AUTHOR=Zhuang Zhenchao , Qi Yuxiang , Yao Yimin , Yu Ying 

TITLE=A predictive model for disease severity among COVID-19 elderly patients based on IgG subtypes and machine learning

JOURNAL=Frontiers in Immunology

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/immunology/articles/10.3389/fimmu.2023.1286380

DOI=10.3389/fimmu.2023.1286380

ISSN=1664-3224

ABSTRACT=Objective: Elderly patients with coronavirus disease 2019 (COVID-19) are more likely to develop severe pneumonia, with a high mortality rate. However, there are no IgG subtype-based models to predict the severity of COVID-19 in elderly patients. We aimed to develop and validate a predictive model for differentiating elderly patients with severe COVID-19. Methods: This was a retrospective study that collected clinical data from 103 confirmed SARS-CoV-2-positive patients. These patients were randomly divided into a training cohort (80%) and a validation cohort (20%). In addition, 22 COVID-19 elderly patients from the other two centers were divided into an external validation cohort. Differential indicators were analyzed through univariate analysis, and variable selection was performed using LASSO regression. Five machine learning algorithms were used to construct the predictive model for the severity of elderly patients with COVID-19. The performance of these models was measured by AUC. Interpretation and evaluation of the prediction model were performed using calibration curves, DCA curves, and SHAP plots. Results: The logistic regression model was chosen as the best machine learning model with 4 principal variables that could predict the probability of COVID-19 severity. The AUC of the model was 0.889 in the training cohort and 0.824 in the testing cohort. The calibration curve demonstrated excellent consistency between actual and predicted probabilities. The DCA curve showed that the model had a high clinical benefit. Moreover, our model worked well in an external validation cohort (AUC=0.74). Conclusions: We developed a model that can distinguish between severe and non-severe cases of COVID-19 in elderly patients, which may