Artificial intelligence helpful in stratifying COVID-19 risk based on chest x-rays: Study

USA: A modified commercially available deep learning algorithm (M-qXR) could be utilized in low-resource settings to risk-stratify patients with suspected COVID-19 infections by detecting abnormalities on chest X-rays, shows a recent study. The study was published in the journal Intelligence-Based Medicine on January 13, 2022. 

According to the study, the artificial intelligence (AI) algorithm had comparable accuracy to ground truth for detecting radiographic abnormalities on CXR suggestive of COVID-19 and thus could serve as a radiology decision tool to guide management of patients who are deemed at risk for COVID-19. 

Previous studies have shown that in resource-limited settings, deep learning-based radiological image analysis could facilitate the use of chest x-rays as a triaging tool for COVID-19 diagnosis. Diego A. Hipolito Canario, UNC School of Medicine, the University of North Carolina at Chapel Hill, Chapel Hill, NC, United States, and colleagues thus aimed to determine whether a modified commercially available deep learning algorithm (M-qXR) could risk-stratify patients with suspected COVID-19 infections. 

For this purpose, the researchers designed a dual-track clinical validation study to assess the clinical accuracy of M-qXR. All Chest-X-rays (CXRs) performed during the study period were evaluated for abnormal findings and assigned a COVID-19 risk score. Four independent radiologists served as radiological ground truth. 

The researchers then compared M-qXR algorithm output against radiological ground truth and calculated summary statistics for prediction accuracy. In a co-occurrence matrix, patients who underwent both PCR testing and CXR for suspected COVID-19 infection were included to assess the sensitivity and specificity of the M-qXR algorithm.