Predictive Modeling of Infectious Disease Dynamics Using Hybrid Approach

Modern healthcare generates vast amounts of clinical data stored in medical databases. Extracting meaningful information from this data and making informed decisions for disease diagnosis and treatment has become increasingly essential. In this study, we propose a Covid-19 infection prediction system designed to assist in preventing fatalities. The system analyzes patient records to identify effective treatments and deliver improved outcomes. The proposed framework provides physicians with a powerful tool to make data-driven decisions by utilizing historical datasets for analysis. The study employs various data mining algorithms to predict Covid-19 infections and evaluate the most effective prediction method. The predictive accuracy of Naïve Bayes, Support Vector Machine (SVM), and a hybrid approach was assessed. Experimental results reveal that the hybrid model delivers superior performance compared to the individual algorithms, achieving higher accuracy in Covid-19 prediction.