Resting-state functional connectivity identifies individuals and predicts age in 8-to-26-month-olds
Resting-state functional connectivity (rsFC) measured with fMRI has been used to characterize functional brain maturation in typically and atypically developing children and adults. However, its reliability and utility for predicting development in infants and toddlers is less well understood. Here,...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-08-01
|
| Series: | Developmental Cognitive Neuroscience |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1878929322000664 |
| _version_ | 1828262352942792704 |
|---|---|
| author | Omid Kardan Sydney Kaplan Muriah D. Wheelock Eric Feczko Trevor K.M. Day Óscar Miranda-Domínguez Dominique Meyer Adam T. Eggebrecht Lucille A. Moore Sooyeon Sung Taylor A. Chamberlain Eric Earl Kathy Snider Alice Graham Marc G. Berman Kamil Uğurbil Essa Yacoub Jed T. Elison Christopher D. Smyser Damien A. Fair Monica D. Rosenberg |
| author_facet | Omid Kardan Sydney Kaplan Muriah D. Wheelock Eric Feczko Trevor K.M. Day Óscar Miranda-Domínguez Dominique Meyer Adam T. Eggebrecht Lucille A. Moore Sooyeon Sung Taylor A. Chamberlain Eric Earl Kathy Snider Alice Graham Marc G. Berman Kamil Uğurbil Essa Yacoub Jed T. Elison Christopher D. Smyser Damien A. Fair Monica D. Rosenberg |
| author_sort | Omid Kardan |
| collection | DOAJ |
| description | Resting-state functional connectivity (rsFC) measured with fMRI has been used to characterize functional brain maturation in typically and atypically developing children and adults. However, its reliability and utility for predicting development in infants and toddlers is less well understood. Here, we use fMRI data from the Baby Connectome Project study to measure the reliability and uniqueness of rsFC in infants and toddlers and predict age in this sample (8-to-26 months old; n = 170). We observed medium reliability for within-session infant rsFC in our sample, and found that individual infant and toddler’s connectomes were sufficiently distinct for successful functional connectome fingerprinting. Next, we trained and tested support vector regression models to predict age-at-scan with rsFC. Models successfully predicted novel infants’ age within ± 3.6 months error and a prediction R2 = .51. To characterize the anatomy of predictive networks, we grouped connections into 11 infant-specific resting-state functional networks defined in a data-driven manner. We found that connections between regions of the same network—i.e. within-network connections—predicted age significantly better than between-network connections. Looking ahead, these findings can help characterize changes in functional brain organization in infancy and toddlerhood and inform work predicting developmental outcome measures in this age range. |
| first_indexed | 2024-04-13T03:54:29Z |
| format | Article |
| id | doaj.art-36649cae5b714f408572f1b5655334d0 |
| institution | Directory Open Access Journal |
| issn | 1878-9293 |
| language | English |
| last_indexed | 2024-04-13T03:54:29Z |
| publishDate | 2022-08-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Developmental Cognitive Neuroscience |
| spelling | doaj.art-36649cae5b714f408572f1b5655334d02022-12-22T03:03:42ZengElsevierDevelopmental Cognitive Neuroscience1878-92932022-08-0156101123Resting-state functional connectivity identifies individuals and predicts age in 8-to-26-month-oldsOmid Kardan0Sydney Kaplan1Muriah D. Wheelock2Eric Feczko3Trevor K.M. Day4Óscar Miranda-Domínguez5Dominique Meyer6Adam T. Eggebrecht7Lucille A. Moore8Sooyeon Sung9Taylor A. Chamberlain10Eric Earl11Kathy Snider12Alice Graham13Marc G. Berman14Kamil Uğurbil15Essa Yacoub16Jed T. Elison17Christopher D. Smyser18Damien A. Fair19Monica D. Rosenberg20University of Chicago, USA; Corresponding authors.Washington University in St. Louis School of Medicine, USAWashington University in St. Louis School of Medicine, USAUniversity of Minnesota, USAUniversity of Minnesota, USAUniversity of Minnesota, USAWashington University in St. Louis School of Medicine, USAWashington University in St. Louis School of Medicine, USAOregon Health & Science University, USAUniversity of Minnesota, USAUniversity of Chicago, USAOregon Health & Science University, USAOregon Health & Science University, USAOregon Health & Science University, USAUniversity of Chicago, USAUniversity of Minnesota, USAUniversity of Minnesota, USAUniversity of Minnesota, USAWashington University in St. Louis School of Medicine, USAUniversity of Minnesota, USAUniversity of Chicago, USA; Corresponding authors.Resting-state functional connectivity (rsFC) measured with fMRI has been used to characterize functional brain maturation in typically and atypically developing children and adults. However, its reliability and utility for predicting development in infants and toddlers is less well understood. Here, we use