Clinical and CT image features for survival prediction in severe pneumonia during the SARS-CoV-2 Omicron wave

Back to news list

Source: Frontiers Medicine

Original: https://www.frontiersin.org/articles/10.3389/fmed.2025.1663710...

Published: 2026-01-09T00:00:00Z

The study retrospectively evaluated patients with severe pneumonia caused by the Omikron SARS-CoV-2 variant, admitted to the emergency department of Shandong Provincial Hospital between December 2022 and January 2023. Of the total number of 1,739 patients with COVID-19, 151 (8.68%) had severe pneumonia, with a median age of 75 years, and 70.1% were men. Clinical, laboratory, and CT data were analyzed, with patients randomly assigned to training (70%) and validation (30%) cohorts. Multivariate analysis showed that CT findings of pleural effusion and cardiac enlargement, low baseline oxygen saturation (SpO₂), elevated serum amyloid A (SAA), elevated glycemia (GLU), and decreased calcium (Ca) were independently associated with survival. Based on these signs, a nomogram was created to predict mortality during hospitalization. This tool had very good predictive accuracy, with an AUC of 0.914 in the training cohort and 0.802 in the validation cohort. The authors report that the identified combination of clinical and CT features may serve as a useful tool for early risk assessment and treatment targeting in patients with severe Omicron pneumonia.