Data-Driven Models for COVID-19 Severity Analysis in Comorbid Patients

This book presents a comprehensive Artificial Intelligence driven framework for predicting COVID-19 severity in patients with comorbidities, addressing critical challenges in diagnosis, prognosis, and healthcare resource management. It integrates Machine Learning and Deep Learning techniques to analyze large-scale clinical, demographic, and medical imaging data. Imbalanced clinical datasets are handled using advanced preprocessing and resampling strategies, enabling robust prediction of mortality, survival, and disease severity. The book serves as a comprehensive guide for researchers, data scientists, and healthcare professionals interested in AI-based Prediction of COVID-19 Severity in Patients with Comorbidities. It highlights that classical Machine Learning models, including Decision Tree, Random Forest, and Gaussian Naïve Bayes, achieve high precision, while neural network-based models demonstrate strong generalization and robustness.