fMRI data from the Baby Connectome Project study to measure the reliability and uniqueness of rsFC in infants and toddlers and predict age in this sample (8-to-26 months old; n = 170). We observed medium reliability for within-session infant rsFC in our sample, and found that individual infant and toddler’s connectomes were sufficiently distinct for successful functional connectome fingerprinting. Next, we trained and tested support vector regression models to predict age-at-scan with rsFC. Models successfully predicted novel infants’ age within ± 3.6 months error and a prediction R2 = .51. To characterize the anatomy of predictive networks, we grouped connections into 11 infant-specific resting-state functional networks defined in a data-driven manner. We found that connections between regions of the same network—i.e. within-network connections—predicted age significantly better than between-network connections. Looking ahead, these findings can help characterize changes in functional brain organization in infancy and toddlerhood and inform work predicting developmental outcome measures in this age range.http://www.sciencedirect.com/science/article/pii/S1878929322000664Functional connectivityFMRIReliabilityDevelopmentMachine learningAge prediction |
| spellingShingle | Omid Kardan Sydney Kaplan Muriah D. Wheelock Eric Feczko Trevor K.M. Day Óscar Miranda-Domínguez Dominique Meyer Adam T. Eggebrecht Lucille A. Moore Sooyeon Sung Taylor A. Chamberlain Eric Earl Kathy Snider Alice Graham Marc G. Berman Kamil Uğurbil Essa Yacoub Jed T. Elison Christopher D. Smyser Damien A. Fair Monica D. Rosenberg Resting-state functional connectivity identifies individuals and predicts age in 8-to-26-month-olds Developmental Cognitive Neuroscience Functional connectivity FMRI Reliability Development Machine learning Age prediction |
| title | Resting-state functional connectivity identifies individuals and predicts age in 8-to-26-month-olds |
| title_full | Resting-state functional connectivity identifies individuals and predicts age in 8-to-26-month-olds |
| title_fullStr | Resting-state functional connectivity identifies individuals and predicts age in 8-to-26-month-olds |
| title_full_unstemmed | Resting-state functional connectivity identifies individuals and predicts age in 8-to-26-month-olds |
| title_short | Resting-state functional connectivity identifies individuals and predicts age in 8-to-26-month-olds |
| title_sort | resting state functional connectivity identifies individuals and predicts age in 8 to 26 month olds |
| topic | Functional connectivity FMRI Reliability Development Machine learning Age prediction |
| url | http://www.sciencedirect.com/science/article/pii/S1878929322000664 |
| work_keys_str_mv | AT omidkardan restingstatefunctionalconnectivityidentifiesindividualsandpredictsagein8to26montholds AT sydneykaplan restingstatefunctionalconnectivityidentifiesindividualsandpredictsagein8to26montholds AT muriahdwheelock restingstatefunctionalconnectivityidentifiesindividualsandpredictsagein8to26montholds AT ericfeczko restingstatefunctionalconnectivityidentifiesindividualsandpredictsagein8to26montholds AT trevorkmday restingstatefunctionalconnectivityidentifiesindividualsandpredictsagein8to26montholds AT oscarmirandadominguez restingstatefunctionalconnectivityidentifiesindividualsandpredictsagein8to26montholds AT dominiquemeyer restingstatefunctionalconnectivityidentifiesindividualsandpredictsagein8to26montholds AT adamteggebrecht restingstatefunctionalconnectivityidentifiesindividualsandpredictsagein8to26montholds AT lucilleamoore restingstatefunctionalconnectivityidentifiesindividualsandpredictsagein8to26montholds AT sooyeonsung restingstatefunctionalconnectivityidentifiesindividualsandpredictsagein8to26montholds AT taylorachamberlain restingstatefunctionalconnectivityidentifiesindividualsandpredictsagein8to26montholds AT ericearl restingstatefunctionalconnectivityidentifiesindividualsandpredictsagein8to26montholds AT kathysnider restingstatefunctionalconnectivityidentifiesindividualsandpredictsagein8to26montholds AT alicegraham restingstatefunctionalconnectivityidentifiesindividualsandpredictsagein8to26montholds AT marcgberman restingstatefunctionalconnectivityidentifiesindividualsandpredictsagein8to26montholds AT kamilugurbil restingstatefunctionalconnectivityidentifiesindividualsandpredictsagein8to26montholds AT essayacoub restingstatefunctionalconnectivityidentifiesindividualsandpredictsagein8to26montholds AT jedtelison restingstatefunctionalconnectivityidentifiesindividualsandpredictsagein8to26montholds AT christopherdsmyser restingstatefunctionalconnectivityidentifiesindividualsandpredictsagein8to26montholds AT damienafair restingstatefunctionalconnectivityidentifiesindividualsandpredictsagein8to26montholds AT monicadrosenberg restingstatefunctionalconnectivityidentifiesindividualsandpredictsagein8to26montholds |