A comparative machine learning study of schizophrenia biomarkers derived from functional connectivity
Abstract Functional connectivity holds promise as a biomarker of schizophrenia. Yet, the high dimensionality of predictive models trained on functional connectomes, combined with small sample sizes in clinical research, increases the risk of overfitting. Recently, low-dimensional representations of...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-024-84152-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585784331337728 |
|---|---|
| author | Victoria Shevchenko R. Austin Benn Robert Scholz Wei Wei Carla Pallavicini Ulysse Klatzmann Francesco Alberti Theodore D. Satterthwaite Demian Wassermann Pierre-Louis Bazin Daniel S. Margulies |
| author_facet | Victoria Shevchenko R. Austin Benn Robert Scholz Wei Wei Carla Pallavicini Ulysse Klatzmann Francesco Alberti Theodore D. Satterthwaite Demian Wassermann Pierre-Louis Bazin Daniel S. Margulies |
| author_sort | Victoria Shevchenko |
| collection | DOAJ |
| description | Abstract Functional connectivity holds promise as a biomarker of schizophrenia. Yet, the high dimensionality of predictive models trained on functional connectomes, combined with small sample sizes in clinical research, increases the risk of overfitting. Recently, low-dimensional representations of the connectome such as macroscale cortical gradients and gradient dispersion have been proposed, with studies noting consistent gradient and dispersion differences in psychiatric conditions. However, it is unknown which of these derived measures has the highest predictive capacity and how they compare to raw functional connectivity specifically in the case of schizophrenia. Our study evaluates which connectome features derived from resting state functional MRI — functional connectivity, gradients, or gradient dispersion — best identify schizophrenia. To this end, we leveraged data of 936 individuals from three large open-access datasets: COBRE, LA5c, and SRPBS-1600. We developed a pipeline which allows us to aggregate over a million different features and assess their predictive potential in a single, computationally efficient experiment. We selected top 1% of features with the largest permutation feature importance and trained 13 classifiers on them using 10-fold cross-validation. Our findings indicate that functional connectivity outperforms its low-dimensional derivatives such as cortical gradients and gradient dispersion in identifying schizophrenia (Mann–Whitney test conducted on test accuracy: connectivity vs. 1st gradient: U = 142, p < 0.003; connectivity vs. neighborhood dispersion: U = 141, p = 0.004). Additionally, we demonstrated that the edges which contribute the most to classification performance are the ones connecting primary sensory regions. Functional connectivity within the primary sensory regions showed the highest discrimination capabilities between subjects with schizophrenia and neurotypical controls. These findings along with the feature selection pipeline proposed here will facilitate future inquiries into the prediction of schizophrenia subtypes and transdiagnostic phenomena. |
| format | Article |
| id | doaj-art-7c550b14ded04b578f277a943257d388 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-7c550b14ded04b578f277a943257d3882025-01-26T12:31:56ZengNature PortfolioScientific Reports2045-23222025-01-0115111410.1038/s41598-024-84152-2A comparative machine learning study of schizophrenia biomarkers derived from functional connectivityVictoria Shevchenko0R. Austin Benn1Robert Scholz2Wei Wei3Carla Pallavicini4Ulysse Klatzmann5Francesco Alberti6Theodore D. Satterthwaite7Demian Wassermann8Pierre-Louis Bazin9Daniel S. Margulies10Cognitive Neuroanatomy Lab, INCC UMR 8002, CNRS, Université Paris CitéCognitive Neuroanatomy Lab, INCC UMR 8002, CNRS, Université Paris CitéCognitive Neuroanatomy Lab, INCC UMR 8002, CNRS, Université Paris CitéCognitive Neuroanatomy Lab, INCC UMR 8002, CNRS, Université Paris CitéCognitive Neuroanatomy Lab, INCC UMR 8002, CNRS, Université Paris CitéCognitive Neuroanatomy Lab, INCC UMR 8002, CNRS, Université Paris CitéCognitive Neuroanatomy Lab, INCC UMR 8002, CNRS, Université Paris CitéUniversity of Pennsylvania, Perelman School of MedicineMIND Team, Inria Saclay, Université Paris-SaclayFull Brain Picture AnalyticsCognitive Neuroanatomy Lab, INCC UMR 8002, CNRS, Université Paris CitéAbstract Functional connectivity holds promise as a biomarker of schizophrenia. Yet, the high dimensionality of predictive models trained on functional connectomes, combined with small sample sizes in clinical research, increases the risk of overfitting. Recently, low-dimensional representations of the connectome such as macroscale cortical gradients and gradient dispersion have been proposed, with studies noting consistent gradient and dispersion differences in psychiatric conditions. However, it is unknown which of these derived measures has the highest predictive capacity and how they compare to raw functional connectivity specifically