Determining the Malignancy of Breast Cancer Using a Combined Neural Network-Support Vector Machine Scheme

Data mining has been useful in medical diagnosis area. The current research proposes a new combined classification technique based on support vector machine and neural network to determine malignancy of breast cancer tumours. The proposed method uses a meta-heuristic algorithm to find the best weights for combining the results of two aforementioned techniques. The numerical and statistical results confirm the superiority of our model in comparison to the previous methods. Following the results, the best accuracies are 98.23% and 96.85% for proposed and the previous methods, respectively. The method has potential to be implemented as a decision support system for breast cancer diagnosis.