ARRS 2022 Abstracts

RETURN TO ABSTRACT LISTING


E2033. Using Artificial Intelligence to Risk Stratify Patients With COVID-19 Based on Chest X-ray Findings
Authors
  1. Eric Fromke; University of North Carolina at Chapel Hill School of Medicine
  2. Matthew Patetta; University of North Carolina at Chapel Hill School of Medicine
  3. Diego Hipolito Canario; University of North Carolina at Chapel Hill Department of Surgery
  4. Juan Reyes-Gonzalez; Angeles del Pedregal Hospital Department of Radiology
  5. Valeria Fusco Cornejo; Mindscale
  6. Seymour Duncker; Mindscale
  7. Jessica Stewart; UCLA Health Santa Clarita Imaging and Interventional Center; UNC School of Medicine Department of Radiology
Objective:
Deep learning-based radiological image analysis could facilitate use of chest x-rays as a triaging tool for COVID-19 diagnosis in resource-limited settings. This study sought to determine whether a modified commercially available deep learning algorithm called “M-qXR” could risk stratify patients with suspected COVID-19 infections.

Materials and Methods:
A dual track clinical validation study was designed to assess the clinical accuracy of M-qXR. The algorithm evaluated all Chest x-rays (CXRs) performed during the study period for abnormal findings and assigned a COVID-19 risk score. Four independent radiologists served as ground truth. The M-qXR algorithm output was compared against radiological ground truth and summary statistics for prediction accuracy were calculated. In addition, patients who underwent both PCR testing and CXR for suspected COVID-19 infection were included in a co-occurrence matrix to assess the sensitivity and specificity of the M-qXR algorithm.

Results:
A total of 625 CXRs were included in the clinical validation study. Ninety-eight percent of total interpretations made by M-qXR agreed with ground truth (p = 0.25). M-qXR correctly identified the presence or absence of pulmonary opacities in 94% of CXR interpretations. M-qXR sensitivity, specificity, PPV, and NPV for detecting pulmonary opacities were 94%, 95%, 99%, and 88% respectively. M-qXR correctly identified the presence or absence of pulmonary consolidation in 88% of CXR interpretations (p = 0.48). M-qXR sensitivity, specificity, PPV, and NPV for detecting pulmonary consolidation were 91%, 84%, 89%, and 86% respectively. Furthermore, 113 PCR-confirmed COVID-19 cases were used to create a co-occurrence matrix between the M-qXR COVID-19 risk score and COVID-19 PCR test results. The PPV and NPV of a medium to high COVID-19 risk score assigned by M-qXR yielding a positive COVID-19 PCR test result was estimated to be 89.7% and 80.4%, respectively.

Conclusion:
M-qXR was found to have comparable accuracy to ground truth in detecting radiographic abnormalities on CXR suggestive of COVID-19. The M-qXR algorithm has the potential to provide benefit in guiding medical management of patients suspected of having COVID-19 who present with a high likelihood of disease, and where timely viral testing is not feasible due to limited resources.