Eintrag weiter verarbeiten
Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability
Gespeichert in:
Zeitschriftentitel: | PLOS Computational Biology |
---|---|
Personen und Körperschaften: | , , , |
In: | PLOS Computational Biology, 17, 2021, 3, S. e1008347 |
Format: | E-Article |
Sprache: | Englisch |
veröffentlicht: |
Public Library of Science (PLoS)
|
Schlagwörter: |
author_facet |
Rasero, Javier Sentis, Amy Isabella Yeh, Fang-Cheng Verstynen, Timothy Rasero, Javier Sentis, Amy Isabella Yeh, Fang-Cheng Verstynen, Timothy |
---|---|
author |
Rasero, Javier Sentis, Amy Isabella Yeh, Fang-Cheng Verstynen, Timothy |
spellingShingle |
Rasero, Javier Sentis, Amy Isabella Yeh, Fang-Cheng Verstynen, Timothy PLOS Computational Biology Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability Computational Theory and Mathematics Cellular and Molecular Neuroscience Genetics Molecular Biology Ecology Modeling and Simulation Ecology, Evolution, Behavior and Systematics |
author_sort |
rasero, javier |
spelling |
Rasero, Javier Sentis, Amy Isabella Yeh, Fang-Cheng Verstynen, Timothy 1553-7358 Public Library of Science (PLoS) Computational Theory and Mathematics Cellular and Molecular Neuroscience Genetics Molecular Biology Ecology Modeling and Simulation Ecology, Evolution, Behavior and Systematics http://dx.doi.org/10.1371/journal.pcbi.1008347 <jats:p>Variation in cognitive ability arises from subtle differences in underlying neural architecture. Understanding and predicting individual variability in cognition from the differences in brain networks requires harnessing the unique variance captured by different neuroimaging modalities. Here we adopted a multi-level machine learning approach that combines diffusion, functional, and structural MRI data from the Human Connectome Project (N = 1050) to provide unitary prediction models of various cognitive abilities: global cognitive function, fluid intelligence, crystallized intelligence, impulsivity, spatial orientation, verbal episodic memory and sustained attention. Out-of-sample predictions of each cognitive score were first generated using a sparsity-constrained principal component regression on individual neuroimaging modalities. These individual predictions were then aggregated and submitted to a LASSO estimator that removed redundant variability across channels. This stacked prediction led to a significant improvement in accuracy, relative to the best single modality predictions (approximately 1% to more than 3% boost in variance explained), across a majority of the cognitive abilities tested. Further analysis found that diffusion and brain surface properties contribute the most to the predictive power. Our findings establish a lower bound to predict individual differences in cognition using multiple neuroimaging measures of brain architecture, both structural and functional, quantify the relative predictive power of the different imaging modalities, and reveal how each modality provides unique and complementary information about individual differences in cognitive function.</jats:p> Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability PLOS Computational Biology |
doi_str_mv |
10.1371/journal.pcbi.1008347 |
facet_avail |
Online Free |
finc_class_facet |
Mathematik Biologie Psychologie Geographie |
format |
ElectronicArticle |
fullrecord |
blob:ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTM3MS9qb3VybmFsLnBjYmkuMTAwODM0Nw |
id |
ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTM3MS9qb3VybmFsLnBjYmkuMTAwODM0Nw |
institution |
DE-Pl11 DE-Rs1 DE-14 DE-105 DE-Ch1 DE-L229 DE-D275 DE-Bn3 DE-Brt1 DE-Zwi2 DE-D161 DE-Zi4 DE-Gla1 DE-15 |
imprint |
Public Library of Science (PLoS), 2021 |
imprint_str_mv |
Public Library of Science (PLoS), 2021 |
issn |
1553-7358 |
issn_str_mv |
1553-7358 |
language |
English |
mega_collection |
Public Library of Science (PLoS) (CrossRef) |
match_str |
rasero2021integratingacrossneuroimagingmodalitiesboostspredictionaccuracyofcognitiveability |
publishDateSort |
2021 |
publisher |
Public Library of Science (PLoS) |
recordtype |
ai |
record_format |
ai |
series |
PLOS Computational Biology |
source_id |
49 |
title |
Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability |
title_unstemmed |
Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability |
title_full |
Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability |
title_fullStr |
Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability |
title_full_unstemmed |
Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability |
title_short |
Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability |
title_sort |
integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability |
topic |
Computational Theory and Mathematics Cellular and Molecular Neuroscience Genetics Molecular Biology Ecology Modeling and Simulation Ecology, Evolution, Behavior and Systematics |
url |
http://dx.doi.org/10.1371/journal.pcbi.1008347 |
publishDate |
2021 |
physical |
e1008347 |
description |
