Development and prospective validation of COVID-19 chest X-ray screening model for patients attending emergency departments
Chest X-rays (CXRs) are the first-line investigation in patients presenting to emergency departments (EDs) with dyspnoea and are a valuable adjunct to clinical management of COVID-19 associated lung disease. Artificial intelligence (AI) has the potential to facilitate rapid triage of CXRs for further patient testing and/or isolation.
Despite their utility, radiological interpretation of CXRs in suspected COVID-19 patients remains challenging due to the idiosyncratic nature of this disease. For example, no single feature on chest radiography is diagnostic of COVID-19 pneumonia and early or mild disease is often accompanied by a paucity of radiological signs. Computer-aided diagnostic systems that can aid radiologists to more rapidly and accurately detect COVID-19 cases have been suggested as important operational adjuncts with potential to alleviate radiology workloads and improve patient safety.
Our recent work shows that radiological signs of Covid-19 pneumonia can be reliably identified from frontal chest X-Rays at first presentation. The AI algorithm, CovIx, was trained to differentiate normal, abnormal, non-COVID-19 pneumonia, and COVID-19 CXRs using a multicentre cohort of 293,143 CXRs. The algorithm is prospectively validated in 3289 CXRs acquired from patients presenting to ED with symptoms of COVID-19 across four sites in NHS Greater Glasgow and Clyde. CovIx achieves area under receiver operating characteristic curve for COVID-19 of 0.86, with sensitivity and F1-score up to 0.83 and 0.71 respectively, and performs on-par with four board-certified radiologists. AI-based algorithms can identify CXRs with COVID-19 associated pneumonia, as well as distinguish non-COVID pneumonias in symptomatic patients presenting to ED. Pre-trained models and inference scripts are freely available at https://github.com/beringresearch/bravecx-covid.