The brains of people with advanced Alzheimer’s disease often look older than expected based on the patients’ actual age. This ‘brain age gap’ (how old a brain appears compared to the person’s chronological age) can be calculated thanks to machine learning algorithms which analyse images of the organ to detect changes related to aging. Traditionally, these models have relied on images of the brain structure, such as the size and thickness of various brain areas; more recent models have started to use activity data, such as how different brain regions work together to form functional networks.

While the brain age gap is a useful measure for researchers who investigate aging and disease, it is not yet helpful for clinicians. For example, it is unclear whether the machine learning algorithm could detect changes in the brains of individuals in the initial stages of Alzheimer’s disease, before they start to manifest cognitive symptoms.

Millar et al. explored this question by testing whether models which incorporate structural and activity data could be more sensitive to these early changes. Three machine learning algorithms (relying on either structural data, activity data, or combination of both) were used to predict the brain ages of participants with no sign of disease; with biological markers of Alzheimer’s disease but preserved cognitive functions; and with marked cognitive symptoms of the condition.

Overall, the combined model was slightly better at predicting the brain age of healthy volunteers, and all three models indicated that patients with dementia had a brain which looked older than normal. For this group, the model based on structural data was also able to make predictions which reflected the severity of cognitive decline. Crucially, the algorithm which used activity data predicted that, in individuals with biological markers of Alzheimer’s disease but no cognitive impairment, the brain looked in fact younger than chronological age. Exactly why this is the case remains unclear, but this signal may be driven by neural processes which unfold in the early stages of the disease. While more research is needed, the work by Millar et al. helps to explore how various types of machine learning models could one day be used to assess and predict brain health.

Alzheimer disease (AD) is marked by structural and functional disruptions in the brain, some of which can be observed through multimodal magnetic resonance imaging (MRI) in preclinical and symptomatic stages of the disease (Frisoni et al., 2010; Brier et al., 2014a). More recently, the ‘brain-predicted age’ framework has emerged as a promising tool for neuroimaging analyses, leveraging recent developments and accessibility of machine-learning techniques, as well as large-scale, publicly available neuroimaging datasets (Cole and Franke, 2017b; Franke and Gaser, 2019). These models are trained to quantify how ‘old’ a brain appears, as compared to a normative sample of training data - typically consisting of cognitively normal participants across the adult lifespan (e.g., Cole et al., 2015). Thus, the framework allows for a residual-based interpretation of the brain age gap (BAG), defined as the difference between model-predicted age and chronological age, as an index of vulnerability and/or resistance to underlying disease pathology. Indeed, several studies have demonstrated that BAG is elevated (i.e. the brain ‘appears older’ than expected) in a host of neurological and psychiatric disorders, including symptomatic AD (Franke et al., 2010; Franke and Gaser, 2012; Gaser et al., 2013), as well as schizophrenia (e.g., Koutsouleris et al., 2014), HIV (e.g., Cole et al., 2017c), and type-2 diabetes (e.g., Franke et al., 2013), and moreover, predicts mortality (Cole et al., 2018). Conversely, lower BAG is associated with lower risk of disease progression (Gaser et al., 2013; Wang et al., 2019; Bocancea et al., 2021). Critically, at least one comparison suggests that BAG exceeds other established MRI (hippocampal volume) and CSF (pTau and Aβ42) biomarkers in sensitivity to AD progression (Gaser et al., 2013). Thus, by summarizing complex, non-linear, highly multivariate patterns of neuroimaging features into a simple, interpretable summary metric, BAG may reflect a comprehensive biomarker of brain health.

Several studies have established that symptomatic AD and mild cognitive impairment (MCI) are associated with elevated BAG (Cole and Franke, 2017b; Franke and Gaser, 2019). However, the sensitivity of these model estimates to AD in the presymptmatic stage (i.e. present amyloid pathology in the absence of cognitive decline [Sperling et al., 2011]) is less clear. The development of sensitive, reliable, non-invasive biomarkers of preclinical AD pathology is critical for the assessment of individual AD risk, as well as the evaluation of AD clinical prevention trials. Recent studies have demonstrated that greater BAG is associated with greater amyloid PET burden in a Down syndrome cohort (Cole et al., 2017a) and with greater tau PET burden in sporadic MCI and symptomatic AD (Lee et al., 2022). One approach to maximize sensitivity of BAG to presymptomatic AD pathology may be to train brain age models exclusively on amyloid-negative participants. As undetected AD pathology might influence MRI measures, and thus confound effects otherwise attributed to ‘healthy aging’ (Brier et al., 2014b), including the patterns learned by a traditional brain age model, an alternative model trained on amyloid-negative participants only might be more sensitive to detect presymptomatic AD pathology as deviations in BAG. Indeed, one recent study demonstrated that an amyloid-negative trained brain age model (Ly et al., 2020) is more sensitive to progressive stages of AD than a typical amyloid-insensitive model (Cole et al., 2015). However, this comparison included amyloid-negative and amyloid-positive test samples from two separate cohorts and thus may be driven by cohort, scanner, and/or site differences. To validate the applicability of the brain-predicted age approach to presymptomatic AD, it is important to test a model’s sensitivity to amyloid status, as well as continuous relationships with AD biomarkers, within a single cohort. Another recent comparison demonstrated that both traditional and amyloid-negative trained brain age models were similarly related to molecular AD biomarkers, but that further attempts to ‘disentangle’ AD from brain age by including more advanced AD continuum participants in the training sample significantly reduced relationships between brain age and AD markers (Hwang et al., 2022). Thus, in this study, we will apply the amyloid-negative training approach to a multimodal MRI dataset in order to maximize sensitivity to AD pathology in the presymptomatic stage.

