A reusable benchmark of brain-age prediction from M/EEG resting-state signals
Population-level modeling can define quantitative measures of individual aging by applying machine learning to large volumes of brain images. These measures of brain age, obtained from the general population, helped characterize disease severity in neurological populations, improving estimates of di...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-11-01
|
| Series: | NeuroImage |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S105381192200636X |
| _version_ | 1811338494846435328 |
|---|---|
| author | Denis A. Engemann Apolline Mellot Richard Höchenberger Hubert Banville David Sabbagh Lukas Gemein Tonio Ball Alexandre Gramfort |
| author_facet | Denis A. Engemann Apolline Mellot Richard Höchenberger Hubert Banville David Sabbagh Lukas Gemein Tonio Ball Alexandre Gramfort |
| author_sort | Denis A. Engemann |
| collection | DOAJ |
| description | Population-level modeling can define quantitative measures of individual aging by applying machine learning to large volumes of brain images. These measures of brain age, obtained from the general population, helped characterize disease severity in neurological populations, improving estimates of diagnosis or prognosis. Magnetoencephalography (MEG) and Electroencephalography (EEG) have the potential to further generalize this approach towards prevention and public health by enabling assessments of brain health at large scales in socioeconomically diverse environments. However, more research is needed to define methods that can handle the complexity and diversity of M/EEG signals across diverse real-world contexts. To catalyse this effort, here we propose reusable benchmarks of competing machine learning approaches for brain age modeling. We benchmarked popular classical machine learning pipelines and deep learning architectures previously used for pathology decoding or brain age estimation in 4 international M/EEG cohorts from diverse countries and cultural contexts, including recordings from more than 2500 participants. Our benchmarks were built on top of the M/EEG adaptations of the BIDS standard, providing tools that can be applied with minimal modification on any M/EEG dataset provided in the BIDS format. Our results suggest that, regardless of whether classical machine learning or deep learning was used, the highest performance was reached by pipelines and architectures involving spatially aware representations of the M/EEG signals, leading to R2 scores between 0.60-0.74. Hand-crafted features paired with random forest regression provided robust benchmarks even in situations in which other approaches failed. Taken together, this set of benchmarks, accompanied by open-source software and high-level Python scripts, can serve as a starting point and quantitative reference for future efforts at developing M/EEG-based measures of brain aging. The generality of the approach renders this benchmark reusable for other related objectives such as modeling specific cognitive variables or clinical endpoints. |
| first_indexed | 2024-04-13T18:11:42Z |
| format | Article |
| id | doaj.art-ebcaa85e47004b388395f1051f01a3a4 |
| institution | Directory Open Access Journal |
| issn | 1095-9572 |
| language | English |
| last_indexed | 2024-04-13T18:11:42Z |
| publishDate | 2022-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage |
| spelling | doaj.art-ebcaa85e47004b388395f1051f01a3a42022-12-22T02:35:53ZengElsevierNeuroImage1095-95722022-11-01262119521A reusable benchmark of brain-age prediction from M/EEG resting-state signalsDenis A. Engemann0Apolline Mellot1Richard Höchenberger2Hubert Banville3David Sabbagh4Lukas Gemein5Tonio Ball6Alexandre Gramfort7Roche Pharma Research and Early Development, Neuroscience and Rare Diseases, Roche Innovation Center Basel, F. Hoffmann–La Roche Ltd., Basel, Switzerland; Université Paris-Saclay, Inria, CEA, Palaiseau, France; Max Planck Institute for Human Cognitive and Brain Sciences, Department of Neurology, D-04103, Leipzig, Germany; Correspondence author.Université Paris-Saclay, Inria, CEA, Palaiseau, FranceUniversité Paris-Saclay, Inria, CEA, Palaiseau, FranceUniversité Paris-Saclay, Inria, CEA, Palaiseau, France; Inserm, UMRS-942, Paris Diderot University, Paris, FranceUniversité Paris-Saclay, Inria, CEA, Palaiseau, France; Neuromedical AI Lab, Department of Neurosurgery, Medical Center – University of Freiburg, Faculty of Medicine, University of Freiburg, Engelbergerstr. 