A machine learning approach for identifying anatomical biomarkers of early mild cognitive impairment
Background Alzheimer’s Disease (AD) poses a major challenge as a neurodegenerative disorder, and early detection is critical for effective intervention. Magnetic resonance imaging (MRI) is a critical tool in AD research due to its availability and cost-effectiveness in clinical settings. Objective T...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2024-12-01
|
| Series: | PeerJ |
| Subjects: | |
| Online Access: | https://peerj.com/articles/18490.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846121677723795456 |
|---|---|
| author | Alwani Liyana Ahmad Jose M. Sanchez-Bornot Roberto C. Sotero Damien Coyle Zamzuri Idris Ibrahima Faye |
| author_facet | Alwani Liyana Ahmad Jose M. Sanchez-Bornot Roberto C. Sotero Damien Coyle Zamzuri Idris Ibrahima Faye |
| author_sort | Alwani Liyana Ahmad |
| collection | DOAJ |
| description | Background Alzheimer’s Disease (AD) poses a major challenge as a neurodegenerative disorder, and early detection is critical for effective intervention. Magnetic resonance imaging (MRI) is a critical tool in AD research due to its availability and cost-effectiveness in clinical settings. Objective This study aims to conduct a comprehensive analysis of machine learning (ML) methods for MRI-based biomarker selection and classification to investigate early cognitive decline in AD. The focus to discriminate between classifying healthy control (HC) participants who remained stable and those who developed mild cognitive impairment (MCI) within five years (unstable HC or uHC). Methods 3-Tesla (3T) MRI data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and Open Access Series of Imaging Studies 3 (OASIS-3) were used, focusing on HC and uHC groups. Freesurfer’s recon-all and other tools were used to extract anatomical biomarkers from subcortical and cortical brain regions. ML techniques were applied for feature selection and classification, using the MATLAB Classification Learner (MCL) app for initial analysis, followed by advanced methods such as nested cross-validation and Bayesian optimization, which were evaluated within a Monte Carlo replication analysis as implemented in our customized pipeline. Additionally, polynomial regression-based data harmonization techniques were used to enhance ML and statistical analysis. In our study, ML classifiers were evaluated using performance metrics such as Accuracy (Acc), area under the receiver operating characteristic curve (AROC), F1-score, and a normalized Matthew’s correlation coefficient (MCC′). Results Feature selection consistently identified biomarkers across ADNI and OASIS-3, with the entorhinal, hippocampus, lateral ventricle, and lateral orbitofrontal regions being the most affected. Classification results varied between balanced and imbalanced datasets and between ADNI and OASIS-3. For ADNI balanced datasets, the naíve Bayes model using z-score harmonization and ReliefF feature selection performed best (Acc = 69.17%, AROC = 77.73%, F1 = 69.21%, MCC’ = 69.28%). For OASIS-3 balanced datasets, SVM with zscore-corrected data outperformed others (Acc = 66.58%, AROC = 72.01%, MCC’ = 66.78%), while logistic regression had the best F1-score (66.68%). In imbalanced data, RUSBoost showed the strongest overall performance on ADNI (F1 = 50.60%, AROC = 81.54%) and OASIS-3 (MCC’ = 63.31%). Support vector machine (SVM) excelled on ADNI in terms of Acc (82.93%) and MCC’ (70.21%), while naïve Bayes performed best on OASIS-3 by F1 (42.54%) and AROC (70.33%). Conclusion Data harmonization significantly improved the consistency and performance of feature selection and ML classification, with z-score harmonization yielding the best results. This study also highlights the importance of nested cross-validation (CV) to control overfitting and the potential of a semi-automatic pipeline for early AD detection using MRI, with future applications integrating other neuroimaging data to enhance prediction. |
| format | Article |
| id | doaj-art-d4eec1612064472187cecc3d06c5467a |
| institution | Kabale University |
| issn | 2167-8359 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ |
| spelling | doaj-art-d4eec1612064472187cecc3d06c5467a2024-12-15T15:05:10ZengPeerJ Inc.PeerJ2167-83592024-12-0112e1849010.7717/peerj.18490A machine learning approach for identifying anatomical biomarkers of early mild cognitive impairmentAlwani Liyana Ahmad0Jose M. Sanchez-Bornot1Roberto C. Sotero2Damien Coyle3Zamzuri Idris4Ibrahima Faye5Department of Fundamental and Applied Sciences, Faculty of Science and Information Technology, Universiti Teknologi PETRONAS, Seri Iskandar, Perak, MalaysiaIntelligent Systems Research Centre, School of Computing, Engineering and Intelligent Systems, Ulster University, Magee Campus, Derry Londonderry, United KingdomDepartment of Radiology and Hotchkiss Brain Institute, University of Calgary, Calgary, Alberta, CanadaThe Bath Institute for the Augmented Human, University of Bath, Bath, United KingdomDepartment of Neurosciences, Hospital Pakar Universiti Sains Malaysia, Kubang Kerian, Kelantan, MalaysiaDepartment of Fundamental and Applied Sciences, Faculty of Science and Information Technology, Universiti Teknologi PETRONAS, Seri Iskandar, Perak, MalaysiaBackground Alzheimer’s Disease (AD) poses a major challenge as a neurodegenerative disorder, and early detection is critical for effective intervention. Magnetic resonance imaging (MRI) is a