In this chapter, we were able to predict autism in patients with about 90% accuracy. We also learned how to deal with categorical data; a lot of health applications are going to have categorical data and one way to address this is by using one-hot encoded vectors. Furthermore, we learned how to reduce overfitting using dropout regularization.
In this book, we explored how to implement machine learning to analyze various healthcare issues. In the first chapter, we used machine learning to detect cancer in a set of patients using the SVM and KNN models. In the second chapter, we created a deep neural network in Keras to predict the onset of diabetes on a huge dataset of patients. In the third chapter, we predicted whether or not a short sequence of E.coli bacteria DNA was a promoter or a non-promoter, and we used some common classifiers to classify short E. coli DNA sequences...