Most of the brain-predicted age reports described above focused primarily on structural MRI. However, other studies have successfully modeled brain age using a variety of other modalities, including metabolic PET (Goyal et al., 2019; Lee et al., 2022), diffusion MRI (Cherubini et al., 2016; Petersen et al., 2022), and functional connectivity (FC) (Dosenbach et al., 2010; Liem et al., 2017; Eavani et al., 2018; Nielsen et al., 2019). Integration of multiple neuroimaging modalities may maximize sensitivity of BAG estimates to preclinical AD. Indeed, recent multimodal comparisons suggest that structural MRI and FC capture complementary age-related signals (Eavani et al., 2018; Dunås et al., 2021) and that age prediction may be improved by incorporating multiple modalities (Liem et al., 2017; Engemann et al., 2020). One recent study has shown that BAG estimates from an FC graph theory-based model are significantly elevated in autosomal dominant AD mutation carriers and are positively associated with amyloid PET (Gonneaud et al., 2021). Furthermore, we have recently demonstrated that FC correlation-based BAG estimates are surprisingly reduced in cognitively normal participants with evidence of amyloid pathology and elevated pTau, as well as in cognitively normal APOE ε4 carriers at genetic risk of AD (Millar et al., 2022). Thus, incorporating FC into BAG models may improve sensitivity to early AD.

This project aimed to develop multimodal models of brain-predicted age, incorporating both FC and structural MRI. Participants with presymptomatic AD pathology were excluded from the training set to maximize sensitivity. We hypothesized that BAG estimates would be sensitive to the presence of AD biomarkers and early cognitive impairment. We further considered whether estimates were continuously associated with AD biomarkers of amyloid and tau, as well as cognition. We hypothesized that FC and structural MRI would capture complementary signals related to age and AD. Thus, we systematically compared models trained on unimodal FC, structural MRI, and combined modalities to test the added utility of multimodal integration in accurately predicting age and whether each modality captures unique relationships with AD biomarkers and cognition.

We first found that machine-learning models successfully predicted age when trained on FC, structural MRI, and multimodal datasets. As expected, the structural model predicted age with greater accuracy than the FC model, but the multimodal model outperformed both unimodal models. Second, BAG estimates from all models were significantly elevated in CI participants compared to CN controls. BAG estimates in the FC model were significantly reduced in cognitively normal participants with elevated amyloid, but no structural group differences were observed in presymptomatic stages. Third, interactive relationships were observed, such that greater BAG was associated with greater continuous AD biomarker load in CI, but not in CN, participants. Specifically, in the FC model, such a pattern only appeared in a non-significant interaction predicting CSF pTau/Aβ40. However, in the structural model, these interactions were significantly observed in relation to CSF pTau/Aβ40 and tau PET. In the multimodal model, these same interactions were also observed in addition to a non-significant interaction with amyloid PET. Finally, regarding cognitive relationships, similar interactive patterns were observed, such that in CI participants, greater BAG estimates from structural and multimodal models were associated with lower cognitive performance; however, this relationship was not observed in the FC model.

This project utilized datasets obtained from the Knight ADRC and DIAN. The Knight ADRC and DIAN encourage and facilitate research by current and new investigators, and thus, the data and code are available to all qualified researchers after appropriate review. Requests for access to the data used in this study may be placed to the Knight ADRC Leadership Committee (https://knightadrc.wustl.edu/professionals-clinicians/request-center-resources/) and the DIAN Steering Committee (https://dian.wustl.edu/our-research/for-investigators/dian-observational-study-investigator-resources/data-request-form/). Requests for access to the Ances lab data may be placed to the corresponding author. Code used in this study is available at https://github.com/peterrmillar/MultimodalBrainAge (copy archived at swh:1:rev:de233b8fe813f5fcca317ce0a6353047f0dfbb92).

1. 1. Armitage SG

   (1946) An analysis of certain psychological tests used for the evaluation of brain injury

   Psychological Monographs 60:i1–i48.

   https://doi.org/10.1037/h0093567

   • Google Scholar
2. 1. Aschenbrenner AJ
   2. Gordon BA
   3. Benzinger TLS
   4. Morris JC
   5. Hassenstab JJ

   (2018) Influence of tau PET, amyloid PET, and hippocampal volume on cognition in Alzheimer disease

   Neurology 91:e859–e866.

   https://doi.org/10.1212/WNL.0000000000006075

   • PubMed
   • Google Scholar
3. 1. Bashyam VM
   2. Erus G
   3. Doshi J
   4. Habes M
   5. Nasrallah IM
   6. Truelove-Hill M
   7. Srinivasan D
   8. Mamourian L
   9. Pomponio R
   10. Fan Y
   11. Launer LJ
   12. Masters CL
   13. Maruff P
   14. Zhuo C
   15. Völzke H
   16. Johnson SC
   17. Fripp J
   18. Koutsouleris N
   19. Satterthwaite TD
   20. Wolf D
   21. Gur RE
   22. Gur RC
   23. Morris J
   24. Albert MS
   25. Grabe HJ
   26. Resnick S
   27. Bryan RN
   28. Wolk DA
   29. Shou H
   30. Davatzikos C

   (2020) Mri signatures of brain age and disease over the lifespan based on a deep brain network and 14 468 individuals worldwide

   Brain 143:2312–2324.

