A Stack Based Multimodal Machine Learning Model for Breast Cancer Diagnosis

Breast cancer is the most frequent type of cancer, and it has a dismal prognosis. It represents about 30 % (or 1 in 3) of all new female cancers each year. As a result, there is a pressing need to create efficient and quick computational approaches for breast cancer prognosis. In this study, a multimodal deep learning model that enables decision-making on data from multiple data sources is proposed and used with three different classifiers. We achieved 82% accuracy in decision trees, 90% in random forests and 88% in support vector machines. We have seen that the results we get from the combined data are more successful than the distinct convolutional neural network models we have run separately before. Combining diverse data sources for the successful application of multimodal deep learning algorithms appears to be an effective strategy to improve human breast cancer prediction performance.