About half of the people who develop heart failure (HF) die within five years of diagnosis. Over the years, researchers have developed several machine learning-based models for the early prediction of HF and to help cardiologists to improve the diagnosis process. In this paper, we introduce an expert system that stacks two support vector machine (SVM) models for the effective prediction of HF. The first SVM model is linear and L 1 regularized. It has the capability to eliminate irrelevant features by shrinking their coefficients to zero. The second SVM model is L 2 regularized. It is used as a predictive model. To optimize the two models, we propose a hybrid grid search algorithm (HGSA) that is capable of optimizing the two models simultaneously. The effectiveness of the proposed method is evaluated using six different evaluation metrics: accuracy, sensitivity, specificity, the Matthews correlation coefficient (MCC), ROC charts, and area under the curve (AUC). The experimental results confirm that the proposed method improves the performance of a conventional SVM model by 3.3%. Moreover, the proposed method shows better performance compared to the ten previously proposed methods that achieved accuracies in the range of 57.85%-91.83%. In addition, the proposed method also shows better performance than the other state-of-the-art machine learning ensemble models.INDEX TERMS Clinical expert system, feature selection, heart failure prediction, hybrid grid search algorithm, support vector machine.

Different automated decision support systems based on artificial neural network (ANN) have been widely proposed for the detection of heart disease in previous studies. However, most of these techniques focus on the preprocessing of features only. In this paper, we focus on both, i.e., refinement of features and elimination of the problems posed by the predictive model, i.e., the problems of underfitting and overfitting. By avoiding the model from overfitting and underfitting, it can show good performance on both the datasets, i.e., training data and testing data. Inappropriate network configuration and irrelevant features often result in overfitting the training data. To eliminate irrelevant features, we propose to use χ 2 statistical model while the optimally configured deep neural network (DNN) is searched by using exhaustive search strategy. The strength of the proposed hybrid model named χ 2-DNN is evaluated by comparing its performance with conventional ANN and DNN models, another state of the art machine learning models and previously reported methods for heart disease prediction. The proposed model achieves the prediction accuracy of 93.33%. The obtained results are promising compared to the previously reported methods. The findings of the study suggest that the proposed diagnostic system can be used by physicians to accurately predict heart disease. INDEX TERMS Deep neural network, heart disease, hyperparameters optimization, overfitting, underfitting.

No abstract

No abstract