   https://doi.org/10.1093/brain/awaa160

   • PubMed
   • Google Scholar
4. 1. Bocancea DI
   2. van Loenhoud AC
   3. Groot C
   4. Barkhof F
   5. van der Flier WM
   6. Ossenkoppele R

   (2021) Measuring resilience and resistance in aging and Alzheimer disease using residual methods: a systematic review and meta-analysis

   Neurology 97:474–488.

   https://doi.org/10.1212/WNL.0000000000012499

   • PubMed
   • Google Scholar
5. 1. Brier MR
   2. Thomas JB
   3. Ances BM

   (2014a) Network dysfunction in alzheimer’s disease: refining the disconnection hypothesis

   Brain Connectivity 4:299–311.

   https://doi.org/10.1089/brain.2014.0236

   • PubMed
   • Google Scholar
6. 1. Brier MR
   2. Thomas JB
   3. Snyder AZ
   4. Wang L
   5. Fagan AM
   6. Benzinger T
   7. Morris JC
   8. Ances BM

   (2014b) Unrecognized preclinical alzheimer disease confounds rs-fcmri studies of normal aging

   Neurology 83:1613–1619.

   https://doi.org/10.1212/WNL.0000000000000939

   • PubMed
   • Google Scholar
7. 1. Butler ER
   2. Chen A
   3. Ramadan R
   4. Le TT
   5. Ruparel K
   6. Moore TM
   7. Satterthwaite TD
   8. Zhang F
   9. Shou H
   10. Gur RC
   11. Nichols TE
   12. Shinohara RT

   (2021) Pitfalls in brain age analyses

   Human Brain Mapping 42:4092–4101.

   https://doi.org/10.1002/hbm.25533

   • PubMed
   • Google Scholar
8. 1. Cabeza R
   2. Albert M
   3. Belleville S
   4. Craik FIM
   5. Duarte A
   6. Grady CL
   7. Lindenberger U
   8. Nyberg L
   9. Park DC
   10. Reuter-Lorenz PA
   11. Rugg MD
   12. Steffener J
   13. Rajah MN

   (2018) Maintenance, reserve and compensation: the cognitive neuroscience of healthy ageing

   Nature Reviews. Neuroscience 19:701–710.

   https://doi.org/10.1038/s41583-018-0068-2

   • PubMed
   • Google Scholar
9. 1. Cherubini A
   2. Caligiuri ME
   3. Peran P
   4. Sabatini U
   5. Cosentino C
   6. Amato F

   (2016) Importance of multimodal MRI in characterizing brain tissue and its potential application for individual age prediction

   IEEE Journal of Biomedical and Health Informatics 20:1232–1239.

   https://doi.org/10.1109/JBHI.2016.2559938

   • PubMed
   • Google Scholar
10. 1. Chien DT
    2. Bahri S
    3. Szardenings AK
    4. Walsh JC
    5. Mu F
    6. Su M-Y
    7. Shankle WR
    8. Elizarov A
    9. Kolb HC

    (2013) Early clinical PET imaging results with the novel PHF-tau radioligand [ F-18 ] -t807

    Journal of Alzheimer’s Disease 34:457–468.

    https://doi.org/10.3233/JAD-122059

    • PubMed
    • Google Scholar
11. 1. Cole JH
    2. Leech R
    3. Sharp DJ

    (2015) Prediction of brain age suggests accelerated atrophy after traumatic brain injury

    Annals of Neurology 77:571–581.

    https://doi.org/10.1002/ana.24367

    • PubMed
    • Google Scholar
12. 1. Cole JH
    2. Annus T
    3. Wilson LR
    4. Remtulla R
    5. Hong YT
    6. Fryer TD
    7. Acosta-Cabronero J
    8. Cardenas-Blanco A
    9. Smith R
    10. Menon DK
    11. Zaman SH
    12. Nestor PJ
    13. Holland AJ

    (2017a) Brain-predicted age in down syndrome is associated with beta amyloid deposition and cognitive decline

    Neurobiology of Aging 56:41–49.

    https://doi.org/10.1016/j.neurobiolaging.2017.04.006

    • Google Scholar
13. 1. Cole JH
    2. Franke K

    (2017b) Predicting age using neuroimaging: innovative brain ageing biomarkers

    Trends in Neurosciences 40:681–690.

    https://doi.org/10.1016/j.tins.2017.10.001

    • PubMed
    • Google Scholar
14. 1. Cole JH
    2. Underwood J
    3. Caan MWA
    4. De Francesco D
    5. van Zoest RA
    6. Leech R
    7. Wit F
    8. Portegies P
    9. Geurtsen GJ
    10. Schmand BA
    11. Schim van der Loeff MF
    12. Franceschi C
    13. Sabin CA
    14. Majoie C
    15. Winston A
    16. Reiss P
    17. Sharp DJ
    18. COBRA collaboration

    (2017c) Increased brain-predicted aging in treated HIV disease

    Neurology 88:1349–1357.

    https://doi.org/10.1212/WNL.0000000000003790

    • PubMed
    • Google Scholar
15. 1. Cole JH
    2. Ritchie SJ
    3. Bastin ME
    4. Valdés Hernández MC
    5. Muñoz Maniega S
    6. Royle N
    7. Corley J
    8. Pattie A
    9. Harris SE
    10. Zhang Q
    11. Wray NR
    12. Redmond P
    13. Marioni RE
    14. Starr JM
    15. Cox SR
    16. Wardlaw JM
    17. Sharp DJ
    18. Deary IJ

