Accurate prognosis of COVID-19 patient survival is vital for healthcare decision-making. This research proposes a tripartite machine learning approach that integrates K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and XGBoost for outcome prediction. Our hybrid model exploits the strengths of individual algorithms and combines their predictions using a weighted ensemble. Leveraging clinical data, KNN captures local patterns, SVM finds complex boundaries, and XGBoost enhances overall performance. Experimental results show exceptional precision (0.93), recall (0.93), and F1-score (0.93) for both classes, affirming accurate classification of "Alive" and "Died" cases. The achieved accuracy of 0.93 further demonstrates the reliability of the proposed approach. Our tripartite method holds the potential to enhance COVID-19 survival prediction, providing valuable insights for clinical practitioners and policymakers. This study contributes by seamlessly fusing KNN, SVM, and XGBoost models into a robust predictive tool, thereby aiding medical professionals in informed decision-making for patient care and resource allocation. The demonstrated success underscores the efficacy of a combined approach, highlighting its relevance in accurately predicting patient outcomes.
Copyrights © 2023