A novel model to predict severe COVID-19 and mortality using an artificial intelligence algorithm to interpret chest radiographs and clinical variables

Background Patients with coronavirus disease 2019 (COVID-19) could develop severe disease requiring admission to the intensive care unit (ICU). This article presents a novel method that predicts whether a patient will need admission to the ICU and assesses the risk of in-hospital mortality by training a deep-learning model that combines a set of clinical variables and features in chest radiographs. Methods This was a prospective diagnostic test study. Patients with confirmed severe acute respiratory syndrome coronavirus 2 infection between March 2020 and January 2021 were included. This study was designed to build predictive models obtained by training convolutional neural networks for chest radiograph images using an artificial intelligence (AI) tool and a random forest analysis to identify critical clinical variables. Then, both architectures were connected and fine-tuned to provide combined models. Results 2552 patients were included in the clinical cohort. The variables independently associated with ICU admission were age, fraction of inspired oxygen (F-iO2) on admission, dyspnoea on admission and obesity. Moreover, the variables associated with hospital mortality were age, F-iO2 on admission and dyspnoea. When implementing the AI model to interpret the chest radiographs and the clinical variables identified by random forest, we developed a model that accurately predicts ICU admission (area under the curve (AUC) 0.92 +/- 0.04) and hospital mortality (AUC 0.81 +/- 0.06) in patients with confirmed COVID-19. Conclusions This automated chest radiograph interpretation algorithm, along with clinical variables, is a reliable alternative to identify patients at risk of developing severe COVID-19 who might require admission to the ICU.

Automated summary

This study successfully predicted the need for ICU admission and the risk of in-hospital mortality in COVID-19 patients by training a deep-learning model that combines clinical variables and chest radiograph features.