    (2018) Brain age predicts mortality

    Molecular Psychiatry 23:1385–1392.

    https://doi.org/10.1038/mp.2017.62

    • PubMed
    • Google Scholar
16. 1. Desikan RS
    2. Ségonne F
    3. Fischl B
    4. Quinn BT
    5. Dickerson BC
    6. Blacker D
    7. Buckner RL
    8. Dale AM
    9. Maguire RP
    10. Hyman BT
    11. Albert MS
    12. Killiany RJ

    (2006) An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest

    NeuroImage 31:968–980.

    https://doi.org/10.1016/j.neuroimage.2006.01.021

    • PubMed
    • Google Scholar
17. 1. Dosenbach NUF
    2. Nardos B
    3. Cohen AL
    4. Fair DA
    5. Power JD
    6. Church JA
    7. Nelson SM
    8. Wig GS
    9. Vogel AC
    10. Lessov-Schlaggar CN
    11. Barnes KA
    12. Dubis JW
    13. Feczko E
    14. Coalson RS
    15. Pruett JR
    16. Barch DM
    17. Petersen SE
    18. Schlaggar BL

    (2010) Prediction of individual brain maturity using fmri

    Science 329:1358–1361.

    https://doi.org/10.1126/science.1194144

    • PubMed
    • Google Scholar
18. 1. Dunås T
    2. Wåhlin A
    3. Nyberg L
    4. Boraxbekk CJ

    (2021) Multimodal image analysis of apparent brain age identifies physical fitness as predictor of brain maintenance

    Cerebral Cortex 31:3393–3407.

    https://doi.org/10.1093/cercor/bhab019

    • PubMed
    • Google Scholar
19. 1. Eavani H
    2. Habes M
    3. Satterthwaite TD
    4. An Y
    5. Hsieh MK
    6. Honnorat N
    7. Erus G
    8. Doshi J
    9. Ferrucci L
    10. Beason-Held LL
    11. Resnick SM
    12. Davatzikos C

    (2018) Heterogeneity of structural and functional imaging patterns of advanced brain aging revealed via machine learning methods

    Neurobiology of Aging 71:41–50.

    https://doi.org/10.1016/j.neurobiolaging.2018.06.013

    • PubMed
    • Google Scholar
20. 1. Engemann DA
    2. Kozynets O
    3. Sabbagh D
    4. Lemaître G
    5. Varoquaux G
    6. Liem F
    7. Gramfort A

    (2020) Combining magnetoencephalography with magnetic resonance imaging enhances learning of surrogate-biomarkers

    eLife 9:e55.

    https://doi.org/10.7554/eLife.54055

    • PubMed
    • Google Scholar
21. 1. Fagan AM
    2. Mintun MA
    3. Mach RH
    4. Lee S-Y
    5. Dence CS
    6. Shah AR
    7. LaRossa GN
    8. Spinner ML
    9. Klunk WE
    10. Mathis CA
    11. DeKosky ST
    12. Morris JC
    13. Holtzman DM

    (2006) Inverse relation between in vivo amyloid imaging load and cerebrospinal fluid Abeta42 in humans

    Annals of Neurology 59:512–519.

    https://doi.org/10.1002/ana.20730

    • PubMed
    • Google Scholar
22. 1. Fischl B
    2. Salat DH
    3. Busa E
    4. Albert M
    5. Dieterich M
    6. Haselgrove C
    7. van der Kouwe A
    8. Killiany R
    9. Kennedy D
    10. Klaveness S
    11. Montillo A
    12. Makris N
    13. Rosen B
    14. Dale AM

    (2002) Whole brain segmentation

    Neuron 33:341–355.

    https://doi.org/10.1016/S0896-6273(02)00569-X

    • PubMed
    • Google Scholar
23. 1. Fischl B

    (2012) FreeSurfer

    NeuroImage 62:774–781.

    https://doi.org/10.1016/j.neuroimage.2012.01.021

    • PubMed
    • Google Scholar
24. 1. Fortin JP
    2. Parker D
    3. Tunç B
    4. Watanabe T
    5. Elliott MA
    6. Ruparel K
    7. Roalf DR
    8. Satterthwaite TD
    9. Gur RC
    10. Gur RE
    11. Schultz RT
    12. Verma R
    13. Shinohara RT

    (2017) Harmonization of multi-site diffusion tensor imaging data

    NeuroImage 161:149–170.

    https://doi.org/10.1016/j.neuroimage.2017.08.047

    • PubMed
    • Google Scholar
25. 1. Fortin JP
    2. Cullen N
    3. Sheline YI
    4. Taylor WD
    5. Aselcioglu I
    6. Cook PA
    7. Adams P
    8. Cooper C
    9. Fava M
    10. McGrath PJ
    11. McInnis M
    12. Phillips ML
    13. Trivedi MH
    14. Weissman MM
    15. Shinohara RT

    (2018) Harmonization of cortical thickness measurements across scanners and sites

    NeuroImage 167:104–120.

    https://doi.org/10.1016/j.neuroimage.2017.11.024

    • PubMed
    • Google Scholar
26. 1. Fox MD
    2. Zhang D
    3. Snyder AZ
    4. Raichle ME

    (2009) The global signal and observed anticorrelated resting state brain networks

    J Neurophysiol 101:3270–3283.

    https://doi.org/10.1152/jn.90777.2008

    • Google Scholar
27. 1. Franke K
    2. Ziegler G
    3. Klöppel S
    4. Gaser C

