{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T10:58:38Z","timestamp":1774436318248,"version":"3.50.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1008347","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2021,3,22]],"date-time":"2021-03-22T00:00:00Z","timestamp":1616371200000}}],"reference-count":61,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2021,3,5]],"date-time":"2021-03-05T00:00:00Z","timestamp":1614902400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<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":"10.1371\/journal.pcbi.1008347","type":"journal-article","created":{"date-parts":[[2021,3,5]],"date-time":"2021-03-05T13:49:04Z","timestamp":1614952144000},"page":"e1008347","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":74,"title":["Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1661-2856","authenticated-orcid":true,"given":"Javier","family":"Rasero","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3231-4322","authenticated-orcid":true,"given":"Amy Isabella","family":"Sentis","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7946-2173","authenticated-orcid":true,"given":"Fang-Cheng","family":"Yeh","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4720-0336","authenticated-orcid":true,"given":"Timothy","family":"Verstynen","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2021,3,5]]},"reference":[{"issue":"1","key":"pcbi.1008347.ref001","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/j.neuron.2015.09.027","article-title":"Brain Networks and Cognitive Architectures","volume":"88","author":"SE Petersen","year":"2015","journal-title":"Neuron"},{"issue":"1","key":"pcbi.1008347.ref002","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1016\/j.neuroimage.2004.04.025","article-title":"Structural brain variation and general intelligence","volume":"23","author":"RJ Haier","year":"2004","journal-title":"NeuroImage"},{"issue":"3","key":"pcbi.1008347.ref003","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1016\/S0160-2896(97)90039-8","article-title":"Intelligence and regional brain volumes in normal controls","volume":"25","author":"LA Flashman","year":"1997","journal-title":"Intelligence"},{"issue":"10","key":"pcbi.1008347.ref004","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1097\/01.JGP.0000238502.40963.ac","article-title":"The Relationship Between Frontal Gray Matter Volume and Cognition Varies Across the Healthy Adult Lifespan","volume":"14","author":"ME Zimmerman","year":"2006","journal-title":"The American Journal of Geriatric Psychiatry"},{"issue":"2","key":"pcbi.1008347.ref005","first-page":"83","article-title":"The association between brain volume and intelligence is of genetic origin","volume":"5","author":"D Posthuma","year":"2002","journal-title":"Nature News"},{"issue":"9","key":"pcbi.1008347.ref006","doi-asserted-by":"crossref","first-page":"2163","DOI":"10.1093\/cercor\/bhl125","article-title":"Relationships between IQ and Regional Cortical Gray Matter Thickness in Healthy Adults","volume":"17","author":"KL Narr","year":"2006","journal-title":"Cerebral Cortex"},{"issue":"6","key":"pcbi.1008347.ref007","doi-asserted-by":"crossref","first-page":"1608","DOI":"10.1093\/cercor\/bht357","article-title":"Changes in Thickness and Surface Area of the Human Cortex and Their Relationship with Intelligence","volume":"25","author":"HG Schnack","year":"2015","journal-title":"Cerebral Cortex"},{"issue":"10","key":"pcbi.1008347.ref008","first-page":"878","article-title":"Resting-State Connectivity and Its Association With Cognitive Performance, Educational Attainment, and Household Income in the UK Biobank","volume":"3","author":"X Shen","year":"2018","journal-title":"Biological Psychiatry: Cognitive Neuroscience and Neuroimaging"},{"issue":"2","key":"pcbi.1008347.ref009","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1016\/j.neuroimage.2005.01.054","article-title":"Common and unique components of response inhibition revealed by fMRI","volume":"27","author":"TD Wager","year":"2005","journal-title":"NeuroImage"},{"issue":"23","key":"pcbi.1008347.ref010","doi-asserted-by":"crossref","first-page":"7619","DOI":"10.1523\/JNEUROSCI.1443-09.2009","article-title":"Efficiency of Functional Brain Networks and Intellectual Performance","volume":"29","author":"MP van den Heuvel","year":"2009","journal-title":"Journal of Neuroscience"},{"issue":"5","key":"pcbi.1008347.ref011","first-page":"1","article-title":"Brain Anatomical Network and Intelligence","volume":"5","author":"Y Li","year":"2009","journal-title":"PLOS Computational Biology"},{"key":"pcbi.1008347.ref012","article-title":"Neuroimaging-based Individualized Prediction of Cognition and Behavior for Mental Disorders and Health: Methods and Promises","author":"J Sui","journal-title":"Biological Psychiatry"},{"issue":"1756","key":"pcbi.1008347.ref013","doi-asserted-by":"crossref","first-page":"20170284","DOI":"10.1098\/rstb.2017.0284","article-title":"A distributed brain