Forecast Model of Breast Cancer Diagnosis Based on RF-AdaBoost
Yifan Duan, Jialin Lu, Feng Boxi
Abstract
Breast cancer is a female malignant tumor with the highest incidence, which seriously affects women's health. Therefore, early and accurate diagnosis of breast cancer patients is particularly crucial. This paper took the Wisconsin female breast cancer tumor data set as the research object, through the integration of Random Forest and AdaBoost algorithms, proposed a breast cancer classification prediction model that can give a diagnosis result of benign or malignant. Finally, compared the model with single Support Vector Machine, Logistic Regression, K-Nearest Neighbor, Decision Tree algorithms. The test results have shown that the ensemble model's prediction accuracy has been increased by 4.3% on average compared to the single algorithm models, with the highest increase up to 9.8%, which has provided a new reference model for breast cancer prediction.