    (2010) Estimating the age of healthy subjects from T1-weighted MRI scans using kernel methods: exploring the influence of various parameters

    NeuroImage 50:883–892.

    https://doi.org/10.1016/j.neuroimage.2010.01.005

    • PubMed
    • Google Scholar
28. 1. Franke K
    2. Gaser C

    (2012) Longitudinal changes in individual brainage in healthy aging, mild cognitive impairment, and alzheimer’s disease

    GeroPsych 25:235–245.

    https://doi.org/10.1024/1662-9647/a000074

    • Google Scholar
29. 1. Franke K
    2. Gaser C
    3. Manor B
    4. Novak V

    (2013) Advanced brainage in older adults with type 2 diabetes mellitus

    Frontiers in Aging Neuroscience 5:90.

    https://doi.org/10.3389/fnagi.2013.00090

    • PubMed
    • Google Scholar
30. 1. Franke K
    2. Gaser C

    (2019) Ten years of brainage as a neuroimaging biomarker of brain aging: what insights have we gained?

    Frontiers in Neurology 10:789.

    https://doi.org/10.3389/fneur.2019.00789

    • PubMed
    • Google Scholar
31. 1. Frisoni GB
    2. Fox NC
    3. Jack CR
    4. Scheltens P
    5. Thompson PM

    (2010) The clinical use of structural MRI in Alzheimer disease

    Nature Reviews. Neurology 6:67–77.

    https://doi.org/10.1038/nrneurol.2009.215

    • PubMed
    • Google Scholar
32. 1. Gaser C
    2. Franke K
    3. Klöppel S
    4. Koutsouleris N
    5. Sauer H

    (2013) BrainAGE in mild cognitive impaired patients: predicting the conversion to alzheimer’s disease

    PLOS ONE 8:e67346.

    https://doi.org/10.1371/journal.pone.0067346

    • PubMed
    • Google Scholar
33. 1. Gong W
    2. Beckmann CF
    3. Vedaldi A
    4. Smith SM
    5. Peng H

    (2021) Optimising a simple fully convolutional network for accurate brain age prediction in the PAC 2019 challenge

    Frontiers in Psychiatry 12:627996.

    https://doi.org/10.3389/fpsyt.2021.627996

    • PubMed
    • Google Scholar
34. 1. Gonneaud J
    2. Baria AT
    3. Binette AP
    4. Gordon BA
    5. Chhatwal JP
    6. Cruchaga C

    (2021) Accelerated functional brain aging in pre-clinical familial alzheimer’s disease

    Nat Commun 12:5346.

    https://doi.org/10.1038/s41467-021-25492-9

    • Google Scholar
35. Book

    1. Goodglass H
    2. Kaplan E

    (1983)

    Boston Diagnostic Aphasia Examination Booklet, III: Oral Expression: Animal Naming Fluency in Controlled Association

    In Philadelphia: Lea & Febiger.

    • Google Scholar
36. 1. Goyal MS
    2. Blazey TM
    3. Su Y
    4. Couture LE
    5. Durbin TJ
    6. Bateman RJ
    7. Benzinger TLS
    8. Morris JC
    9. Raichle ME
    10. Vlassenko AG

    (2019) Persistent metabolic youth in the aging female brain

    PNAS 116:3251–3255.

    https://doi.org/10.1073/pnas.1815917116

    • PubMed
    • Google Scholar
37. Preprint

    1. Goyal MS
    2. Blazey T
    3. Metcalf NV
    4. McAvoy MP
    5. Strain J
    6. Rahmani M
    7. Durbin TJ
    8. Xiong C
    9. Benzinger TLS
    10. Morris JC
    11. Raichle ME
    12. Vlassenko AG

    (2022) Brain Aerobic Glycolysis and Resilience in Alzheimer Disease

    bioRxiv.

    https://doi.org/10.1101/2022.06.21.497006

    • Google Scholar
38. 1. Grober E
    2. Buschke H
    3. Crystal H
    4. Bang S
    5. Dresner R

    (1988) Screening for dementia by memory testing

    Neurology 38:900–903.

    https://doi.org/10.1212/wnl.38.6.900

    • PubMed
    • Google Scholar
39. 1. Guo T
    2. Korman D
    3. La Joie R
    4. Shaw LM
    5. Trojanowski JQ
    6. Jagust WJ
    7. Landau SM
    8. Alzheimer’s Disease Neuroimaging Initiative

    (2020) Normalization of CSF ptau measurement by aβ40 improves its performance as a biomarker of alzheimer’s disease

    Alzheimer’s Research & Therapy 12:97.

    https://doi.org/10.1186/s13195-020-00665-8

    • PubMed
    • Google Scholar
40. 1. Hansson O
    2. Lehmann S
    3. Otto M
    4. Zetterberg H
    5. Lewczuk P

    (2019) Advantages and disadvantages of the use of the CSF amyloid β (Aβ) 42/40 ratio in the diagnosis of alzheimer’s disease

    Alzheimer’s Research & Therapy 11:34.

    https://doi.org/10.1186/s13195-019-0485-0

    • PubMed
    • Google Scholar
41. 1. Harris SS
    2. Wolf F
    3. De Strooper B
    4. Busche MA

    (2020) Tipping the scales: peptide-dependent dysregulation of neural circuit dynamics in alzheimer’s disease

    Neuron 107:417–435.

