C4.5: programs for machine learning
C4.5: programs for machine learning
A Neural Network Model for Prognostic Prediction
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Data Mining: Concepts and Techniques
Data Mining: Concepts and Techniques
Hi-index | 0.00 |
Accurate prognostic prediction of cancer disease is of crucial importance to the follow-up treatment of the patient. Medical professionals and healthcare providers need such learned estimates to choose appropriate treatments and services. In practice, disease prognosis is often based on physician's clinical experience. Such a prognosis can either be overly optimistic or too conservative. The discrepancy may influence the clinical decision on planning treatments. In order to improve the accuracy of cancer prognosis, methods such as linear programming and neural network had been proposed in the past. This paper presents a case-based Bayesian approach for the recurrence prediction of breast cancer. The experiment data is from the Wisconsin breast cancer dataset. The proposed approach is compared with the CART and the C4.5 methods. The results indicate that our approach is able to produce more effective prediction outcomes. The accuracy rate reaches 98%.