Scholarlink

The COVID-19 pandemic has highlighted the vital importance of data-driven healthcare solutions, especially for risk assessment and disease diagnosis. This study evaluates six machine learning classifiers Decision Tree, Random Forest (RF), Gradient Boosting, XGBoost, Stacking, and AdaBoost to identify the most effective model for classifying COVID-19 patient outcomes. The dataset includes demographic information, medical history, and symptom-related features, enabling comprehensive predictive analysis. To assess model robustness and generalizability, both 5-fold and 10-fold cross-validation were applied. Among the classifiers, Stacking achieved the highest accuracy, reaching 99.7% with 10-fold CV and 99.2% with 5-fold CV, followed by XGBoost and Gradient Boosting. Random Forest achieved an AUC of 1.000, while Decision Tree and AdaBoost exhibited comparatively lower accuracy.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Stacking and Ensemble-Based Machine Learning for COVID-19 Diagnosis and Risk Assessment

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Prince Jain,
  • Pujita Bhatt,
  • Jaivik Pathak,
  • Unnati Joshi,
  • Anand Joshi

摘要

The COVID-19 pandemic has highlighted the vital importance of data-driven healthcare solutions, especially for risk assessment and disease diagnosis. This study evaluates six machine learning classifiers Decision Tree, Random Forest (RF), Gradient Boosting, XGBoost, Stacking, and AdaBoost to identify the most effective model for classifying COVID-19 patient outcomes. The dataset includes demographic information, medical history, and symptom-related features, enabling comprehensive predictive analysis. To assess model robustness and generalizability, both 5-fold and 10-fold cross-validation were applied. Among the classifiers, Stacking achieved the highest accuracy, reaching 99.7% with 10-fold CV and 99.2% with 5-fold CV, followed by XGBoost and Gradient Boosting. Random Forest achieved an AUC of 1.000, while Decision Tree and AdaBoost exhibited comparatively lower accuracy.