Related Experiment Video
Updated: Jul 15, 2026
The 4 Mountains Test: A Short Test of Spatial Memory with High Sensitivity for the Diagnosis of Pre-dementia Alzheimer's Disease
Published on: October 13, 2016
Alzheimer's Disease Diagnosis Based on Cortical and Subcortical Features
Yubraj Gupta1,2, Kun Ho Lee3,2, Kyu Yeong Choi2
1School of Information Communication Engineering, Chosun University, 309 Pilmun-Daero, Dong-Gu, Gwangju 61452, Republic of Korea.
Abstract:
Alzheimer's disease (AD) is a common neurodegenerative disease with an often seen prodromal mild cognitive impairment (MCI) phase, where memory loss is the main complaint progressively worsening with behavior issues and poor self-care. However, not all patients clinically diagnosed with MCI progress to the AD. Currently, several high-dimensional classification techniques have been developed to automatically distinguish among AD, MCI, and healthy control (HC) patients based on T1-weighted MRI. However, these method features are based on wavelets, contourlets, gray-level co-occurrence matrix, etc., rather than using clinical features which helps doctors to understand the pathological mechanism of the AD. In this study, a new approach is proposed using cortical thickness and subcortical volume for distinguishing binary and tertiary classification of the National Research Center for Dementia dataset (NRCD), which consists of 326 subjects. Five classification experiments are performed: binary classification, i.e., AD vs HC, HC vs mAD (MCI due to the AD), and mAD vs aAD (asymptomatic AD), and tertiary classification, i.e., AD vs HC vs mAD and AD vs HC vs aAD using cortical and subcortical features. Datasets were divided in a 70/30 ratio, and later, 70% were used for training and the remaining 30% were used to get an unbiased estimation performance of the suggested methods. For dimensionality reduction purpose, principal component analysis (PCA) was used. After that, the output of PCA was passed to various types of classifiers, namely, softmax, support vector machine (SVM), k-nearest neighbors, and naïve Bayes (NB) to check the performance of the model. Experiments on the NRCD dataset demonstrated that the softmax classifier is best suited for the AD vs HC classification with an F1 score of 99.06, whereas for other groups, the SVM classifier is best suited for the HC vs mAD, mAD vs aAD, and AD vs HC vs mAD classifications with the F1 scores being 99.51, 97.5, and 99.99, respectively. In addition, for the AD vs HC vs aAD classification, NB performed well with an F1 score of 95.88. In addition, to check our proposed model efficiency, we have also used the OASIS dataset for comparing with 9 state-of-the-art methods.
Insights
This study introduces a novel approach using brain imaging features to accurately classify Alzheimer's disease (AD) and mild cognitive impairment (MCI). The findings highlight specific machine learning models for precise diagnosis, aiding early detection and intervention strategies.
Area of Science:
- Neuroimaging and computational neuroscience
- Medical diagnostics and machine learning
Background:
- Alzheimer's disease (AD) is a progressive neurodegenerative disorder often preceded by mild cognitive impairment (MCI).
- Accurate differentiation between AD, MCI, and healthy controls (HC) is crucial for timely intervention.
- Current MRI-based classification methods often rely on complex features, lacking clinical interpretability.
Purpose of the Study:
- To develop and evaluate a novel classification approach for distinguishing between Alzheimer's disease (AD), mild cognitive impairment (MCI), and healthy controls (HC) using neuroimaging features.
- To compare the performance of various machine learning classifiers (softmax, SVM, k-NN, NB) for binary and tertiary classifications.
- To assess the clinical utility of cortical thickness and subcortical volume measurements in AD diagnosis.
Main Methods:
- Utilized cortical thickness and subcortical volume data from the National Research Center for Dementia (NRCD) dataset (326 subjects).
- Employed Principal Component Analysis (PCA) for dimensionality reduction.
- Trained and tested binary (AD vs HC, HC vs MCI due to AD, MCI due to AD vs asymptomatic AD) and tertiary (AD vs HC vs MCI due to AD, AD vs HC vs asymptomatic AD) classifiers.
- Validated model performance using a 70/30 train/test split and F1 scores, comparing with state-of-the-art methods on the OASIS dataset.
Main Results:
- Softmax classifier achieved 99.06% F1 score for AD vs HC classification.
- Support Vector Machine (SVM) classifier excelled in HC vs MCI due to AD (99.51%), MCI due to AD vs asymptomatic AD (97.5%), and AD vs HC vs MCI due to AD (99.99%) classifications.
- Naïve Bayes (NB) demonstrated strong performance for AD vs HC vs asymptomatic AD classification (95.88% F1 score).
- The proposed model showed competitive results when compared with existing methods on the OASIS dataset.
Conclusions:
- Cortical thickness and subcortical volume are effective neuroimaging biomarkers for classifying AD and MCI.
- Specific machine learning models (softmax, SVM, NB) show high accuracy in differentiating cognitive states.
- This approach offers a promising, clinically relevant tool for early and accurate diagnosis of Alzheimer's disease and its prodromal stages.
Related Concept Videos
01:26Alzheimer's Disease: Overview
The clinical diagnosis of AD hinges on the presence of memory and other cognitive impairments. Biomarkers, such as changes in Aβ and tau...
01:22Alzheimer's Disease: Treatment
01:30Dementia
The progression of dementia is generally gradual.
01:29Alzheimer Disease l: Introduction
01:23Alzheimer Disease ll: Pathophysiology
01:22Dementia l: Introduction