Survey and Classification of Functional Characteristics in Neural Network Technique for the Diagnosis of Ischemic Heart Disease: A Systematic Review

Background: Nowadays, the prevalence of ischemic heart diseases (IHDs) leads to destructive effects such as patient death. Late diagnosis of such diseases as well as their invasive diagnostic approaches made researchers provide a decision support system based on neural network techniques, while using minimum data set for timely diagnosis. In this regard, selecting minimum useful features is significant for designing neural network structure and it paves the way to attain maximum accuracy in obtaining the results. Methods: In this systematic review, valid databases using sensitive keywords were initially searched out to find articles related to "diagnosing the ischemic heart disease using artificial neural networks" and afterwards, scientific methods were used to analyze and classify the content. Findings: Researchers applied various extractable features from demographic data, medical history, signs and symptoms, and paraclinical examinations, to design the neural network structure. Among them, the features obtained from electrocardiographic test, embedded in paraclinical examinations, had led to a remarkable increase of efficiency in neural network. Conclusion: Utilizing such diagnostic decision support systems in practical environments depends on their high confidence coefficient and physicians’ acceptability. Therefore, it can be useful to improve maturity in the design of the neural network structure depending on the choice of the minimum optimal features, and to create required infrastructures to input patients’ real, accurate, and flowing data in these systems.