    https://doi.org/10.1016/j.neuron.2020.06.005

    • PubMed
    • Google Scholar
42. 1. Hwang G
    2. Abdulkadir A
    3. Erus G
    4. Habes M
    5. Pomponio R
    6. Shou H
    7. Doshi J
    8. Mamourian E
    9. Rashid T
    10. Bilgel M
    11. Fan Y
    12. Sotiras A
    13. Srinivasan D
    14. Morris JC
    15. Albert MS
    16. Bryan NR
    17. Resnick SM
    18. Nasrallah IM
    19. Davatzikos C
    20. Wolk DA
    21. from the iSTAGING consortium
    22. ADNI

    (2022) Disentangling Alzheimer’s disease neurodegeneration from typical brain ageing using machine learning

    Brain Communications 4:fcac117.

    https://doi.org/10.1093/braincomms/fcac117

    • PubMed
    • Google Scholar
43. 1. Jagust WJ
    2. Mormino EC

    (2011) Lifespan brain activity, β-amyloid, and alzheimer’s disease

    Trends in Cognitive Sciences 15:520–526.

    https://doi.org/10.1016/j.tics.2011.09.004

    • PubMed
    • Google Scholar
44. 1. Johnson WE
    2. Li C
    3. Rabinovic A

    (2007) Adjusting batch effects in microarray expression data using empirical Bayes methods

    Biostatistics 8:118–127.

    https://doi.org/10.1093/biostatistics/kxj037

    • PubMed
    • Google Scholar
45. 1. Jones DT
    2. Knopman DS
    3. Gunter JL
    4. Graff-Radford J
    5. Vemuri P
    6. Boeve BF
    7. Petersen RC
    8. Weiner MW
    9. Jack CR

    (2016) Cascading network failure across the alzheimer’s disease spectrum

    Brain 139:547–562.

    https://doi.org/10.1093/brain/awv338

    • PubMed
    • Google Scholar
46. 1. Jones DT
    2. Graff-Radford J
    3. Lowe VJ
    4. Wiste HJ
    5. Gunter JL
    6. Senjem ML
    7. Botha H
    8. Kantarci K
    9. Boeve BF
    10. Knopman DS
    11. Petersen RC
    12. Jack CR

    (2017) Tau, amyloid, and cascading network failure across the alzheimer’s disease spectrum

    Cortex; a Journal Devoted to the Study of the Nervous System and Behavior 97:143–159.

    https://doi.org/10.1016/j.cortex.2017.09.018

    • PubMed
    • Google Scholar
47. 1. Klunk WE
    2. Engler H
    3. Nordberg A
    4. Wang Y
    5. Blomqvist G
    6. Holt DP
    7. Bergström M
    8. Savitcheva I
    9. Huang G
    10. Estrada S
    11. Ausén B
    12. Debnath ML
    13. Barletta J
    14. Price JC
    15. Sandell J
    16. Lopresti BJ
    17. Wall A
    18. Koivisto P
    19. Antoni G
    20. Mathis CA
    21. Långström B

    (2004) Imaging brain amyloid in Alzheimer’s disease with Pittsburgh compound-B

    Annals of Neurology 55:306–319.

    https://doi.org/10.1002/ana.20009

    • PubMed
    • Google Scholar
48. 1. Koutsouleris N
    2. Davatzikos C
    3. Borgwardt S
    4. Gaser C
    5. Bottlender R
    6. Frodl T
    7. Falkai P
    8. Riecher-Rössler A
    9. Möller H-J
    10. Reiser M
    11. Pantelis C
    12. Meisenzahl E

    (2014) Accelerated brain aging in schizophrenia and beyond: a neuroanatomical marker of psychiatric disorders

    Schizophrenia Bulletin 40:1140–1153.

    https://doi.org/10.1093/schbul/sbt142

    • PubMed
    • Google Scholar
49. 1. Le TT
    2. Kuplicki RT
    3. McKinney BA
    4. Yeh HW
    5. Thompson WK
    6. Paulus MP
    7. Tulsa 1000 Investigators

    (2018) A nonlinear simulation framework supports adjusting for age when analyzing brainage

    Frontiers in Aging Neuroscience 10:317.

    https://doi.org/10.3389/fnagi.2018.00317

    • PubMed
    • Google Scholar
50. 1. Lee J
    2. Burkett BJ
    3. Min HK
    4. Senjem ML
    5. Lundt ES
    6. Botha H
    7. Graff-Radford J
    8. Barnard LR
    9. Gunter JL
    10. Schwarz CG
    11. Kantarci K
    12. Knopman DS
    13. Boeve BF
    14. Lowe VJ
    15. Petersen RC
    16. Jack CR
    17. Jones DT

    (2022) Deep learning-based brain age prediction in normal aging and dementia

    Nature Aging 2:412–424.

    https://doi.org/10.1038/s43587-022-00219-7

    • Google Scholar
51. 1. Liang H
    2. Zhang F
    3. Niu X

    (2019) Investigating systematic bias in brain age estimation with application to post-traumatic stress disorders

    Human Brain Mapping 40:3143–3152.

    https://doi.org/10.1002/hbm.24588

    • PubMed
    • Google Scholar
52. 1. Liem F
    2. Varoquaux G
    3. Kynast J
    4. Beyer F
    5. Kharabian Masouleh S
    6. Huntenburg JM
    7. Lampe L
    8. Rahim M
    9. Abraham A
    10. Craddock RC
    11. Riedel-Heller S
    12. Luck T
    13. Loeffler M
    14. Schroeter ML
    15. Witte AV
    16. Villringer A
    17. Margulies DS

    (2017) Predicting brain-age from multimodal imaging data captures cognitive impairment

