UK Biobank MRI data can power the development of generalizable brain clocks: A study of standard ML/DL methodologies and performance analysis on external databases
In this study, we present a comprehensive pipeline to train and compare a broad spectrum of machine learning and deep learning brain clocks, integrating diverse preprocessing strategies and correction terms. Our analysis also includes established methodologies which have shown success in prior UK Bi...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | NeuroImage |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1053811925000667 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832087679949340672 |
|---|---|
| author | Marco Capó Silvia Vitali Georgios Athanasiou Nicole Cusimano Daniel García Garth Cruickshank Bipin Patel |
| author_facet | Marco Capó Silvia Vitali Georgios Athanasiou Nicole Cusimano Daniel García Garth Cruickshank Bipin Patel |
| author_sort | Marco Capó |
| collection | DOAJ |
| description | In this study, we present a comprehensive pipeline to train and compare a broad spectrum of machine learning and deep learning brain clocks, integrating diverse preprocessing strategies and correction terms. Our analysis also includes established methodologies which have shown success in prior UK Biobank-related studies. For our analysis we used T1-weighted MRI scans and processed de novo all images via FastSurfer, transforming them into a conformed space for deep learning and extracting image-derived phenotypes for our machine learning approaches. We rigorously evaluated these approaches both as robust age predictors for healthy individuals and as potential biomarkers for various neurodegenerative conditions, leveraging data from the UK Biobank, ADNI, and NACC datasets. To this end we designed a statistical framework to assess age prediction performance, the robustness of the prediction across cohort variability (database, machine type and ethnicity) and its potential as a biomarker for neurodegenerative conditions. Results demonstrate that highly accurate brain age models, typically utilising penalised linear machine learning models adjusted with Zhang's methodology, with mean absolute errors under 1 year in external validation, can be achieved while maintaining consistent prediction performance across different age brackets and subgroups (e.g., ethnicity and MRI machine/manufacturer). Additionally, these models show strong potential as biomarkers for neurodegenerative conditions, such as dementia, where brain age prediction achieved an AUROC of up to 0.90 in distinguishing healthy individuals from those with dementia. |
| format | Article |
| id | doaj-art-25b463a2434b4631ab424f6c84de3e31 |
| institution | Kabale University |
| issn | 1095-9572 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage |
| spelling | doaj-art-25b463a2434b4631ab424f6c84de3e312025-02-06T05:11:10ZengElsevierNeuroImage1095-95722025-03-01308121064UK Biobank MRI data can power the development of generalizable brain clocks: A study of standard ML/DL methodologies and performance analysis on external databasesMarco Capó0Silvia Vitali1Georgios Athanasiou2Nicole Cusimano3Daniel García4Garth Cruickshank5Bipin Patel6Oxcitas Limited, 28 Chesterton Road, Cambridge CB4 3AZ, United Kingdom; Corresponding author.Oxcitas Limited, 28 Chesterton Road, Cambridge CB4 3AZ, United KingdomOxcitas Limited, 28 Chesterton Road, Cambridge CB4 3AZ, United KingdomOxcitas Limited, 28 Chesterton Road, Cambridge CB4 3AZ, United KingdomOxcitas Limited, 28 Chesterton Road, Cambridge CB4 3AZ, United KingdomUniversity of Birmingham, Birmingham B15 2TT, United Kingdom; Queen Elizabeth Hospital Birmingham, Mindelsohn Way, Birmingham B15 2GW, United KingdomOxcitas Limited, 28 Chesterton Road, Cambridge CB4 3AZ, United Kingdom; ElectronRX Limited, 28 Chesterton Road, Cambridge CB4 3AZ, United KingdomIn this study, we present a comprehensive pipeline to train and compare a broad spectrum of machine learning and deep learning brain clocks, integrating diverse preprocessing strategies and correction terms. Our analysis also includes established methodologies which have shown success in prior UK Biobank-related studies. For our analysis we used T1-weighted MRI