Neural Network Applications in Understanding Neurodegenerative Disease Progression

Abstract

Neurodegenerative diseases are a group of chronic progressive disorders characterized by the gradual degeneration of the structure and function of the affected nervous system. The two main components of the nervous system are the brain and spinal cord. Many neurodegenerative diseases, including Alzheimer's, Parkinson's, and spinocerebellar ataxia, can damage these areas and consequently affect memory, thought, and language. Moreover, there is no cure for these destructive diseases, and they are becoming more common due to population aging. Growing awareness of the risk factors and improving diagnostic technology have led to progress in the initiation and development of different investigational interventions. Artificial Neural Networks are a simplified model of the human brain's decision-making structure and have been extensively used in a wide range of medical applications.

Although the application of Artificial Neural Networks assists with various stages of research, its utility in the comprehension of neurodegenerative disease progression and management is largely untapped. This paper seeks to evaluate the existing applications of Artificial Neural Networks in Alzheimer's, Parkinson's, and spinocerebellar ataxia to determine the readiness of Artificial Neural Networks to support advanced progress in understanding neurodegenerative diseases and to help researchers know where to focus on preparing the application of Artificial Neural Networks in the management of different stages of neurodegenerative diseases. The results suggest that several prediction models have been developed from Artificial Neural Networks that can identify individuals at risk for Alzheimer's and Parkinson's, the progression of Alzheimer's, spinocerebellar ataxia, and Parkinson's. However, there is no model to identify the stages of the process of neurodegenerative diseases.