    NeuroImage 148:179–188.

    https://doi.org/10.1016/j.neuroimage.2016.11.005

    • PubMed
    • Google Scholar
53. 1. Ly M
    2. Yu GZ
    3. Karim HT
    4. Muppidi NR
    5. Mizuno A
    6. Klunk WE
    7. Aizenstein HJ

    (2020) Improving brain age prediction models: incorporation of amyloid status in alzheimer’s disease

    Neurobiology of Aging 87:44–48.

    https://doi.org/10.1016/j.neurobiolaging.2019.11.005

    • PubMed
    • Google Scholar
54. Software

    1. MathWorks

    (2021) Regression learner app, version 1.2.1

    Internet.

    https://www.mathworks.com/help/stats/regression-learner-app.html
55. Preprint

    1. McKay NS
    2. Gordon BA
    3. Hornbeck RC
    4. Jack CR
    5. Koeppe R
    6. Flores S
    7. Keefe S
    8. Hobbs DA
    9. Joseph-Mathurin N
    10. Wang Q
    11. Rahmani F
    12. Chen CD
    13. McCullough A
    14. Koudelis D
    15. Chua J
    16. Ances BM
    17. Millar PR
    18. Nickels M
    19. Perrin RJ
    20. Allegri RF
    21. Berman SB
    22. Brooks WS
    23. Cash DM
    24. Chhatwal JP
    25. Farlow MR
    26. Fox NC
    27. Fulham M
    28. Ghetti B
    29. Graff-Radford N
    30. Ikeuchi T
    31. Day G
    32. Klunk W
    33. Levin J
    34. Lee JH
    35. Martins R
    36. Masters CL
    37. McConathy J
    38. Mori H
    39. Noble JM
    40. Rowe C
    41. Salloway S
    42. Sanchez-Valle R
    43. Schofield PR
    44. Shimada H
    45. Shoji M
    46. Su Y
    47. Suzuki K
    48. Vöglein J
    49. Yakushev I
    50. Swisher L
    51. Cruchaga C
    52. Hassenstab J
    53. Karch C
    54. McDade E
    55. Xiong C
    56. Morris JC
    57. Bateman RJ
    58. Benzinger TLS
    59. Dominantly Inherited Alzheimer Network

    (2022) Neuroimaging within the Dominantly Inherited Alzheimer’s Network (DIAN): PET and MRI

    bioRxiv.

    https://doi.org/10.1101/2022.03.25.485799

    • Google Scholar
56. 1. McKhann GM
    2. Knopman DS
    3. Chertkow H
    4. Hyman BT
    5. Jack CR
    6. Kawas CH
    7. Klunk WE
    8. Koroshetz WJ
    9. Manly JJ
    10. Mayeux R
    11. Mohs RC
    12. Morris JC
    13. Rossor MN
    14. Scheltens P
    15. Carrillo MC
    16. Thies B
    17. Weintraub S
    18. Phelps CH

    (2011) The diagnosis of dementia due to alzheimer’s disease: recommendations from the national institute on aging-alzheimer’s association workgroups on diagnostic guidelines for alzheimer’s disease

    Alzheimer’s & Dementia 7:263–269.

    https://doi.org/10.1016/j.jalz.2011.03.005

    • PubMed
    • Google Scholar
57. 1. Millar PR
    2. Ances BM
    3. Gordon BA
    4. Benzinger TLS
    5. Morris JC
    6. Balota DA

    (2021) Evaluating cognitive relationships with resting-state and task-driven blood oxygen level-dependent variability

    Journal of Cognitive Neuroscience 33:279–302.

    https://doi.org/10.1162/jocn_a_01645

    • PubMed
    • Google Scholar
58. 1. Millar PR
    2. Luckett PH
    3. Gordon BA
    4. Benzinger TLS
    5. Schindler SE
    6. Fagan AM
    7. Cruchaga C
    8. Bateman RJ
    9. Allegri R
    10. Jucker M
    11. Lee JH
    12. Mori H
    13. Salloway SP
    14. Yakushev I
    15. Morris JC
    16. Ances BM
    17. Dominantly Inherited Alzheimer Network

    (2022) Predicting brain age from functional connectivity in symptomatic and preclinical alzheimer disease

    NeuroImage 256:119228.

    https://doi.org/10.1016/j.neuroimage.2022.119228

    • PubMed
    • Google Scholar
59. 1. Mishra S
    2. Gordon BA
    3. Su Y
    4. Christensen J
    5. Friedrichsen K
    6. Jackson K
    7. Hornbeck R
    8. Balota DA
    9. Cairns NJ
    10. Morris JC
    11. Ances BM
    12. Benzinger TLS

    (2017) AV-1451 PET imaging of tau pathology in preclinical Alzheimer disease: defining a summary measure

    NeuroImage 161:171–178.

    https://doi.org/10.1016/j.neuroimage.2017.07.050

    • PubMed
    • Google Scholar
60. 1. Morris JC

    (1993) The clinical dementia rating (CDR): current version and scoring rules

    Neurology 43:2412–2414.

    https://doi.org/10.1212/wnl.43.11.2412-a

    • PubMed
    • Google Scholar
61. 1. Nielsen AN
    2. Greene DJ
    3. Gratton C
    4. Dosenbach NUF
    5. Petersen SE
    6. Schlaggar BL

    (2019) Evaluating the prediction of brain maturity from functional connectivity after motion artifact denoising

    Cerebral Cortex 29:2455–2469.

