Prediction of Alzheimer’s Disease using Oasis Dataset
Chandni Naidu1, Dhanush Kumar2, N Maheswari3, M Sivagami4, Gang Li5
1Chandni Naidu, SCSE, Vellore Institute of Technology, Chennai (Tamil Nadu), India.
2Dhanush Kumar, SCSE, Vellore Institute of Technology, Chennai (Tamil Nadu), India.
3N Maheswari, SCSE, Vellore Institute of Technology, Chennai (Tamil Nadu), India.
4M Sivagami, SCSE, Vellore Institute of Technology, Chennai (Tamil Nadu), India.
5Gang Li, School of Information Technology, Deakin University, Australia.
Manuscript received on 22 April 2019 | Revised Manuscript received on 01 May 2019 | Manuscript Published on 07 May 2019 | PP: 36-42 | Volume-7 Issue-6S3 April 2019 | Retrieval Number: F1008376S19/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Alzheimer’s Disease (AD) is hard to predict in the early stage. But giving treatment at an early stage of AD is more effective and causes less damage to people. Various approaches like Random Forest, Support Vector Machine, Gradient Boosting and Lasso Regression have been applied to identify the best parameters for the Alzheimer’s Disease prediction. Accuracy results are tabulated. Alzheimer’s Disease has been predicted using Open Access Series of Imaging Studies (OASIS) dataset. Random Forest has the best accuracy rate of 97.94% and SVM has the least accuracy rate of 93.6%.
Keywords: OASIS; Alzheimer’s Diease; MRI; Random Forest; Gradient Boosting; Lasso; SVM.
Scope of the Article: Regression and Prediction