scans and processed de novo all images via FastSurfer, transforming them into a conformed space for deep learning and extracting image-derived phenotypes for our machine learning approaches. We rigorously evaluated these approaches both as robust age predictors for healthy individuals and as potential biomarkers for various neurodegenerative conditions, leveraging data from the UK Biobank, ADNI, and NACC datasets. To this end we designed a statistical framework to assess age prediction performance, the robustness of the prediction across cohort variability (database, machine type and ethnicity) and its potential as a biomarker for neurodegenerative conditions. Results demonstrate that highly accurate brain age models, typically utilising penalised linear machine learning models adjusted with Zhang's methodology, with mean absolute errors under 1 year in external validation, can be achieved while maintaining consistent prediction performance across different age brackets and subgroups (e.g., ethnicity and MRI machine/manufacturer). Additionally, these models show strong potential as biomarkers for neurodegenerative conditions, such as dementia, where brain age prediction achieved an AUROC of up to 0.90 in distinguishing healthy individuals from those with dementia.http://www.sciencedirect.com/science/article/pii/S1053811925000667Brain age predictionNeurodegenerative condition diagnosisUK BiobankMachine learningT1 weighted MRI |
| spellingShingle | Marco Capó Silvia Vitali Georgios Athanasiou Nicole Cusimano Daniel García Garth Cruickshank Bipin Patel UK Biobank MRI data can power the development of generalizable brain clocks: A study of standard ML/DL methodologies and performance analysis on external databases NeuroImage Brain age prediction Neurodegenerative condition diagnosis UK Biobank Machine learning T1 weighted MRI |
| title | UK Biobank MRI data can power the development of generalizable brain clocks: A study of standard ML/DL methodologies and performance analysis on external databases |
| title_full | UK Biobank MRI data can power the development of generalizable brain clocks: A study of standard ML/DL methodologies and performance analysis on external databases |
| title_fullStr | UK Biobank MRI data can power the development of generalizable brain clocks: A study of standard ML/DL methodologies and performance analysis on external databases |
| title_full_unstemmed | UK Biobank MRI data can power the development of generalizable brain clocks: A study of standard ML/DL methodologies and performance analysis on external databases |
| title_short | UK Biobank MRI data can power the development of generalizable brain clocks: A study of standard ML/DL methodologies and performance analysis on external databases |
| title_sort | uk biobank mri data can power the development of generalizable brain clocks a study of standard ml dl methodologies and performance analysis on external databases |
| topic | Brain age prediction Neurodegenerative condition diagnosis UK Biobank Machine learning T1 weighted MRI |
| url | http://www.sciencedirect.com/science/article/pii/S1053811925000667 |
| work_keys_str_mv | AT marcocapo ukbiobankmridatacanpowerthedevelopmentofgeneralizablebrainclocksastudyofstandardmldlmethodologiesandperformanceanalysisonexternaldatabases AT silviavitali ukbiobankmridatacanpowerthedevelopmentofgeneralizablebrainclocksastudyofstandardmldlmethodologiesandperformanceanalysisonexternaldatabases AT georgiosathanasiou ukbiobankmridatacanpowerthedevelopmentofgeneralizablebrainclocksastudyofstandardmldlmethodologiesandperformanceanalysisonexternaldatabases AT nicolecusimano ukbiobankmridatacanpowerthedevelopmentofgeneralizablebrainclocksastudyofstandardmldlmethodologiesandperformanceanalysisonexternaldatabases AT danielgarcia ukbiobankmridatacanpowerthedevelopmentofgeneralizablebrainclocksastudyofstandardmldlmethodologiesandperformanceanalysisonexternaldatabases AT garthcruickshank ukbiobankmridatacanpowerthedevelopmentofgeneralizablebrainclocksastudyofstandardmldlmethodologiesandperformanceanalysisonexternaldatabases AT bipinpatel ukbiobankmridatacanpowerthedevelopmentofgeneralizablebrainclocksastudyofstandardmldlmethodologiesandperformanceanalysisonexternaldatabases |