Using Artificial Intelligence for COVID-19 Chest X-ray Diagnosis [article]

Andrew A Borkowski, Narayan A Viswanadham, L Brannon Thomas, Rodney D Guzman, Lauren A Deland, Stephen M Mastorides
2020 medRxiv   pre-print
Coronavirus disease-19 (COVID-19), caused by a novel member of the coronavirus family, is a respiratory disease that rapidly reached pandemic proportions with high morbidity and mortality. It has had a dramatic impact on society and world economies in only a few months. COVID-19 presents numerous challenges to all aspects of healthcare, including reliable methods for diagnosis, treatment, and prevention. Initial efforts to contain the spread of the virus were hampered by the time required to
more » ... elop reliable diagnostic methods. Artificial intelligence (AI) is a rapidly growing field of computer science with many applications to healthcare. Machine learning is a subset of AI that employs deep learning with neural network algorithms. It can recognize patterns and achieve complex computational tasks often far quicker and with increased precision than humans. In this manuscript, we explore the potential for a simple and widely available test as a chest x-ray (CXR) to be utilized with AI to diagnose COVID-19 reliably. Microsoft CustomVision is an automated image classification and object detection system that is a part of Microsoft Azure Cognitive Services. We utilized publicly available CXR images for patients with COVID-19 pneumonia, pneumonia from other etiologies, and normal CXRs as a dataset to train Microsoft CustomVision. Our trained model overall demonstrated 92.9% sensitivity (recall) and positive predictive value (precision), with results for each label showing sensitivity and positive predictive value at 94.8% and 98.9% for COVID-19 pneumonia, 89% and 91.8% for non-COVID-19 pneumonia, 95% and 88.8% for normal lung. We then validated the program using CXRs of patients from our institution with confirmed COVID-19 diagnoses along with non-COVID-19 pneumonia and normal CXRs. Our model performed with 100% sensitivity, 95% specificity, 97% accuracy, 91% positive predictive value, and 100% negative predictive value. Finally, we developed and described a publicly available website to demonstrate how this technology can be made readily available in the future.
doi:10.1101/2020.05.21.20106518 fatcat:rcm7meyzpzgu3jjpquskmu3gue