<jats:p>Variation in cognitive ability arises from subtle differences in underlying neural architecture. Understanding and predicting individual variability in cognition from the differences in brain networks requires harnessing the unique variance captured by different neuroimaging modalities. Here we adopted a multi-level machine learning approach that combines diffusion, functional, and structural MRI data from the Human Connectome Project (N = 1050) to provide unitary prediction models of various cognitive abilities: global cognitive function, fluid intelligence, crystallized intelligence, impulsivity, spatial orientation, verbal episodic memory and sustained attention. Out-of-sample predictions of each cognitive score were first generated using a sparsity-constrained principal component regression on individual neuroimaging modalities. These individual predictions were then aggregated and submitted to a LASSO estimator that removed redundant variability across channels. This stacked prediction led to a significant improvement in accuracy, relative to the best single modality predictions (approximately 1% to more than 3% boost in variance explained), across a majority of the cognitive abilities tested. Further analysis found that diffusion and brain surface properties contribute the most to the predictive power. Our findings establish a lower bound to predict individual differences in cognition using multiple neuroimaging measures of brain architecture, both structural and functional, quantify the relative predictive power of the different imaging modalities, and reveal how each modality provides unique and complementary information about individual differences in cognitive function.</jats:p> |
container_issue |
3 |
container_start_page |
0 |
container_title |
PLOS Computational Biology |
container_volume |
17 |
format_de105 |
Article, E-Article |
format_de14 |
Article, E-Article |
format_de15 |
Article, E-Article |
format_de520 |
Article, E-Article |
format_de540 |
Article, E-Article |
format_dech1 |
Article, E-Article |
format_ded117 |
Article, E-Article |
format_degla1 |
E-Article |
format_del152 |
Buch |
format_del189 |
Article, E-Article |
format_dezi4 |
Article |
format_dezwi2 |
Article, E-Article |
format_finc |
Article, E-Article |
format_nrw |
Article, E-Article |
_version_ |
1792348782791229452 |
geogr_code |
not assigned |
last_indexed |
2024-03-01T18:16:39.822Z |
geogr_code_person |
not assigned |
openURL |
url_ver=Z39.88-2004&ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fvufind.svn.sourceforge.net%3Agenerator&rft.title=Integrating+across+neuroimaging+modalities+boosts+prediction+accuracy+of+cognitive+ability&rft.date=2021-03-05&genre=article&issn=1553-7358&volume=17&issue=3&pages=e1008347&jtitle=PLOS+Computational+Biology&atitle=Integrating+across+neuroimaging+modalities+boosts+prediction+accuracy+of+cognitive+ability&aulast=Verstynen&aufirst=Timothy&rft_id=info%3Adoi%2F10.1371%2Fjournal.pcbi.1008347&rft.language%5B0%5D=eng |
SOLR | |
_version_ | 1792348782791229452 |
author | Rasero, Javier, Sentis, Amy Isabella, Yeh, Fang-Cheng, Verstynen, Timothy |
author_facet | Rasero, Javier, Sentis, Amy Isabella, Yeh, Fang-Cheng, Verstynen, Timothy, Rasero, Javier, Sentis, Amy Isabella, Yeh, Fang-Cheng, Verstynen, Timothy |
author_sort | rasero, javier |
container_issue | 3 |
container_start_page | 0 |
container_title | PLOS Computational Biology |
container_volume | 17 |
description | <jats:p>Variation in cognitive ability arises from subtle differences in underlying neural architecture. Understanding and predicting individual variability in cognition from the differences in brain networks requires harnessing the unique variance captured by different neuroimaging modalities. Here we adopted a multi-level machine learning approach that combines diffusion, functional, and structural MRI data from the Human Connectome Project (N = 1050) to provide unitary prediction models of various cognitive abilities: global cognitive function, fluid intelligence, crystallized intelligence, impulsivity, spatial orientation, verbal episodic memory and sustained attention. Out-of-sample predictions of each cognitive score were first generated using a sparsity-constrained principal component regression on individual neuroimaging modalities. These individual predictions were then aggregated and submitted to a LASSO estimator that removed redundant variability across channels. This stacked prediction led to a significant improvement in accuracy, relative to the best single modality predictions (approximately 1% to more than 3% boost in variance explained), across a majority of the cognitive abilities tested. Further analysis found that diffusion and brain surface properties contribute the most to the predictive power. Our findings establish a lower bound to predict individual differences in cognition using multiple neuroimaging measures of brain architecture, both structural and functional, quantify the relative predictive power of the different imaging modalities, and reveal how each modality provides unique and complementary information about individual differences in cognitive function.</jats:p> |
