A Two-stage Approach Using Artificial Neural Networks for Diagnosis of Heart Diseases Based on ECG Data

Background and Aim Most heart diseases show symptoms on ECG, but diagnosing disease with ECG requires the knowledge experience of medical specialized. Because these specialists may not always be available, it is necessary to design tools diagnose in situations. In this paper, a two-stage approach based artificial neural networks designed using information.In study, we aim propose network (ANN) data. Methods & Materials To proposed approach, first data 861 patients referred centers Arak, Iran were collected. The examined opinions specialists. Then, 154 features from used as inputs model. stage, an ANN was detect status (usable unusable). second usable data, presence or absence disease. Finally, performance evaluated its accuracy precision determining quality diagnosis determined. Ethical Considerations This study approved by ethics committee Arak University Medical Sciences (Code: IR.ARAKMU.REC.1400.138). Results for had 97.1% 97.3%. 95.8% 95.4%. Conclusion Considering high efficiency disease, possible use help treatment staff.