Data Driven Estimation of Covid-19 Prognosis

Abstract

Continuous spread of novel coronavirus (COVID-19) and availability of limited resources force the severity-based allocation of resources. While it is essential to have a reliable severity assessment method, it is even more critical to have a prognosis model to estimate infection progress in individuals. An accurate estimate of infection progression would naturally help in optimized treatment and morbidity reduction. We aim at the prognosis of the COVID-19 infections including, ground-glass opacities, consolidation, and pleural effusion, from the longitudinal chest X-ray (CXR) images of the patient. For this purpose, we first propose a learning-based framework that predicts infection type from a given CXR image. This helps in finding low dimensional embeddings of CXR images, which we use in a recurrent learning framework to predict the type of infection for the subsequent days. We achieve a test AUC of 0.85 for infection type prediction and a test AUC of 0.88 for prognosis on the benchmark COVID-19 dataset.