CT quantification of pneumonia lesions in early days predicts progression to severe illness in a cohort of COVID-19 patients

Abstract

Rationale: Some patients with coronavirus disease 2019 (COVID-19) rapidly develop respiratory failure or even die, underscoring the need for early identification of patients at elevated risk of severe illness. This study aims to quantify pneumonia lesions by computed tomography (CT) in the early days to predict progression to severe illness in a cohort of COVID-19 patients. Methods: This retrospective cohort study included confirmed COVID-19 patients. Three quantitative CT features of pneumonia lesions were automatically calculated using artificial intelligence algorithms, representing the percentages of ground-glass opacity volume (PGV), semi-consolidation volume (PSV), and consolidation volume (PCV) in both lungs. CT features, acute physiology and chronic health evaluation II (APACHE-II) score, neutrophil-to-lymphocyte ratio (NLR), and d-dimer, on day 0 (hospital admission) and day 4, were collected to predict the occurrence of severe illness within a 28-day follow-up using both logistic regression and Cox proportional hazard models. Results: We included 134 patients, of whom 19 (14.2%) developed any severe illness. CT features on day 0 and day 4, as well as their changes from day 0 to day 4, showed predictive capability. Changes in CT features from day 0 to day 4 performed the best in the prediction (area under the receiver operating characteristic curve = 0.93, 95% confidence interval [CI] 0.87~0.99; C-index=0.88, 95% CI 0.81~0.95). The hazard ratios of PGV and PCV were 1.39 (95% CI 1.05~1.84, P=0.023) and 1.67 (95% CI 1.17~2.38, P=0.005), respectively. CT features, adjusted for age and gender, on day 4 and in terms of changes from day 0 to day 4 outperformed APACHE-II, NLR, and d-dimer. Conclusions: CT quantification of pneumonia lesions can early and non-invasively predict the progression to severe illness, providing a promising prognostic indicator for clinical management of COVID-19.

Keywords: Artificial intelligence; COVID-19; Chest CT; Retrospective cohort; Severe illness.

Figure 1

Flow diagram of the study population.

Figure 2

CT image quantization and analysis with artificial intelligence (AI) system. CT images acquired on the day of admission (day 0, in the lower right panel of the figure denoted as “Previous”) and acquired four (±1) days after admission (day 4, upper right denoted as “Current”) can be compared using histograms (upper left) and AI-derived quantitative features. Here, on day 0, the percentage of ground-glass opacity (GGO) volume, percentage of semi-consolidation volume, and percentage of consolidation volume were 0.7, 0.6 and 0.1, while on day 4, they increased to 10.8, 26.1 and 11.5.

Figure 3

COVID-19 pneumonia lesions detected by the AI system and visualized as pseudo colors. First to third columns: initial CT images; displayed with red pseudo colors; displayed with blue, pink, and red pseudo colors representing ground-glass opacity (GGO), semi-consolidation and consolidation, respectively. Pictures of two patients are illustrated: one was a 38year-old male (A and B), who reached the endpoint of progression to severe illness after 7 days from admission, and the other was a 31-year-old male (C), who did not meet the endpoint during the follow-up and was discharged from the hospital after 13 days from admission. The upper halves of A, B, and C show images on day 0, and the lower halves show images on day 4.