Ayush2018 - Breast Cancer Detection using SVM and WDBC Dataset

In this study, authors had briefly talked about the comparison of Support Vector Machines (SVM) and Artificial Neural Networks (ANN) for binary classification of cancer. It is concluded that, SVMs perform better on cancer prediction which are not expressed by their genotype whereas ANNs capture the flaws in the other case. In this paper, the author's had provided a good strategy to construct SVM model. The model was coded from their approach and Grid Search method was used for estimation of a better set of parameters. The resulted model had provided better evaluation metrics than the one mentioned in the manuscript. The model is then exported to Open Neural Network Exchange (ONNX) format to avail the model to be accessible in various platforms thereby promoting the FAIReR (Findable, Accessible, Interoperable, Reusable, and Reproducible) protocol for sharing machine learning models. Docker files were provided for both training and testing environment so that the curator can reproduce the results.

The prediction output '0' means the sample is Benign, otherwise its Malignant.