The Effect of Features on Dementia Detection Accuracy
CSEF · 2013 Mathematics & Software
Overview
Objectives/Goals 13% of people above age 65 have dementia. The objective of my project is to detect dementia presence from MRI data through machine learning. In my work, I used the OASIS dataset. This dataset includes MRI data for 436 patients and other features for each patient, like gender and dementia rating. Methods/Materials First, I read the MRI data into MATLAB. My MATLAB code counts different voxels and computes features like the amount of white matter in the brain. I designed a new feature for symmetry along various axes that weights different brain matter equally. Then, using a Python program, I combine these features with the feature values from the original dataset into a form that I can input into a machine learning algorithm. Results The machine learning algorithm, called Support Vector Machine (SVM), takes the feature values and graphs it. Then, it finds a plane of best fit separating the dementia patients and the non-dementia patients. This algorithm is applied repeatedly to different test sets, and the accuracy is recorded and averaged and found to be 86.3%. Conclusions/Discussion My accuracy of detecting dementia is 86.3%, 1.6% higher than previous studies. This result is obtained primarily due to my new symmetry feature. My work can help develop radiologist's tools that can filter and prioritize dementia cases requiring further human review.
Summary statement
My project detects presence of dementia in humans from MRI data using machine learning
Help received
My advisor Mr Jason Robertson helped me find the OASIS dataset. My father helped me install Matlab and learn Python and machine learning.
Competition history
- CSEF 2013
Resources
Related projects
CSEF · 2015
Automated Diagnosis of Alzheimer's Using MRI Images
CSEF · 2018
Early Classification of Alzheimer's Disease Using Machine Learning
AJAS · 2017
Automated Diagnosis of Dementia Through Supervised Learning Classification Algorithm
CSEF · 2019
Implementation and Validation of a Machine Learning Model for the Early Detection of Alzheimer's Disease
CSEF · 2023
Using a Convolutional Neural Network to Classify the Progression of Alzheimer's Patients MRI's.
ISEF · 2018
Early Diagnosis of Alzheimer's Disease Using Machine Learning
CWSF · 2026
AD-istics: A Machine Learning Framework for Optimized Detection of Dementia and Alzheimer's Disease
ISEF · 2024
Beyond Scans: Predicting Alzheimer's Through MRI and Handwriting Analysis
Closest projects by meaning, across every fair and year in the corpus.
Browse more like this
Source: California Science & Engineering Fair public projects