Comparative Analysis of Decision Trees on Two COVID-19 Symptom Datasets

Abstract

AbstractObjectiveThis study compares decision trees on two COVID-19 symptom datasets to assess their performance and feature importance in predicting and understanding infection patterns.MethodsWe created decision trees on Israeli and Swedish COVID-19 infection datasets. Performance metrics were used to assess their predictive capabilities, and feature importance analysis identified significant variables in the decision-making process.ResultsThe study observed different performance levels of decision trees on the COVID-19 datasets. The Swedish dataset achieved high accuracy and F1-score without hyperparameter tuning, while the Israeli dataset improved significantly with Extreme Gradient Boosting. Dataset characteristics impact the selection of an optimal decision tree algorithm. The key variable in both datasets was sore throat.ConclusionThis study compares decision trees on COVID-19 infection datasets, emphasizing the importance of dataset characteristics in selecting an optimal algorithm. Identifying significant features enhances understanding of infection patterns, benefiting decision-making and prediction accuracy in infectious disease analysis.