in the case of schizophrenia. Our study evaluates which connectome features derived from resting state functional MRI — functional connectivity, gradients, or gradient dispersion — best identify schizophrenia. To this end, we leveraged data of 936 individuals from three large open-access datasets: COBRE, LA5c, and SRPBS-1600. We developed a pipeline which allows us to aggregate over a million different features and assess their predictive potential in a single, computationally efficient experiment. We selected top 1% of features with the largest permutation feature importance and trained 13 classifiers on them using 10-fold cross-validation. Our findings indicate that functional connectivity outperforms its low-dimensional derivatives such as cortical gradients and gradient dispersion in identifying schizophrenia (Mann–Whitney test conducted on test accuracy: connectivity vs. 1st gradient: U = 142, p < 0.003; connectivity vs. neighborhood dispersion: U = 141, p = 0.004). Additionally, we demonstrated that the edges which contribute the most to classification performance are the ones connecting primary sensory regions. Functional connectivity within the primary sensory regions showed the highest discrimination capabilities between subjects with schizophrenia and neurotypical controls. These findings along with the feature selection pipeline proposed here will facilitate future inquiries into the prediction of schizophrenia subtypes and transdiagnostic phenomena.https://doi.org/10.1038/s41598-024-84152-2 |
| spellingShingle | Victoria Shevchenko R. Austin Benn Robert Scholz Wei Wei Carla Pallavicini Ulysse Klatzmann Francesco Alberti Theodore D. Satterthwaite Demian Wassermann Pierre-Louis Bazin Daniel S. Margulies A comparative machine learning study of schizophrenia biomarkers derived from functional connectivity Scientific Reports |
| title | A comparative machine learning study of schizophrenia biomarkers derived from functional connectivity |
| title_full | A comparative machine learning study of schizophrenia biomarkers derived from functional connectivity |
| title_fullStr | A comparative machine learning study of schizophrenia biomarkers derived from functional connectivity |
| title_full_unstemmed | A comparative machine learning study of schizophrenia biomarkers derived from functional connectivity |
| title_short | A comparative machine learning study of schizophrenia biomarkers derived from functional connectivity |
| title_sort | comparative machine learning study of schizophrenia biomarkers derived from functional connectivity |
| url | https://doi.org/10.1038/s41598-024-84152-2 |
| work_keys_str_mv | AT victoriashevchenko acomparativemachinelearningstudyofschizophreniabiomarkersderivedfromfunctionalconnectivity AT raustinbenn acomparativemachinelearningstudyofschizophreniabiomarkersderivedfromfunctionalconnectivity AT robertscholz acomparativemachinelearningstudyofschizophreniabiomarkersderivedfromfunctionalconnectivity AT weiwei acomparativemachinelearningstudyofschizophreniabiomarkersderivedfromfunctionalconnectivity AT carlapallavicini acomparativemachinelearningstudyofschizophreniabiomarkersderivedfromfunctionalconnectivity AT ulysseklatzmann acomparativemachinelearningstudyofschizophreniabiomarkersderivedfromfunctionalconnectivity AT francescoalberti acomparativemachinelearningstudyofschizophreniabiomarkersderivedfromfunctionalconnectivity AT theodoredsatterthwaite acomparativemachinelearningstudyofschizophreniabiomarkersderivedfromfunctionalconnectivity AT demianwassermann acomparativemachinelearningstudyofschizophreniabiomarkersderivedfromfunctionalconnectivity AT pierrelouisbazin acomparativemachinelearningstudyofschizophreniabiomarkersderivedfromfunctionalconnectivity AT danielsmargulies acomparativemachinelearningstudyofschizophreniabiomarkersderivedfromfunctionalconnectivity AT victoriashevchenko comparativemachinelearningstudyofschizophreniabiomarkersderivedfromfunctionalconnectivity AT raustinbenn comparativemachinelearningstudyofschizophreniabiomarkersderivedfromfunctionalconnectivity AT robertscholz comparativemachinelearningstudyofschizophreniabiomarkersderivedfromfunctionalconnectivity AT weiwei comparativemachinelearningstudyofschizophreniabiomarkersderivedfromfunctionalconnectivity AT carlapallavicini comparativemachinelearningstudyofschizophreniabiomarkersderivedfromfunctionalconnectivity AT ulysseklatzmann comparativemachinelearningstudyofschizophreniabiomarkersderivedfromfunctionalconnectivity AT francescoalberti comparativemachinelearningstudyofschizophreniabiomarkersderivedfromfunctionalconnectivity AT theodoredsatterthwaite comparativemachinelearningstudyofschizophreniabiomarkersderivedfromfunctionalconnectivity AT demianwassermann comparativemachinelearningstudyofschizophreniabiomarkersderivedfromfunctionalconnectivity AT pierrelouisbazin comparativemachinelearningstudyofschizophreniabiomarkersderivedfromfunctionalconnectivity AT danielsmargulies comparativemachinelearningstudyofschizophreniabiomarkersderivedfromfunctionalconnectivity |