Advanced COVID-19 Severity Prediction with Differential Weibull Polar Lights Optimizer and Case Study Insights

The COVID-19 pandemic, caused by the SARS-CoV-2 virus, has led to a global health crisis, creating an urgent need for accurate predictive models to forecast disease severity and assist in clinical decision-making. This study presents an innovative machine learning approach, the bDWPLO-FKNN model, to predict the severity of COVID-19 pneumonia in patients. The model integrates the differential Weibull polar lights optimizer (DWPLO), an enhancement of the polar lights optimizer (PLO) with the differential evolution operator and the Weibull flight operator, to perform effective feature selection. The DWPLO's performance was rigorously tested against IEEE CEC 2017 benchmark functions, proving its robust optimization capabilities. The binary version of DWPLO (bDWPLO) was then combined with the fuzzy K-nearest neighbors (FKNN) algorithm to form the predictive model. Utilizing a dataset from the People's Hospital Affiliated with Ningbo University, the model was trained to identify patients at risk of developing severe pneumonia due to COVID-19. The bDWPLO-FKNN model demonstrated exceptional predictive accuracy, with an accuracy of 84.036%, and specificity of 88.564%. The analysis highlighted key predictors, including albumin, albumin to globulin ratio, lactate dehydrogenase, urea nitrogen, gamma-glutamyl transferase, and inorganic phosphorus, which were significantly associated with disease severity. The integration of DWPLO with FKNN not only enhances feature selection but also improves the model's predictive power, offering a valuable tool for clinicians to assess patient risk and allocate healthcare resources effectively during the COVID-19 pandemic.