Machine Learning Approach for Identifying Anatomical Biomarkers of Early Mild Cognitive Impairment - Full Paper

Aug 3, 2026

Uploaded by Oliver

Alzheimer’s Disease requires early identification to support effective intervention, and MRI offers a practical, cost-effective basis for biomarker research. This study performs comprehensive analysis of machine learning methods for MRI-based biomarker selection and classification of early cognitive decline. Healthy controls stable over five years are contrasted with those who progressed to mild cognitive impairment. 3T MRI data from ADNI and OASIS-3 are processed with Freesurfer and evaluated using nested cross-validation, Bayesian optimization, harmonization, and standard performance metrics.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages97

Reading Time4 h 4 min

AccessFree to download

Abstract

Background and Objective

Methods

Results

Conclusion

Introduction

Machine Learning Approach for Identifying Anatomical Biomarkers of Early Mild Cognitive Impairment Alwani Liyana Ahmad 1,2,3 , Jose Sanchez-Bornot4, Roberto C. Sotero5, Damien Coyle6, Zamzuri Idris2,3,7, Ibrahima Faye 1,8, *, for the Alzheimer’s Disease Neuroimaging Initiative© 1 Department of Fundamental and Applied Sciences, Faculty of Science and Information Technology, Universiti Teknologi PETRONAS, Perak, Malaysia. 2 Department of Neurosciences, Hospital Universiti Sains Malaysia, Kelantan, Malaysia. 3 Brain and Behaviour Cluster, School of Medical Sciences, Universiti Sains Malaysia, Kelantan, Malaysia 4 Intelligent Systems Research Centre, School of Computing, Engineering and Intelligent Systems, Ulster University, Magee campus, Derry~Londonderry, BT48 7JL, UK. 5 Department of Radiology and Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada. 6 The Bath Institute for the Augmented Human, University of Bath, Bath, BA2 7AY, UK. 7 Department of Neurosciences, School of Medical Sciences, Universiti Sains Malaysia, Kelantan, Malaysia 8 Centre for Intelligent Signal & Imaging Research (CISIR), Universiti Teknologi PETRONAS, Perak, Malaysia. ©Data used in preparation of this article were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database ([adni.loni.usc.edu](adni.loni.usc.edu)). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete listing of ADNI investigators can be found at: [http://adni.loni.usc.edu/wpcontent/uploads/how_to_apply/ADNI_Acknowledgement_List.pdf](http://adni.loni.usc.edu/wpcontent/uploads/how_to_apply/ADNI_Acknowledgement_List.pdf). Corresponding Author: Ibrahima Faye 1,8 Universiti Teknologi PETRONAS, Perak, 32610, Malaysia Email address: [ibrahima_faye @utp.edu.my](ibrahima_faye @utp.edu.my) Abstract Background. Alzheimer's Disease (AD) represents a significant challenge in neurodegenerative disorders, necessitating early detection for effective intervention. Among neuroimaging methods, magnetic resonance imaging (MRI) is widely used because it is easy to apply in clinical practice and cost-effective, making it crucial for studying AD. Objective. This study aims to perform a comprehensive analysis of machine learning (ML) methods used in MRI-based biomarker selection and classification analysis. The goal is to study AD-related early cognitive decline by discriminating between healthy control (HC) participants who stayed stable and those unstable (uHC) who developed mild cognitive impairment (MCI) within five years. Methods. We utilized 3-Tesla (3T) MRI data from the Alzheimer's Disease Neuroinformatic Initiative (ADNI) and the Open Access Series of Imaging Studies 3 (OASIS-3), focusing on HC and uHC. Freesurfer’s recon-all, among other tools, was used to extract MRI-based anatomical biomarkers corresponding to semi-automatic segmented subcortical and cortical brain regions. We applied various ML techniques to select features and classify the data. These included methods from preliminary analysis performed in the MATLAB Classification Learner (MCL) app and more sophisticated methods like nested cross-validation and Bayesian optimization implemented in a customized pipeline to enhance classification performance for balanced and imbalanced datasets. Our pipeline was applied to both original imbalanced and randomly balanced datasets within a Monte Carlo analysis. Moreover, we implemented data harmonization approaches based on polynomial regression that enhanced the performance of ML and statistical methods. Complementary performance metrics, such as Accuracy (Acc), area under receiver operating characteristic curve (AROC), F1 score, and Matthew’s correlation coefficient (MCC), were used to evaluate the assessed methodologies. Results. In feature selection analyses, consistent outcomes were obtaine

FAQs

What problem does this study address in Alzheimer’s disease research?

It targets early detection of cognitive decline by identifying anatomical biomarkers and training ML models using MRI data.

How are the MRI data and brain regions used for biomarker selection?

3T MRI from ADNI and OASIS-3 is processed with Freesurfer (recon-all) to extract anatomical biomarkers from semi-automatically segmented cortical and subcortical regions.

Which ML and harmonization approaches influenced classification performance?

Polynomial-regression harmonization improved consistency and performance, while different models (e.g., Naïve Bayes, SVM, Logistic regression, RUSBoost) performed best depending on balanced vs imbalanced datasets and which dataset (ADNI vs OASIS-3) was used.

Aug 3, 2026

Uploaded by Oliver