Recommender system: prediction/diagnosis of breast cancer using hybrid machine learning algorithm.

Breast cancer is the second popular cause of the women's death. There are some existing techniques for identifying the breast cancer and one of them is mammography screening, for identifying the breast cancer under the age of 40 to 50 years. For medical diagnosis applications such as breast cancer, the recommender system is very helpful. There is a large number of records or datasets available for diagnosis of human diseases. In this article, we have presented an in-depth study of breast cancer predictions to take the remedial actions. Then experiments are carried out in Microsoft Azure on the breast cancer dataset which is available on Kaggle. The training and testing are done on 70% and 30% of the data. The evaluations are conducted by using machine learning algorithms, Locally Deep SVM, Boosted Decision Tree, Averaged Perception, Bayes Point and Decision Forest to predict Breast Cancer. We conducted an experiment on 18 K breast cancer image dataset. A hybrid machine learning algorithm (HMLA) based on decision tree and average perceptron algorithms is proposed. Based on the experimental evaluation, it is analyzed that proposed algorithm has performed well with 98.1% of accuracy and predicting the accurate results with 95.0% of sensitivity and specificity of 99.0% on the Breast Cancer prediction. [ABSTRACT FROM AUTHOR]