A predictive model for post-COVID-19 pulmonary parenchymal abnormalities based on dual-center data

Abstract

Abstract Documented radiological and physiological anomalies among coronavirus disease 2019 survivors necessitate prompt recognition of residual pulmonary parenchymal abnormalities for effective management of chronic pulmonary consequences. This study aimed to devise a predictive model to identify patients at risk of such abnormalities post-COVID-19. Our prognostic model was derived from a dual-center retrospective cohort comprising 501 hospitalized COVID-19 cases from July 2022 to March 2023. Of these, 240 patients underwent Chest CT scans three months post-infection. A predictive model was developed using stepwise regression based on the Akaike Information Criterion, incorporating clinical and laboratory parameters. The model was trained and validated on a split dataset, revealing a 33.3% incidence of pulmonary abnormalities. It achieved strong discriminatory power in the training set (area under the curve: 0.885, 95% confidence interval 0.832–0.938), with excellent calibration and decision curve analysis suggesting substantial net benefits across various threshold settings. We have successfully developed a reliable prognostic tool, complemented by a user-friendly nomogram, to estimate the probability of residual pulmonary parenchymal abnormalities three months post-COVID-19 infection. This model, demonstrating high performance, holds promise for guiding clinical interventions and improving the management of COVID-19-related pulmonary sequela.

Keywords

• SARS-CoV-2 sequelae
• Pulmonary parenchymal abnormalities
• Clinical prediction model
• Computed tomography imaging
• Nomogram