Designing a Hybrid Artificial Intelligent Clinical Decision Support System Using Artificial Neural Network and Artificial Bee Colony for Predicting Heart Failure Rate

Abstract

Health Care sector profoundly have found use for Artificial Intelligent Clinical Decision Support Systems (AI- CDSS) in making critical decisions using the prediction results of these systems. The minimizations of medical errors are the result of continuous diagnosis process that assists in making more informed and efficient decisions. However, the conventional Artificial Intelligence methodologies are not efficient enough to diagnose or predict heart failure rate in the absence of heart specialists. The paper proposes a hybrid model of Optimized Artificial Neural Network-Artificial Bee Colony (ABC) that could be employed to improve the prediction by using machinelearning approach to obtain the precise diagnosis of heart. Consequently, the proposed method also measures and compares the accuracy by improving the existing AI-CDSS prediction. In addition, the concordance rate between proposed hybrid AI- CDSS and state of art methods in Heart Failure (HF) was measured. The model provides a better accuracy for concordance rate with 99.3% proving that high diagnostic accuracy is obtained for the interpretation of heart failure than the existing conventional methods.