Mortality estimation using APACHE and CT scores with stepwise linear regression method in COVID-19 intensive care...

Area of Science:

• Critical Care Medicine
• Infectious Diseases
• Medical Imaging

Background:

• COVID-19 poses a significant global mortality risk, particularly in intensive care settings.
• Identifying key predictors of mortality in these patients remains an active area of research.

Purpose of the Study:

• To identify factors influencing mortality in COVID-19 intensive care unit (ICU) patients.
• To develop a predictive model for COVID-19 ICU mortality.

Main Methods:

• Retrospective analysis of 229 COVID-19 ICU patients.
• Inclusion of laboratory values, APACHE, SOFA, GCS scores, and chest CT scan scores.
• Stepwise linear regression modeling to identify significant predictors.

Main Results:

• Mortality rate observed was 69.86%.
• Significant differences in age, CRP, D-dimer, creatinine, procalcitonin, APACHE, SOFA, GCS, and CT scores between survivors and non-survivors.
• A predictive model incorporating age, CRP, APACHE score, and CT score achieved 89.9% accuracy.

Conclusions:

• While several parameters individually correlate with mortality, a simplified model using age, CRP, APACHE, and CT score effectively estimates mortality risk.
• These four parameters offer a practical tool for clinicians to optimize treatment strategies and resource allocation in COVID-19 ICUs.