This experiment uses the Heart Disease dataset from the UCI Machine Learning repository to train a model for heart disease prediction.
The Heart Disease prediction dataset is used from the UCI Machine Learning repository to develop two models, a neural network and a two class boosted decision tree. The two class boosted decision tree yields a higher accuracy in predicting the readmission flag, which has been provided in the training data. Appropriate splits of the dataset to training, validation and test data are also taken into consideration. Accuracy achieved ~88%.