21, 79106, Freiburg, GermanyNeurorobotics Lab, Computer Science Department – University of Freiburg, Faculty of Engineering, University of Freiburg, Georges-Köhler-Allee 80, 79110, Freiburg, Germany; BrainLinks-BrainTools Cluster of Excellence, University of Freiburg, Freiburg, GermanyNeurorobotics Lab, Computer Science Department – University of Freiburg, Faculty of Engineering, University of Freiburg, Georges-Köhler-Allee 80, 79110, Freiburg, Germany; InteraXon Inc., Toronto, CanadaUniversité Paris-Saclay, Inria, CEA, Palaiseau, FrancePopulation-level modeling can define quantitative measures of individual aging by applying machine learning to large volumes of brain images. These measures of brain age, obtained from the general population, helped characterize disease severity in neurological populations, improving estimates of diagnosis or prognosis. Magnetoencephalography (MEG) and Electroencephalography (EEG) have the potential to further generalize this approach towards prevention and public health by enabling assessments of brain health at large scales in socioeconomically diverse environments. However, more research is needed to define methods that can handle the complexity and diversity of M/EEG signals across diverse real-world contexts. To catalyse this effort, here we propose reusable benchmarks of competing machine learning approaches for brain age modeling. We benchmarked popular classical machine learning pipelines and deep learning architectures previously used for pathology decoding or brain age estimation in 4 international M/EEG cohorts from diverse countries and cultural contexts, including recordings from more than 2500 participants. Our benchmarks were built on top of the M/EEG adaptations of the BIDS standard, providing tools that can be applied with minimal modification on any M/EEG dataset provided in the BIDS format. Our results suggest that, regardless of whether classical machine learning or deep learning was used, the highest performance was reached by pipelines and architectures involving spatially aware representations of the M/EEG signals, leading to R2 scores between 0.60-0.74. Hand-crafted features paired with random forest regression provided robust benchmarks even in situations in which other approaches failed. Taken together, this set of benchmarks, accompanied by open-source software and high-level Python scripts, can serve as a starting point and quantitative reference for future efforts at developing M/EEG-based measures of brain aging. The generality of the approach renders this benchmark reusable for other related objectives such as modeling specific cognitive variables or clinical endpoints.http://www.sciencedirect.com/science/article/pii/S105381192200636XClinical neuroscienceBrain ageElectroencephalographyMagnetoencephalographyMachine learningPopulation modeling |
| spellingShingle | Denis A. Engemann Apolline Mellot Richard Höchenberger Hubert Banville David Sabbagh Lukas Gemein Tonio Ball Alexandre Gramfort A reusable benchmark of brain-age prediction from M/EEG resting-state signals NeuroImage Clinical neuroscience Brain age Electroencephalography Magnetoencephalography Machine learning Population modeling |
| title | A reusable benchmark of brain-age prediction from M/EEG resting-state signals |
| title_full | A reusable benchmark of brain-age prediction from M/EEG resting-state signals |
| title_fullStr | A reusable benchmark of brain-age prediction from M/EEG resting-state signals |
| title_full_unstemmed | A reusable benchmark of brain-age prediction from M/EEG resting-state signals |
| title_short | A reusable benchmark of brain-age prediction from M/EEG resting-state signals |
| title_sort | reusable benchmark of brain age prediction from m eeg resting state signals |
| topic | Clinical neuroscience Brain age Electroencephalography Magnetoencephalography Machine learning Population modeling |
| url | http://www.sciencedirect.com/science/article/pii/S105381192200636X |
| work_keys_str_mv | AT denisaengemann areusablebenchmarkofbrainagepredictionfrommeegrestingstatesignals AT apollinemellot areusablebenchmarkofbrainagepredictionfrommeegrestingstatesignals AT richardhochenberger areusablebenchmarkofbrainagepredictionfrommeegrestingstatesignals AT hubertbanville areusablebenchmarkofbrainagepredictionfrommeegrestingstatesignals AT davidsabbagh areusablebenchmarkofbrainagepredictionfrommeegrestingstatesignals AT lukasgemein areusablebenchmarkofbrainagepredictionfrommeegrestingstatesignals AT tonioball areusablebenchmarkofbrainagepredictionfrommeegrestingstatesignals AT alexandregramfort areusablebenchmarkofbrainagepredictionfrommeegrestingstatesignals AT denisaengemann reusablebenchmarkofbrainagepredictionfrommeegrestingstatesignals AT apollinemellot reusablebenchmarkofbrainagepredictionfrommeegrestingstatesignals AT richardhochenberger reusablebenchmarkofbrainagepredictionfrommeegrestingstatesignals AT hubertbanville reusablebenchmarkofbrainagepredictionfrommeegrestingstatesignals AT davidsabbagh reusablebenchmarkofbrainagepredictionfrommeegrestingstatesignals AT lukasgemein reusablebenchmarkofbrainagepredictionfrommeegrestingstatesignals AT tonioball reusablebenchmarkofbrainagepredictionfrommeegrestingstatesignals AT alexandregramfort reusablebenchmarkofbrainagepredictionfrommeegrestingstatesignals |