Early Detection of Adult Valve Disease–Mitral Stenosis Using The Elman Artificial Neural Network

In complex, data-based prediction problems, such as medical diagnosis, the Elman Neural Net (ENN) has been applied for the automated detection of various diseases, such as mitral valve stenosis. This paper discusses the design and implementation of an automated classification system for heart diseases, based on ultrasonic devices. M-mode class images are applied to classify the degree of stenosis in the mitral valve. An artificial neural network (ANN), trained by the ENN, demonstrated good performance of the designed system. The system is applied in adult patients 20-60 years old, both male and female. Matlab software is used to design the system used to diagnose. The objective of the system used in our work is to diagnose mitral valve stenosis in samples of echocardiograph images for which there are difficulties in practical experiments in finding the optimal features by specialists who work in laboratories.