Classification of Atrial Septal Defect and Ventricular Septal Defect with Documented Hemodynamic Parameters via Cardiac Catheterization by Genetic Algorithms and Multi-Layered Artificial Neural Network
Mustafa Yıldız, Ayhan Yüksel, Mehmet Korürek, Ahmet Çağrı Aykan, Banu Şahin Yıldız, Alparslan Şahi̇n, Hakan Hasdemi̇r, Mehmet Özkan
Keywords: Heart catheterization, heart septal defects, ventricular; heart septal defects, atrial; algorithms; neural networks.
Introduction: We aimed to develop a classification method to discriminate ventricular septal defect and atrial septal defect by using several hemodynamic parameters. Patients and Methods: Forty three patients (30 atrial septal defect, 13 ventricular septal defect; 26 female, 17 male) with documented hemodynamic parameters via cardiac catheterization are included to study. Such parameters as blood pressure values of different areas, gender, age and Qp/Qs ratios are used for classification. Parameters, we used in classification are determined by divergence analysis method. Those parameters are; i) pulmonary artery diastolic pressure, ii) Qp/Qs ratio, iii) right atrium pressure, iv) age, v) pulmonary artery systolic pressure, vi) left ventricular sistolic pressure, vii) aorta mean pressure, viii) left ventricular diastolic pressure, ix) aorta diastolic pressure, x) aorta systolic pressure. Those parameters detected from our study population, are uploaded to multi-layered artificial neural network and the network was trained by genetic algorithm. Results: Trained cluster consists of 14 factors (7 atrial septal defect and 7 ventricular septal defect). Overall success ratio is 79.2%, and with a proper instruction of artificial neural network this ratio increases up to 89%. Conclusion: Parameters, belonging to artificial neural network, which are needed to be detected by the investigator in classical methods, can easily be detected with the help of genetic algorithms. During the instruction of artificial neural network by genetic algorithms, both the topology of network and factors of network can be determined. During the test stage, elements, not included in instruction cluster, are assumed as in test cluster, and as a result of this study, we observed that multi-layered artificial neural network can be instructed properly, and neural network is a successful method for aimed classification.