Utilization of artificial neural networks and autoregressive modeling in diagnosing mitral valve stenosis

• Published in: Computers in biology and medicine Vol. 36; no. 5; pp. 473 - 483
• Main Authors: Kara, Sadık, Güven, Ayşegül, Okandan, Mustafa, Dirgenali, Fatma
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.05.2006
• Subjects: Adult; Algorithms; Artificial Intelligence; Artificial neural networks; Autoregressive modeling; Back propagation algorithm; Computer Simulation; Constriction, Pathologic - pathology; False Positive Reactions; Female; Humans; Levenberg Marquart method; Male; Mitral valve stenosis; Mitral Valve Stenosis - diagnosis; Mitral Valve Stenosis - pathology; Neural Networks (Computer); Pattern Recognition, Automated; Regression Analysis; Sensitivity and Specificity; Signal Processing, Computer-Assisted; Mitral valve stenosis; Autoregressive modeling; Back propagation algorithm; Levenberg Marquart method; Artificial neural networks
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2005.01.007

This research is concentrated on the diagnosis of mitral heart valve stenosis through the analysis of Doppler Signals’ AR power spectral density graphic with the help of ANN. Multilayer feedforward ANN trained with a Levenberg Marquart backpropagation algorithm was implemented in the MATLAB environment. Correct classification of 94% was achieved, whereas 4 false classifications have been observed for the test group of 68 subjects in total. The designed classification structure has about 97.3% sensitivity, 90.3% specifity and positive prediction is calculated to be 92.3%. The stated results show that the proposed method can make an effective interpretation.