Copyright Statement: This is an open access article licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, even commercially as long as the original work is properly cited.
Digital Object Identifier (DOI) : 10.14569/IJACSA.2017.081216
Article Published in International Journal of Advanced Computer Science and Applications(IJACSA), Volume 8 Issue 12, 2017.
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.
Syed Asif Hassan and Tabrej Khan, “A Machine Learning Model to Predict the Onset of Alzheimer Disease using Potential Cerebrospinal Fluid (CSF) Biomarkers” International Journal of Advanced Computer Science and Applications(IJACSA), 8(12), 2017. http://dx.doi.org/10.14569/IJACSA.2017.081216