A predictive model to explore risk factors for severe COVID-19.

Area of Science:

• Infectious Diseases
• Epidemiology
• Clinical Medicine

Background:

• The COVID-19 pandemic has caused millions of deaths globally, impacting healthcare systems and economies.
• Understanding risk factors for severe illness is crucial for effective patient management and resource allocation.

Purpose of the Study:

• To identify clinical, laboratory, and imaging risk factors associated with severe COVID-19.
• To develop and validate a predictive model for assessing the risk of severe COVID-19.

Main Methods:

• Retrospective analysis of electronic medical records from 346 COVID-19 patients.
• Comparison of clinical, laboratory (including neutrophil-to-lymphocyte ratio (NLR) and lactate dehydrogenase (LDH)), and imaging data between severe and non-severe groups.
• Development of a predictive nomogram model using logistic regression, LASSO, and ROC curve analysis.

Main Results:

• Severe COVID-19 patients showed higher respiratory rates, breathlessness, altered consciousness, NLR, and LDH levels.
• Bilateral pulmonary inflammation and ground-glass opacities were more common in severe cases.
• NLR and LDH were identified as independent risk factors; a model combining NLR, respiratory rate, and LDH demonstrated good predictive value.

Conclusions:

• A validated nomogram model effectively predicts the risk of severe COVID-19.
• The model aids in identifying high-risk patients, potentially improving clinical outcomes and resource management.
• NLR, respiratory rate, and LDH are key indicators for predicting COVID-19 severity.