A nomogram to predict severe COVID-19 patients with increased pulmonary lesions in early days

Lina Chen; Min Li; Zhenghong Wu; Sibin Liu; Yuanyi Huang

doi:10.3389/fmed.2024.1343661

A nomogram to predict severe COVID-19 patients with increased pulmonary lesions in early days

Front Med (Lausanne). 2024 Apr 26:11:1343661. doi: 10.3389/fmed.2024.1343661. eCollection 2024.

Authors

Lina Chen¹, Min Li², Zhenghong Wu¹, Sibin Liu¹, Yuanyi Huang¹

Affiliations

¹ Department of Radiology, Jingzhou Hospital Affiliated to Yangtze University, Jingzhou, Hubei Province, China.
² Department of Radiology, Jingzhou Hospital of Traditional Chinese Medicine, Jingzhou, Hubei Province, China.

Abstract

Objectives: This study aimed to predict severe coronavirus disease 2019 (COVID-19) progression in patients with increased pneumonia lesions in the early days. A simplified nomogram was developed utilizing artificial intelligence (AI)-based quantified computed tomography (CT).

Methods: From 17 December 2019 to 20 February 2020, a total of 246 patients were confirmed COVID-19 infected in Jingzhou Central Hospital, Hubei Province, China. Of these patients, 93 were mildly ill and had follow-up examinations in 7 days, and 61 of them had enlarged lesions on CT scans. We collected the neutrophil-to-lymphocyte ratio (NLR) and three quantitative CT features from two examinations within 7 days. The three quantitative CT features of pneumonia lesions, including ground-glass opacity volume (GV), semi-consolidation volume (SV), and consolidation volume (CV), were automatically calculated using AI. Additionally, the variation volumes of the lesions were also computed. Finally, a nomogram was developed using a multivariable logistic regression model. To simplify the model, we classified all the lesion volumes based on quartiles and curve fitting results.

Results: Among the 93 patients, 61 patients showed enlarged lesions on CT within 7 days, of whom 19 (31.1%) developed any severe illness. The multivariable logistic regression model included age, NLR on the second time, an increase in lesion volume, and changes in SV and CV in 7 days. The personalized prediction nomogram demonstrated strong discrimination in the sample, with an area under curve (AUC) and the receiver operating characteristic curve (ROC) of 0.961 and a 95% confidence interval (CI) of 0.917-1.000. Decision curve analysis illustrated that a nomogram based on quantitative AI was clinically useful.

Conclusion: The integration of CT quantitative changes, NLR, and age in this model exhibits promising performance in predicting the progression to severe illness in COVID-19 patients with early-stage pneumonia lesions. This comprehensive approach holds the potential to assist clinical decision-making.

Keywords: COVID-19; X-ray computed; artificial intelligence; nomograms; pneumonia; prognosis; tomography; viral.

Grants and funding

The author(s) declare that financial support was received for the research, authorship, and/or publication of this article. This work was funded by the Jingzhou Science and Technology Committee (No. 2020CB21-10).