Predicting individual traits from models of brain dynamics accurately and reliably using the Fisher kernel
Predicting an individual’s cognitive traits or clinical condition using brain signals is a central goal in modern neuroscience. This is commonly done using either structural aspects, such as structural connectivity or cortical thickness, or aggregated measures of brain activity that average over tim...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
eLife Sciences Publications Ltd
2025-01-01
|
| Series: | eLife |
| Subjects: | |
| Online Access: | https://elifesciences.org/articles/95125 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576058325467136 |
|---|---|
| author | Christine Ahrends Mark W Woolrich Diego Vidaurre |
| author_facet | Christine Ahrends Mark W Woolrich Diego Vidaurre |
| author_sort | Christine Ahrends |
| collection | DOAJ |
| description | Predicting an individual’s cognitive traits or clinical condition using brain signals is a central goal in modern neuroscience. This is commonly done using either structural aspects, such as structural connectivity or cortical thickness, or aggregated measures of brain activity that average over time. But these approaches are missing a central aspect of brain function: the unique ways in which an individual’s brain activity unfolds over time. One reason why these dynamic patterns are not usually considered is that they have to be described by complex, high-dimensional models; and it is unclear how best to use these models for prediction. We here propose an approach that describes dynamic functional connectivity and amplitude patterns using a Hidden Markov model (HMM) and combines it with the Fisher kernel, which can be used to predict individual traits. The Fisher kernel is constructed from the HMM in a mathematically principled manner, thereby preserving the structure of the underlying model. We show here, in fMRI data, that the HMM-Fisher kernel approach is accurate and reliable. We compare the Fisher kernel to other prediction methods, both time-varying and time-averaged functional connectivity-based models. Our approach leverages information about an individual’s time-varying amplitude and functional connectivity for prediction and has broad applications in cognitive neuroscience and personalised medicine. |
| format | Article |
| id | doaj-art-8b348bab19864037b61196ab55684e69 |
| institution | Kabale University |
| issn | 2050-084X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | eLife Sciences Publications Ltd |
| record_format | Article |
| series | eLife |
| spelling | doaj-art-8b348bab19864037b61196ab55684e692025-01-31T13:12:05ZengeLife Sciences Publications LtdeLife2050-084X2025-01-011310.7554/eLife.95125Predicting individual traits from models of brain dynamics accurately and reliably using the Fisher kernelChristine Ahrends0https://orcid.org/0000-0002-9287-1254Mark W Woolrich1Diego Vidaurre2https://orcid.org/0000-0002-9650-2229Center of Functionally Integrative Neuroscience, Department of Clinical Medicine, Aarhus University, Aarhus, DenmarkOxford Centre for Human Brain Activity, Department of Psychiatry, University of Oxford, Oxford, United KingdomCenter of Functionally Integrative Neuroscience, Department of Clinical Medicine, Aarhus University, Aarhus, Denmark; Department of Psychiatry, University of Oxford, Oxford, United KingdomPredicting an individual’s cognitive traits or clinical condition using brain signals is a central goal in modern neuroscience. This is commonly done using either structural aspects, such as structural connectivity or cortical thickness, or aggregated measures of brain activity that average over time. But these approaches are missing a central aspect of brain function: the unique ways in which an individual’s brain activity unfolds over time. One reason why these dynamic patterns are not usually considered is that they have to be described by complex, high-dimensional models; and it is unclear how best to use these models for prediction. We here propose an approach that describes dynamic functional connectivity and amplitude patterns using a Hidden Markov model (HMM) and combines it with the Fisher kernel, which can be used to predict individual traits. The Fisher kernel is constructed from the HMM in a mathematically principled manner, thereby preserving the structure of the underlying model. We show here, in fMRI data, that the HMM-Fisher kernel approach is accurate and reliable. We compare the Fisher kernel to other prediction methods, both time-varying and time-averaged functional connectivity-based models. Our approach leverages information about an individual’s time-varying amplitude and functional connectivity for prediction and has broad applications in cognitive neuroscience and personalised medicine.https://elifesciences.org/articles/95125brain dynamicsmachine learningfMRIHidden Markov Modelling |
| spellingShingle | Christine Ahrends Mark W Woolrich Diego Vidaurre Predicting individual traits from models of brain dynamics accurately and reliably using the Fisher kernel eLife brain dynamics machine learning fMRI Hidden Markov Modelling |
| title | Predicting individual traits from models of brain dynamics accurately and reliably using the Fisher kernel |
| title_full | Predicting individual traits from models of brain dynamics accurately and reliably using the Fisher kernel |
| title_fullStr | Predicting individual traits from models of brain dynamics accurately and reliably using the Fisher kernel |
| title_full_unstemmed | Predicting individual traits from models of brain dynamics accurately and reliably using the Fisher kernel |
| title_short | Predicting individual traits from models of brain dynamics accurately and reliably using the Fisher kernel |
| title_sort | predicting individual traits from models of brain dynamics accurately and reliably using the fisher kernel |
| topic | brain dynamics machine learning fMRI Hidden Markov Modelling |
| url | https://elifesciences.org/articles/95125 |
| work_keys_str_mv | AT christineahrends predictingindividualtraitsfrommodelsofbraindynamicsaccuratelyandreliablyusingthefisherkernel AT markwwoolrich predictingindividualtraitsfrommodelsofbraindynamicsaccuratelyandreliablyusingthefisherkernel AT diegovidaurre predictingindividualtraitsfrommodelsofbraindynamicsaccuratelyandreliablyusingthefisherkernel |