Home // International Journal On Advances in Life Sciences, volume 6, numbers 3 and 4, 2014 // View article

Using Neural Networks and Feature Selection Algorithms in the Identification of Protein Signatures for the Prediction of Alzheimer's Disease

Authors:
Lara Dantas
Mêuser Valença

Keywords: Neural Networks, Alzheirmer’s Disease, Feature Selection Algorithms.

Abstract:
Alzheimer's Disease is now considered the most common type of dementia in the population. Although, it is a degenerative and irreversible disease, if diagnosed early, medications may be administered to slow the progression of symptoms and provide a better quality of life for the patient. Ray et al., and Gòmez and Moscato conducted studies with classifiers contained in the software Weka using a database with values of 120 blood proteins, and they noticed that they could classify the patient may or may not be diagnosed with AD with an accuracy rate of 93% and 65%, respectively. Thus, this study aims to use neural networks such as Multi-layer Perceptron, Extreme-learning Machine and Reservoir Computing to perform early diagnosis of a patient with or without AD. This article also envisions to utilize the Random Forest Algorithm to select proteins from the original set and, therefore, create a new protein signature. Through experiments it can be concluded that the best performance was obtained with the Multi-layer Perceptron and the new signatures created achieved better results than those available in the literature.

Pages: 373 to 382

Copyright: Copyright (c) to authors, 2014. Used with permission.

Publication date: December 30, 2014

Published in: journal

ISSN: 1942-2660