network predicts general intelligence from resting-state human neuroimaging data","volume":"373","author":"J Dubois","year":"2018","journal-title":"Philosophical Transactions of the Royal Society B: Biological Sciences"},{"issue":"11","key":"pcbi.1008347.ref014","doi-asserted-by":"crossref","first-page":"1664","DOI":"10.1038\/nn.4135","article-title":"Functional connectome fingerprinting: identifying individuals using patterns of brain connectivity","volume":"18","author":"ES Finn","year":"2015","journal-title":"Nature Neuroscience"},{"issue":"1","key":"pcbi.1008347.ref015","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1162\/NETN_a_00031","article-title":"Local connectome phenotypes predict social, health, and cognitive factors","volume":"2","author":"MA Powell","year":"2017","journal-title":"Network Neuroscience"},{"key":"pcbi.1008347.ref016","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.neuroimage.2013.10.067","article-title":"On the interpretation of weight vectors of linear models in multivariate neuroimaging","volume":"87","author":"S Haufe","year":"2014","journal-title":"NeuroImage"},{"key":"pcbi.1008347.ref017","doi-asserted-by":"crossref","first-page":"e43464","DOI":"10.7554\/eLife.43464","article-title":"Empirical examination of the replicability of associations between brain structure and psychological variables","volume":"8","author":"S Kharabian Masouleh","year":"2019","journal-title":"eLife"},{"issue":"45","key":"pcbi.1008347.ref018","doi-asserted-by":"crossref","first-page":"9658","DOI":"10.1523\/JNEUROSCI.0900-18.2018","article-title":"Unique Mapping of Structural and Functional Connectivity on Cognition","volume":"38","author":"J Zimmermann","year":"2018","journal-title":"Journal of Neuroscience"},{"issue":"1","key":"pcbi.1008347.ref019","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1016\/j.neuroimage.2008.06.037","article-title":"Combining multivariate voxel selection and support vector machines for mapping and classification of fMRI spatial patterns","volume":"43","author":"FD Martino]","year":"2008","journal-title":"NeuroImage"},{"key":"pcbi.1008347.ref020","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neuroimage.2014.11.045","article-title":"Finding imaging patterns of structural covariance via Non-Negative Matrix Factorization","volume":"108","author":"A Sotiras","year":"2015","journal-title":"NeuroImage"},{"issue":"3","key":"pcbi.1008347.ref021","doi-asserted-by":"crossref","first-page":"883","DOI":"10.1016\/j.neuroimage.2010.01.005","article-title":"Estimating the age of healthy subjects from T1-weighted MRI scans using kernel methods: Exploring the influence of various parameters","volume":"50","author":"K Franke","year":"2010","journal-title":"NeuroImage"},{"issue":"7","key":"pcbi.1008347.ref022","doi-asserted-by":"crossref","first-page":"1204","DOI":"10.1109\/JSTSP.2016.2600400","article-title":"Transmodal Learning of Functional Networks for Alzheimer\u2019s Disease Prediction","volume":"10","author":"M Rahim","year":"2016","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"issue":"10","key":"pcbi.1008347.ref023","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A Survey on Transfer Learning","volume":"22","author":"SJ Pan","year":"2010","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"issue":"2","key":"pcbi.1008347.ref024","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/S0893-6080(05)80023-1","article-title":"Stacked generalization","volume":"5","author":"DH Wolpert","year":"1992","journal-title":"Neural Networks"},{"key":"pcbi.1008347.ref025","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1016\/j.neuroimage.2016.11.005","article-title":"Predicting brain-age from multimodal imaging data captures cognitive impairment","volume":"148","author":"F Liem","year":"2017","journal-title":"NeuroImage"},{"key":"pcbi.1008347.ref026","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1016\/j.neuroimage.2013.05.041","article-title":"The WU-Minn Human Connectome Project: An overview","volume":"80","author":"DCV Essen]","year":"2013","journal-title":"NeuroImage"},{"issue":"422","key":"pcbi.1008347.ref027","doi-asserted-by":"crossref","first-page":"486","DOI":"10.1080\/01621459.1993.10476299","article-title":"Linear Model Selection by Cross-Validation","volume":"88","author":"J Shao","year":"1993","journal-title":"Journal of the American Statistical Association"},{"key":"pcbi.1008347.ref028","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.neuroimage.2018.05.027","article-title":"Population-averaged atlas of the macroscale human structural connectome and its network topology","volume":"178","author":"FC Yeh","year":"2018","journal-title":"NeuroImage"},{"issue":"1","key":"pcbi.1008347.ref029","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1037\/h0046743","article-title":"Theory of fluid and crystallized intelligence: A critical experiment","volume":"54","author":"RB Cattell","year":"1963","journal-title":"Journal of Educational