critical tool in AD research due to its availability and cost-effectiveness in clinical settings. Objective This study aims to conduct a comprehensive analysis of machine learning (ML) methods for MRI-based biomarker selection and classification to investigate early cognitive decline in AD. The focus to discriminate between classifying healthy control (HC) participants who remained stable and those who developed mild cognitive impairment (MCI) within five years (unstable HC or uHC). Methods 3-Tesla (3T) MRI data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and Open Access Series of Imaging Studies 3 (OASIS-3) were used, focusing on HC and uHC groups. Freesurfer’s recon-all and other tools were used to extract anatomical biomarkers from subcortical and cortical brain regions. ML techniques were applied for feature selection and classification, using the MATLAB Classification Learner (MCL) app for initial analysis, followed by advanced methods such as nested cross-validation and Bayesian optimization, which were evaluated within a Monte Carlo replication analysis as implemented in our customized pipeline. Additionally, polynomial regression-based data harmonization techniques were used to enhance ML and statistical analysis. In our study, ML classifiers were evaluated using performance metrics such as Accuracy (Acc), area under the receiver operating characteristic curve (AROC), F1-score, and a normalized Matthew’s correlation coefficient (MCC′). Results Feature selection consistently identified biomarkers across ADNI and OASIS-3, with the entorhinal, hippocampus, lateral ventricle, and lateral orbitofrontal regions being the most affected. Classification results varied between balanced and imbalanced datasets and between ADNI and OASIS-3. For ADNI balanced datasets, the naíve Bayes model using z-score harmonization and ReliefF feature selection performed best (Acc = 69.17%, AROC = 77.73%, F1 = 69.21%, MCC’ = 69.28%). For OASIS-3 balanced datasets, SVM with zscore-corrected data outperformed others (Acc = 66.58%, AROC = 72.01%, MCC’ = 66.78%), while logistic regression had the best F1-score (66.68%). In imbalanced data, RUSBoost showed the strongest overall performance on ADNI (F1 = 50.60%, AROC = 81.54%) and OASIS-3 (MCC’ = 63.31%). Support vector machine (SVM) excelled on ADNI in terms of Acc (82.93%) and MCC’ (70.21%), while naïve Bayes performed best on OASIS-3 by F1 (42.54%) and AROC (70.33%). Conclusion Data harmonization significantly improved the consistency and performance of feature selection and ML classification, with z-score harmonization yielding the best results. This study also highlights the importance of nested cross-validation (CV) to control overfitting and the potential of a semi-automatic pipeline for early AD detection using MRI, with future applications integrating other neuroimaging data to enhance prediction.https://peerj.com/articles/18490.pdfAlzheimer’s diseaseMachine learningMRINeuroimagingNested cross validationFeature selection |
| spellingShingle | Alwani Liyana Ahmad Jose M. Sanchez-Bornot Roberto C. Sotero Damien Coyle Zamzuri Idris Ibrahima Faye A machine learning approach for identifying anatomical biomarkers of early mild cognitive impairment PeerJ Alzheimer’s disease Machine learning MRI Neuroimaging Nested cross validation Feature selection |
| title | A machine learning approach for identifying anatomical biomarkers of early mild cognitive impairment |
| title_full | A machine learning approach for identifying anatomical biomarkers of early mild cognitive impairment |
| title_fullStr | A machine learning approach for identifying anatomical biomarkers of early mild cognitive impairment |
| title_full_unstemmed | A machine learning approach for identifying anatomical biomarkers of early mild cognitive impairment |
| title_short | A machine learning approach for identifying anatomical biomarkers of early mild cognitive impairment |
| title_sort | machine learning approach for identifying anatomical biomarkers of early mild cognitive impairment |
| topic | Alzheimer’s disease Machine learning MRI Neuroimaging Nested cross validation Feature selection |
| url | https://peerj.com/articles/18490.pdf |
| work_keys_str_mv | AT alwaniliyanaahmad amachinelearningapproachforidentifyinganatomicalbiomarkersofearlymildcognitiveimpairment AT josemsanchezbornot amachinelearningapproachforidentifyinganatomicalbiomarkersofearlymildcognitiveimpairment AT robertocsotero amachinelearningapproachforidentifyinganatomicalbiomarkersofearlymildcognitiveimpairment AT damiencoyle amachinelearningapproachforidentifyinganatomicalbiomarkersofearlymildcognitiveimpairment AT zamzuriidris amachinelearningapproachforidentifyinganatomicalbiomarkersofearlymildcognitiveimpairment AT ibrahimafaye amachinelearningapproachforidentifyinganatomicalbiomarkersofearlymildcognitiveimpairment AT alwaniliyanaahmad machinelearningapproachforidentifyinganatomicalbiomarkersofearlymildcognitiveimpairment AT josemsanchezbornot machinelearningapproachforidentifyinganatomicalbiomarkersofearlymildcognitiveimpairment AT robertocsotero machinelearningapproachforidentifyinganatomicalbiomarkersofearlymildcognitiveimpairment AT damiencoyle machinelearningapproachforidentifyinganatomicalbiomarkersofearlymildcognitiveimpairment AT zamzuriidris machinelearningapproachforidentifyinganatomicalbiomarkersofearlymildcognitiveimpairment AT ibrahimafaye machinelearningapproachforidentifyinganatomicalbiomarkersofearlymildcognitiveimpairment |