Artificial Neural Network based Classification ...

Neurodegenerative disease occurs due to deterioration of cells specially the myelin sheath of the neurons; of brain, spinal cord, and peripheral nerves. The economic and social burden of neurodegenerative diseases is massive and rising too rapidly. Among several of different neurodegenerative disorders, present work is focused on the three most common; Alzheimer’s disease, Parkinson’s disease, and Huntington’s disease. Although the most consistent risk factor for developing a neurodegenerative disorders is increasing age, it has been observed that the symptoms of all the three diseases overlap with each other, clinically and pathologically. Therefore, their practical classification is quite challenging and thus needing an automated tool to classify them. In the present model, backpropagation artificial neural network (ANN) has been designed to classify neurodegenerative disorders according to their symptoms. The 27:70:3 architecture of ANN has been used to predict the clinical outcome from the complex overlapped symptoms that are routinely available to clinicians. The model has found to be effective in differentiating the different types of focused diseases with an overall performance of 96.42%.