TY - JOUR
T1 - Predicting brain age from functional connectivity in symptomatic and preclinical Alzheimer disease
AU - for the Dominantly Inherited Alzheimer Network
AU - Millar, Peter R.
AU - Luckett, Patrick H.
AU - Gordon, Brian A.
AU - Benzinger, Tammie L.S.
AU - Schindler, Suzanne E.
AU - Fagan, Anne M.
AU - Cruchaga, Carlos
AU - Bateman, Randall J.
AU - Allegri, Ricardo
AU - Jucker, Mathias
AU - Lee, Jae Hong
AU - Mori, Hiroshi
AU - Salloway, Stephen P.
AU - Yakushev, Igor
AU - Morris, John C.
AU - Ances, Beau M.
AU - Adams, Sarah
AU - Araki, Aki
AU - Barthelemy, Nicolas
AU - Bateman, Randall
AU - Bechara, Jacob
AU - Berman, Sarah
AU - Bodge, Courtney
AU - Brandon, Susan
AU - Brooks, William (Bill)
AU - Brosch, Jared
AU - Buck, Jill
AU - Buckles, Virginia
AU - Carter, Kathleen
AU - Cash, Lisa
AU - Chen, Charlie
AU - Chhatwal, Jasmeer
AU - Mendez, Patricio Chrem
AU - Chua, Jasmin
AU - Chui, Helena
AU - Courtney, Laura
AU - Day, Gregory S.
AU - DeLaCruz, Chrismary
AU - Denner, Darcy
AU - Diffenbacher, Anna
AU - Dincer, Aylin
AU - Donahue, Tamara
AU - Douglas, Jane
AU - Duong, Duc
AU - Egido, Noelia
AU - Esposito, Bianca
AU - Farlow, Marty
AU - Feldman, Becca
AU - Fitzpatrick, Colleen
AU - Flores, Shaney
AU - Fox, Nick
AU - Franklin, Erin
AU - Joseph-Mathurin, Nelly
AU - Fujii, Hisako
AU - Gardener, Samantha
AU - Ghetti, Bernardino
AU - Goate, Alison
AU - Goldberg, Sarah
AU - Goldman, Jill
AU - Gonzalez, Alyssa
AU - Gordon, Brian
AU - Gräber-Sultan, Susanne
AU - Graff-Radford, Neill
AU - Graham, Morgan
AU - Gray, Julia
AU - Gremminger, Emily
AU - Grilo, Miguel
AU - Groves, Alex
AU - Haass, Christian
AU - Häsler, Lisa
AU - Hassenstab, Jason
AU - Hellm, Cortaiga
AU - Herries, Elizabeth
AU - Hoechst-Swisher, Laura
AU - Hofmann, Anna
AU - Holtzman, David
AU - Hornbeck, Russ
AU - Igor, Yakushev
AU - Ihara, Ryoko
AU - Ikeuchi, Takeshi
AU - Ikonomovic, Snezana
AU - Ishii, Kenji
AU - Jack, Clifford
AU - Jerome, Gina
AU - Johnson, Erik
AU - Karch, Celeste
AU - Käser, Stephan
AU - Kasuga, Kensaku
AU - Keefe, Sarah
AU - Klunk, William
AU - Koeppe, Robert
AU - Koudelis, Deb
AU - Kuder-Buletta, Elke
AU - Laske, Christoph
AU - Levey, Allan
AU - Levin, Johannes
AU - Li, Yan
AU - Lopez, Oscar
AU - Marsh, Jacob
AU - Martins, Ralph
AU - Mason, Neal Scott
AU - Masters, Colin
AU - Mawuenyega, Kwasi
AU - McCullough, Austin
AU - McDade, Eric
AU - Mejia, Arlene
AU - Morenas-Rodriguez, Estrella
AU - Morris, John
AU - Mountz, James
AU - Mummery, Cath
AU - Nadkarni, N. eelesh
AU - Nagamatsu, Akemi
AU - Neimeyer, Katie
AU - Niimi, Yoshiki
AU - Noble, James
AU - Norton, Joanne
AU - Nuscher, Brigitte
AU - Obermüller, Ulricke
AU - O'Connor, Antoinette
AU - Patira, Riddhi
AU - Perrin, Richard
AU - Ping, Lingyan
AU - Preische, Oliver
AU - Renton, Alan
AU - Ringman, John
AU - Salloway, Stephen
AU - Schofield, Peter
AU - Senda, Michio
AU - Seyfried, Nicholas T.
