Computer prediction model for health status using classification tree models and Big data digital image
Jing Wang, Gongli Li · 2021 IEEE 3rd International Conference on Civil Aviation Safety and Information Technology (ICCASIT) · 2021
Breast cancer is the most common cancer for females worldwide. The literature presents a comparison of four machine learning algorithms: Classification Tree, Pruned Classification Tree, Bagging, and Random Forests on the Wisconsin Diagnostic Breast Cancer dataset by measuring the test sensitivity, specificity, precision, negative predictive value, and misclassification error rate. The result shows that the performance of pruned classification tree is better than that of a normal classification tree; aggregated tree models (Bagging and Random Forests) are is better than only use one single decision tree to predict. The best tree model is Random Forests which has the lowest test misclassification error rate of 2.92%.