Psychology"},{"key":"pcbi.1008347.ref030","article-title":"Fluid and crystallised intelligence are associated with distinct regionalisation patterns of cortical morphology","author":"CE Palmer","year":"2020","journal-title":"bioRxiv"},{"issue":"3","key":"pcbi.1008347.ref031","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1038\/nn1014","article-title":"Neural mechanisms of general fluid intelligence","volume":"6","author":"JR Gray","year":"2003","journal-title":"Nature Neuroscience"},{"issue":"2","key":"pcbi.1008347.ref032","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1016\/j.intell.2008.09.008","article-title":"Exploring possible neural mechanisms of intelligence differences using processing speed and working memory tasks: An fMRI study","volume":"37","author":"GD Waiter","year":"2009","journal-title":"Intelligence"},{"issue":"2","key":"pcbi.1008347.ref033","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1016\/j.neuroimage.2005.01.035","article-title":"Neural correlates of intelligence as revealed by fMRI of fluid analogies","volume":"26","author":"JG Geake","year":"2005","journal-title":"NeuroImage"},{"key":"pcbi.1008347.ref034","article-title":"Affective brain patterns as multivariate neural correlates of cardiovascular disease risk","author":"PJ Gianaros","year":"2020","journal-title":"Social Cognitive and Affective Neuroscience"},{"issue":"1","key":"pcbi.1008347.ref035","doi-asserted-by":"crossref","first-page":"10532","DOI":"10.1038\/srep10532","article-title":"A novel brain partition highlights the modular skeleton shared by structure and function","volume":"5","author":"I Diez","year":"2015","journal-title":"Scientific Reports"},{"issue":"1","key":"pcbi.1008347.ref036","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.ijpsycho.2008.12.019","article-title":"Combining fMRI with EEG and MEG in order to relate patterns of brain activity to cognition","volume":"73","author":"WJ Freeman","year":"2009","journal-title":"International Journal of Psychophysiology"},{"key":"pcbi.1008347.ref037","article-title":"Towards Reproducible Brain-Wide Association Studies","author":"S Marek","year":"2020","journal-title":"bioRxiv"},{"key":"pcbi.1008347.ref038","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1016\/j.neuroimage.2019.04.016","article-title":"Global signal regression strengthens association between resting-state functional connectivity and behavior","volume":"196","author":"J Li","year":"2019","journal-title":"NeuroImage"},{"key":"pcbi.1008347.ref039","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1016\/j.neuroimage.2016.11.052","article-title":"Towards a consensus regarding global signal regression for resting state functional connectivity MRI","volume":"154","author":"K Murphy","year":"2017","journal-title":"NeuroImage"},{"key":"pcbi.1008347.ref040","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.neuroimage.2019.02.057","article-title":"Ten simple rules for predictive modeling of individual differences in neuroimaging","volume":"193","author":"D Scheinost","year":"2019","journal-title":"NeuroImage"},{"key":"pcbi.1008347.ref041","article-title":"Establishment of Best Practices for Evidence for Prediction: A Review","author":"RA Poldrack","year":"2019","journal-title":"JAMA Psychiatry"},{"issue":"7","key":"pcbi.1008347.ref042","doi-asserted-by":"crossref","first-page":"1204","DOI":"10.1109\/JSTSP.2016.2600400","article-title":"Transmodal Learning of Functional Networks for Alzheimer\u2019s Disease Prediction","volume":"10","author":"M Rahim","year":"2016","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"issue":"12","key":"pcbi.1008347.ref043","doi-asserted-by":"crossref","first-page":"4663","DOI":"10.1002\/hbm.24312","article-title":"Structure\u2013function multi-scale connectomics reveals a major role of the fronto-striato-thalamic circuit in brain aging","volume":"39","author":"P Bonifazi","year":"2018","journal-title":"Human Brain Mapping"},{"issue":"2","key":"pcbi.1008347.ref044","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1162\/NETN_a_00010","article-title":"Fluid and flexible minds: Intelligence reflects synchrony in the brain\u2019s intrinsic network architecture","volume":"1","author":"MA Ferguson","year":"2017","journal-title":"Network Neuroscience"},{"issue":"1","key":"pcbi.1008347.ref045","doi-asserted-by":"crossref","first-page":"32328","DOI":"10.1038\/srep32328","article-title":"Functional brain networks related to individual differences in human intelligence at rest","volume":"6","author":"LJ Hearne","year":"2016","journal-title":"Scientific Reports"},{"issue":"46","key":"pcbi.1008347.ref046","doi-asserted-by":"crossref","first-page":"16574","DOI":"10.1073\/pnas.1405672111","article-title":"Anatomical accuracy of brain connections derived from diffusion MRI tractography is inherently limited","volume":"111","author":"C Thomas","year":"2014","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"21","key":"pcbi.1008347.ref047","doi-asserted-by":"crossref","first-page":"E2820","DOI":"10.1073\/pnas.1418198112","article-title":"Superficial