Automated AI-Driven CT Quantification of Lung Disease Predicts Adverse Outcomes in Patients Hospitalized for COVID-19 Pneumonia

Abstract

The purpose of our work was to assess the independent and incremental value of AI-derived quantitative determination of lung lesions extent on initial CT scan for the prediction of clinical deterioration or death in patients hospitalized with COVID-19 pneumonia. 323 consecutive patients (mean age 65 ± 15 years, 192 men), with laboratory-confirmed COVID-19 and an abnormal chest CT scan, were admitted to the hospital between March and December 2020. The extent of consolidation and all lung opacities were quantified on an initial CT scan using a 3D automatic AI-based software. The outcome was known for all these patients. 85 (26.3%) patients died or experienced clinical deterioration, defined as intensive care unit admission. In multivariate regression based on clinical, biological and CT parameters, the extent of all opacities, and extent of consolidation were independent predictors of adverse outcomes, as were diabetes, heart disease, C-reactive protein, and neutrophils/lymphocytes ratio. The association of CT-derived measures with clinical and biological parameters significantly improved the risk prediction (p = 0.049). Automated quantification of lung disease at CT in COVID-19 pneumonia is useful to predict clinical deterioration or in-hospital death. Its combination with clinical and biological data improves risk prediction.

Keywords: COVID-19; artificial intelligence; multivariate analysis; outcome prediction; pneumonia; quantitative CT.

Figure 1

Chest CT scan performed the day of hospital admission in a 46 yo male COVID-19 patient. Axial (a), Coronal (b), and Sagittal (c) reformatted CT images after application of the AI-driven software. The interfaces between the pleura and lung parenchyma were automatically segmented by the software. The limits of the lobes are marked with different colors: yellow for the right upper lobe, green for the left upper lobe, dark green for the right lower lobe, and blue for the left lower lobe. The red marks represent the contours of lung opacities segmented by the software, and the purple marks limit the consolidation areas. Automatic measures of the extent of consolidation and all lung opacities were 13% and 39% of lung volume respectively. This patient had diabetes and presented increased C-reactive protein level and neutrophils/lymphocytes ratio. After 3 days of hospitalization, because of clinical deterioration, the patient was transferred to the intensive care unit for high-flow oxygen therapy.