AU - Shady, Kristine
AU - Shimada, Hiroyuki
AU - Sigurdson, Wendy
AU - Smith, Jennifer
AU - Smith, Lori
AU - Snitz, Beth
AU - Sohrabi, Hamid
AU - Stephens, Sochenda
AU - Taddei, Kevin
AU - Thompson, Sarah
AU - Vöglein, Jonathan
AU - Wang, Peter
AU - Wang, Qing
AU - Weamer, Elise
AU - Xiong, Chengjie
AU - Xu, Jinbin
AU - Xu, Xiong
N1 - Funding Information:
This research was funded by grants from the National Institutes of Health (P01-AG026276, P01-AG03991, P30 AG0 66444, 5-R01-AG052550-03, 5-R01-AG057680-03, 1-R01-AG067505-01, 1S10RR022984-01A1), with generous support from the Paula and Rodger O. Riney Fund and the Daniel J. Brennan MD Fund. Data collection and sharing for this project was supported by The Dominantly Inherited Alzheimer's Network (DIAN, U19AG032438) funded by the National Institute on Aging (NIA), the German Center for Neurodegenerative Diseases (DZNE), Institute for Neurological Research Fleni, Partial support by the Research and Development Grants for Dementia from Japan Agency for Medical Research and Development, AMED, and the Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI). We thank the participants for their dedication to this project, Haleem Azmy, Anna Boerwinkle, and Dimitre Tomov for technical and processing support, and Manu Goyal for helpful comments. This manuscript has been reviewed by DIAN Study investigators for scientific content and consistency of data interpretation with previous DIAN Study publications. We acknowledge the altruism of the participants and their families and contributions of the DIAN research and support staff at each of the participating sites for their contributions to this study. We thank the personnel of the Administration, Biomarker, Biostatistics, Clinical, Genetics, and Neuroimaging Cores of the Knight ADRC, as well as the Administration, Biomarker, Biostatistics, Clinical, Cognition, Genetics, and Imaging Cores of DIAN.
Funding Information:
This research was funded by grants from the National Institutes of Health (P01-AG026276, P01-AG03991, P30 AG0 66444, 5-R01-AG052550-03, 5-R01-AG057680-03, 1-R01-AG067505-01, 1S10RR022984-01A1), with generous support from the Paula and Rodger O. Riney Fund and the Daniel J. Brennan MD Fund. Data collection and sharing for this project was supported by The Dominantly Inherited Alzheimer's Network (DIAN, U19AG032438) funded by the National Institute on Aging (NIA), the German Center for Neurodegenerative Diseases (DZNE), Institute for Neurological Research Fleni, Partial support by the Research and Development Grants for Dementia from Japan Agency for Medical Research and Development, AMED, and the Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI).
Funding Information:
The authors declare no conflicts of interests. JC Morris is funded by NIH grants # P30 AG066444; P01AG003991; P01AG026276; U19 AG032438; and U19 AG024904. Neither Dr. Morris nor his family owns stock or has equity interest (outside of mutual funds or other externally directed accounts) in any pharmaceutical or biotechnology company. Dr. Salloway reports personal fees from EISAI, NOVARTIS, GENENTECH, ROCHE, GEMVAX, AVID, and LILLY. Dr. Bateman is on the scientific advisory board of C2N Diagnostics and reports research support from Abbvie, Avid Radiopharmaceuticals, Biogen, Centene, Eisai, Eli Lilly and Company, Genentech, Hoffman-LaRoche, Janssen, and United Neuroscience.
Publisher Copyright:
© 2022
PY - 2022/8/1
Y1 - 2022/8/1
N2 - “Brain-predicted age” quantifies apparent brain age compared to normative neuroimaging trajectories. Advanced brain-predicted age has been well established in symptomatic Alzheimer disease (AD), but is underexplored in preclinical AD. Prior brain-predicted age studies have typically used structural MRI, but resting-state functional connectivity (FC) remains underexplored. Our model predicted age from FC in 391 cognitively normal, amyloid-negative controls (ages 18–89). We applied the trained model to 145 amyloid-negative, 151 preclinical AD, and 156 symptomatic AD participants to test group differences. The model accurately predicted age in the training set. FC-predicted brain age gaps (FC-BAG) were significantly older in symptomatic AD and significantly younger in preclinical AD compared to controls. There was minimal correspondence between networks predictive of age and AD. Elevated FC-BAG may reflect network disruption during symptomatic AD. Reduced FC-BAG in preclinical AD was opposite to the expected direction, and may reflect a biphasic response to preclinical AD pathology or may be driven by inconsistency between age-related vs. AD-related networks. Overall, FC-predicted brain age may be a sensitive AD biomarker.
AB - “Brain-predicted age” quantifies apparent brain age compared to normative neuroimaging trajectories. Advanced brain-predicted age has been well established in symptomatic Alzheimer disease (AD), but is underexplored in preclinical AD. Prior brain-predicted age studies have typically used structural MRI, but resting-state functional connectivity (FC) remains underexplored. Our model predicted age from FC in 391 cognitively normal, amyloid-negative controls (ages 18–89). We applied the trained model to 145 amyloid-negative, 151 preclinical AD, and 156 symptomatic AD participants to test group differences. The model accurately predicted age in the training set. FC-predicted brain age gaps (FC-BAG) were significantly older in symptomatic AD and significantly younger in preclinical AD compared to controls. There was minimal correspondence between networks predictive of age and AD. Elevated FC-BAG may reflect network disruption during symptomatic AD. Reduced FC-BAG in preclinical AD was opposite to the expected direction, and may reflect a biphasic response to preclinical AD pathology or may be driven by inconsistency between age-related vs. AD-related networks. Overall, FC-predicted brain age may be a sensitive AD biomarker.
KW - Alzheimer disease
KW - Brain aging
KW - Machine learning
KW - Resting-state functional connectivity
KW - fMRI
UR - http://www.scopus.com/inward/record.url?scp=85129731315&partnerID=8YFLogxK
U2 - 10.1016/j.neuroimage.2022.119228
DO - 10.1016/j.neuroimage.2022.119228
M3 - Article
C2 - 35452806
AN - SCOPUS:85129731315
SN - 1053-8119
VL - 256
JO - NeuroImage
JF - NeuroImage
M1 - 119228
ER -