white matter fiber systems impede detection of long-range cortical connections in diffusion MR tractography","volume":"112","author":"C Reveley","year":"2015","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"pcbi.1008347.ref048","doi-asserted-by":"crossref","first-page":"247","DOI":"10.3389\/fnins.2016.00247","article-title":"Microstructure Informed Tractography: Pitfalls and Open Challenges","volume":"10","author":"A Daducci","year":"2016","journal-title":"Frontiers in Neuroscience"},{"issue":"1","key":"pcbi.1008347.ref049","doi-asserted-by":"crossref","first-page":"18112","DOI":"10.1038\/srep18112","article-title":"The global landscape of cognition: hierarchical aggregation as an organizational principle of human cortical networks and functions","volume":"5","author":"P Taylor","year":"2015","journal-title":"Scientific Reports"},{"key":"pcbi.1008347.ref050","doi-asserted-by":"crossref","first-page":"215","DOI":"10.3389\/fnagi.2017.00215","article-title":"Group-Level Progressive Alterations in Brain Connectivity Patterns Revealed by Diffusion-Tensor Brain Networks across Severity Stages in Alzheimer\u2019s Disease","volume":"9","author":"J Rasero","year":"2017","journal-title":"Frontiers in Aging Neuroscience"},{"issue":"4","key":"pcbi.1008347.ref051","doi-asserted-by":"crossref","first-page":"1782","DOI":"10.1016\/j.neuroimage.2012.08.067","article-title":"Structural and diffusion MRI measures of the hippocampus and memory performance","volume":"63","author":"T den Heijer","year":"2012","journal-title":"NeuroImage"},{"key":"pcbi.1008347.ref052","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/j.neuroimage.2013.04.127","article-title":"The minimal preprocessing pipelines for the Human Connectome Project","volume":"80","author":"MF Glasser","year":"2013","journal-title":"NeuroImage"},{"issue":"7615","key":"pcbi.1008347.ref053","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1038\/nature18933","article-title":"A multi-modal parcellation of human cerebral cortex","volume":"536","author":"MF Glasser","year":"2016","journal-title":"Nature"},{"key":"pcbi.1008347.ref054","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.neuroimage.2018.10.006","article-title":"Mapping the human brain\u2019s cortical-subcortical functional network organization","volume":"185","author":"JL Ji","year":"2019","journal-title":"NeuroImage"},{"key":"pcbi.1008347.ref055","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1016\/j.neuroimage.2015.10.053","article-title":"Connectometry: A statistical approach harnessing the analytical potential of the local connectome","volume":"125","author":"FC Yeh","year":"2016","journal-title":"NeuroImage"},{"issue":"1","key":"pcbi.1008347.ref056","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.neuroimage.2011.06.021","article-title":"NTU-90: A high angular resolution brain atlas constructed by q-space diffeomorphic reconstruction","volume":"58","author":"FC Yeh","year":"2011","journal-title":"NeuroImage"},{"issue":"9","key":"pcbi.1008347.ref057","doi-asserted-by":"crossref","first-page":"1626","DOI":"10.1109\/TMI.2010.2045126","article-title":"Generalized $ q$-Sampling Imaging","volume":"29","author":"FC Yeh","year":"2010","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"pcbi.1008347.ref058","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1016\/j.neuroimage.2013.05.033","article-title":"Function in the human connectome: Task-fMRI and individual differences in behavior","volume":"80","author":"DM Barch","year":"2013","journal-title":"NeuroImage"},{"issue":"1","key":"pcbi.1008347.ref059","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1007\/BF00117832","article-title":"Stacked regressions","volume":"24","author":"L Breiman","year":"1996","journal-title":"Machine Learning"},{"key":"pcbi.1008347.ref060","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"pcbi.1008347.ref061","article-title":"Controlling for effects of confounding variables on machine learning predictions","author":"R Dinga","year":"2020","journal-title":"bioRxiv"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1008347","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2021,3,22]],"date-time":"2021-03-22T00:00:00Z","timestamp":1616371200000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1008347","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,22]],"date-time":"2021-03-22T13:36:00Z","timestamp":1616420160000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1008347"}},"subtitle":[],"editor":[{"given":"Emma Claire","family":"Robinson","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,3,5]]},"references-count":61,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2021,3,5]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1008347","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2020.09.01.278747","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,5]]}}}