doi_str_mv | 10.1371/journal.pcbi.1008347 |
facet_avail | Online, Free |
finc_class_facet | Mathematik, Biologie, Psychologie, Geographie |
format | ElectronicArticle |
format_de105 | Article, E-Article |
format_de14 | Article, E-Article |
format_de15 | Article, E-Article |
format_de520 | Article, E-Article |
format_de540 | Article, E-Article |
format_dech1 | Article, E-Article |
format_ded117 | Article, E-Article |
format_degla1 | E-Article |
format_del152 | Buch |
format_del189 | Article, E-Article |
format_dezi4 | Article |
format_dezwi2 | Article, E-Article |
format_finc | Article, E-Article |
format_nrw | Article, E-Article |
geogr_code | not assigned |
geogr_code_person | not assigned |
id | ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTM3MS9qb3VybmFsLnBjYmkuMTAwODM0Nw |
imprint | Public Library of Science (PLoS), 2021 |
imprint_str_mv | Public Library of Science (PLoS), 2021 |
institution | DE-Pl11, DE-Rs1, DE-14, DE-105, DE-Ch1, DE-L229, DE-D275, DE-Bn3, DE-Brt1, DE-Zwi2, DE-D161, DE-Zi4, DE-Gla1, DE-15 |
issn | 1553-7358 |
issn_str_mv | 1553-7358 |
language | English |
last_indexed | 2024-03-01T18:16:39.822Z |
match_str | rasero2021integratingacrossneuroimagingmodalitiesboostspredictionaccuracyofcognitiveability |
mega_collection | Public Library of Science (PLoS) (CrossRef) |
physical | e1008347 |
publishDate | 2021 |
publishDateSort | 2021 |
publisher | Public Library of Science (PLoS) |
record_format | ai |
recordtype | ai |
series | PLOS Computational Biology |
source_id | 49 |
spelling | Rasero, Javier Sentis, Amy Isabella Yeh, Fang-Cheng Verstynen, Timothy 1553-7358 Public Library of Science (PLoS) Computational Theory and Mathematics Cellular and Molecular Neuroscience Genetics Molecular Biology Ecology Modeling and Simulation Ecology, Evolution, Behavior and Systematics http://dx.doi.org/10.1371/journal.pcbi.1008347 <jats:p>Variation in cognitive ability arises from subtle differences in underlying neural architecture. Understanding and predicting individual variability in cognition from the differences in brain networks requires harnessing the unique variance captured by different neuroimaging modalities. Here we adopted a multi-level machine learning approach that combines diffusion, functional, and structural MRI data from the Human Connectome Project (N = 1050) to provide unitary prediction models of various cognitive abilities: global cognitive function, fluid intelligence, crystallized intelligence, impulsivity, spatial orientation, verbal episodic memory and sustained attention. Out-of-sample predictions of each cognitive score were first generated using a sparsity-constrained principal component regression on individual neuroimaging modalities. These individual predictions were then aggregated and submitted to a LASSO estimator that removed redundant variability across channels. This stacked prediction led to a significant improvement in accuracy, relative to the best single modality predictions (approximately 1% to more than 3% boost in variance explained), across a majority of the cognitive abilities tested. Further analysis found that diffusion and brain surface properties contribute the most to the predictive power. Our findings establish a lower bound to predict individual differences in cognition using multiple neuroimaging measures of brain architecture, both structural and functional, quantify the relative predictive power of the different imaging modalities, and reveal how each modality provides unique and complementary information about individual differences in cognitive function.</jats:p> Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability PLOS Computational Biology |
spellingShingle | Rasero, Javier, Sentis, Amy Isabella, Yeh, Fang-Cheng, Verstynen, Timothy, PLOS Computational Biology, Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability, Computational Theory and Mathematics, Cellular and Molecular Neuroscience, Genetics, Molecular Biology, Ecology, Modeling and Simulation, Ecology, Evolution, Behavior and Systematics |
title | Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability |
title_full | Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability |
title_fullStr | Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability |
title_full_unstemmed | Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability |
title_short | Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability |
title_sort | integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability |
title_unstemmed | Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability |
topic | Computational Theory and Mathematics, Cellular and Molecular Neuroscience, Genetics, Molecular Biology, Ecology, Modeling and Simulation, Ecology, Evolution, Behavior and Systematics |
url | http://dx.doi.org/10.1371/journal.pcbi.1008347 |