A Machine Learning Model to Predict the Onset of Alzheimer Disease using Potential Cerebrospinal Fluid (CSF) Biomarkers
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2017, Vol 8, Issue 12
Abstract
Clinical studies in the past have shown that the pathology of Alzheimer’s disease (AD) initiates, 10 to 15 years before the visible clinical symptoms of cognitive impairment starts to appear in AD diagnosed patients. Therefore, early diagnosis of the AD using potential early stage cerebrospinal fluid (CSF) biomarkers will be valuable in designing a clinical trial and proper care of AD patients. Therefore, the goal of our study was to generate a classification model to predict earlier stages of the AD using specific early-stage CSF biomarkers obtained from a clinical Alzheimer dataset. The dataset was segmented into variable sizes and classification models based on three machine learning (ML) algorithms, such as Sequential Minimal Optimization (SMO), Naïve Bayes (NB), and J48 were generated. The efficacy of the models to accurately predict the cognitive impairment status was evaluated and compared using various model performance parameters available in Weka software tool. The current findings show that J48 based classification model can be effectively employed for classifying cognitive impaired Alzheimer patient from normal healthy individuals with an accuracy of 98.82%, area under curve (AUC) value of 0.992 and sensitivity & specificity of 99.19% and 97.87%, respectively. The sample size (60% training and 40% independent test data) showed significant improvement in T-test with J48 algorithm when compared with other classifiers tested on Alzheimer dataset.
Authors and Affiliations
Syed Asif Hassan, Tabrej Khan
Keywords
Related Articles
- EP ID EP258309
- DOI 10.14569/IJACSA.2017.081216
- Views 67
- Downloads 0
A Nested Genetic Algorithm for Mobile Ad-Hoc Network Optimization with Fuzzy Fitness
One of the major culprits that faces Mobile Ad-hoc networks (MANET) is broadcasting, which constitutes a very important part of the infrastructure of such networks. This paper presents a nested genetic algorithm (GA) tec...
A Novel Design for XOR Gate used for Quantum-Dot Cellular Automata (QCA) to Create a Revolution in Nanotechnology Structure
Novel digital technologies always lead to high density and very low power consumption. One of these concepts is Quantum-dot Cellular Automata (QCA), which is one of the new emerging nanotechnology-based on Coulomb repuls...
An Efficient Image Haze Removal Algorithm based on New Accurate Depth and Light Estimation Algorithm
Single image Dehazing has become a challenging task for a variety of image processing and computer applications. Many attempts have been devised to recover faded colors and improve image contrast. Such methods, however,...
Proposal of Automatic Methods for the Reuse of Software Components in a Library
The increasing complexity of applications is constraining developers to use reusable components in component markets and mainly free software components. However, the selected components may partially satisfy the require...
Timed-Release Certificateless Encryption
Timed-Release Encryption(TRE) is an encryption mechanism that allows a receiver to decrypt a ciphertext only after the time that a sender designates. In this paper, we propose the notion of Timed-Release Certificateless...