to process chest computed tomography (CT) aims to 1) detect the presence of pathologic patterns associated with interstitial changes in pneumonia; 2) highlight areas on the images with the probable presence of pathologies; 3) provide the physician with the results of image processing, including quantitative indicators of suspected viral pneumonia related lung changes according to visual pulmonary lesion grading system (CT0-4).
The retrospective study aims to demonstrate the clinical validation of the AI-based system. Clinical validation measures (sensitivity, specificity, accuracy, and area under the ROC curve) will be determined to provide evidence about the clinical efficacy of the AI-based system.
The hypothesis is that the measures of clinical validation of the AI-based system differ by no more than 8% from those declared by the manufacturer.
General
Patients over 18 years old;
Patients who underwent CT without contrast enhancement;
Patients who underwent a CT scan according to a standardized scanning protocol: 120 kilovolts, slice thickness max. 2 mm, rigid "lung" filter (kernel) reconstruction;
Patients whose studies contain images with unreported CT patterns;
Patients whose examinations do not conform to DICOM format;
Patients whose examinations do not contain imaging of the lung region
Patients whose examinations contain technical artifacts caused by malfunctions or features of CT scanners;
Adults (patients over 18 years of age) who were referred for a chest CT study by a physician in case of suspicion or monitoring the effectiveness of treatment of diseases manifested by changes in the pulmonary parenchyma.
Cohort
Retrospective
Medical software (AI-based system)
Diagnostic testRetrospective analysis of chest CT images with medical software (AI-based system)
Accuracy
The ability of an AI-based system to produce the correct result relative to the total number of trials
Sensitivity
Effectiveness of the AI-based system to correctly identifies patients with the suspected viral pneumonia related lung changes
Specificity
Effectiveness of the AI-based system to correctly identifies across a range of available measurements patients that do not have the suspected viral pneumonia related lung changes
AUC ROC
The area under curve (AUC) of Receiver Operating Characteristic (ROC) curves of AI-based system in prediction of suspected viral pneumonia related lung changes
Approximate volume of affected lung tissue
Approximate volume of affected lung tissue - quantitative characteristics of lung damage volume in percent (%): separately for left lung, right lung and total percentage of damage
Click on the lead sponsor to view all of their trials.