    https://doi.org/10.1093/cercor/bhy117

    • PubMed
    • Google Scholar
62. 1. Petersen KJ
    2. Metcalf N
    3. Cooley S
    4. Tomov D
    5. Vaida F
    6. Paul R
    7. Ances BM

    (2021) Accelerated brain aging and cerebral blood flow reduction in persons with human immunodeficiency virus

    Clinical Infectious Diseases 73:1813–1821.

    https://doi.org/10.1093/cid/ciab169

    • PubMed
    • Google Scholar
63. 1. Petersen KJ
    2. Strain JF
    3. Cooley SA
    4. Vaida FF
    5. Ances BM

    (2022) Machine learning quantifies accelerated white-matter aging in persons with HIV

    The Journal of Infectious Diseases 226:49–58.

    https://doi.org/10.1093/infdis/jiac156

    • PubMed
    • Google Scholar
64. 1. Power JD
    2. Barnes KA
    3. Snyder AZ
    4. Schlaggar BL
    5. Petersen SE

    (2012) Spurious but systematic correlations in functional connectivity MRI networks arise from subject motion

    NeuroImage 59:2142–2154.

    https://doi.org/10.1016/j.neuroimage.2011.10.018

    • PubMed
    • Google Scholar
65. 1. Ranasinghe KG
    2. Verma P
    3. Cai C
    4. Xie X
    5. Kudo K
    6. Gao X
    7. Lerner H
    8. Mizuiri D
    9. Strom A
    10. Iaccarino L
    11. La Joie R
    12. Miller BL
    13. Gorno-Tempini ML
    14. Rankin KP
    15. Jagust WJ
    16. Vossel K
    17. Rabinovici GD
    18. Raj A
    19. Nagarajan SS

    (2022) Altered excitatory and inhibitory neuronal subpopulation parameters are distinctly associated with tau and amyloid in Alzheimer’s disease

    eLife 11:e77850.

    https://doi.org/10.7554/eLife.77850

    • PubMed
    • Google Scholar
66. Book

    1. Rasmussen CE
    2. von Luxburg U
    3. Rätsch G

    (2004) Advanced lectures on machine learning

    In: Carbonell JG, Siekmann J, editors. Advanced Lectures on Machine Learning. Berlin, Heidelberg: Springer-Verlag. pp. 63–71.

    https://doi.org/10.1007/b100712

    • Google Scholar
67. Software

    1. R Development Core Team

    (2020) R: A language and environment for statistical computing, version 1.2.1

    R Foundation for Statistical Computing, Vienna, Austria.

    https://www.r-project.org/
68. 1. Richard G
    2. Kolskår K
    3. Sanders A-M
    4. Kaufmann T
    5. Petersen A
    6. Doan NT
    7. Monereo Sánchez J
    8. Alnæs D
    9. Ulrichsen KM
    10. Dørum ES
    11. Andreassen OA
    12. Nordvik JE
    13. Westlye LT

    (2018) Assessing distinct patterns of cognitive aging using tissue-specific brain age prediction based on diffusion tensor imaging and brain morphometry

    PeerJ 6:e5908.

    https://doi.org/10.7717/peerj.5908

    • Google Scholar
69. 1. Satterthwaite TD
    2. Wolf DH
    3. Loughead J
    4. Ruparel K
    5. Elliott MA
    6. Hakonarson H
    7. Gur RC
    8. Gur RE

    (2012) Impact of in-scanner head motion on multiple measures of functional connectivity: relevance for studies of neurodevelopment in youth

    NeuroImage 60:623–632.

    https://doi.org/10.1016/j.neuroimage.2011.12.063

    • PubMed
    • Google Scholar
70. 1. Schindler SE
    2. Gray JD
    3. Gordon BA
    4. Xiong C
    5. Batrla-Utermann R
    6. Quan M
    7. Wahl S
    8. Benzinger TLS
    9. Holtzman DM
    10. Morris JC
    11. Fagan AM

    (2018) Cerebrospinal fluid biomarkers measured by elecsys assays compared to amyloid imaging

    Alzheimer’s & Dementia 14:1460–1469.

    https://doi.org/10.1016/j.jalz.2018.01.013

    • PubMed
    • Google Scholar
71. 1. Schultz AP
    2. Chhatwal JP
    3. Hedden T
    4. Mormino EC
    5. Hanseeuw BJ
    6. Sepulcre J
    7. Huijbers W
    8. LaPoint M
    9. Buckley RF
    10. Johnson KA
    11. Sperling RA

    (2017) Phases of hyperconnectivity and hypoconnectivity in the default mode and salience networks track with amyloid and tau in clinically normal individuals

    The Journal of Neuroscience 37:4323–4331.

    https://doi.org/10.1523/JNEUROSCI.3263-16.2017

    • PubMed
    • Google Scholar
72. 1. Seitzman BA
    2. Gratton C
    3. Marek S
    4. Raut RV
    5. Dosenbach NUF
    6. Schlaggar BL
    7. Petersen SE
    8. Greene DJ

    (2020) A set of functionally-defined brain regions with improved representation of the subcortex and cerebellum

    NeuroImage 206:116290.

    https://doi.org/10.1016/j.neuroimage.2019.116290

    • PubMed
    • Google Scholar
73. 1. Shulman GL
    2. Pope DLW
    3. Astafiev SV
    4. McAvoy MP
    5. Snyder AZ
    6. Corbetta M

    (2010) Right hemisphere dominance during spatial selective attention and target detection occurs outside the dorsal frontoparietal network

    J Neurosci 30:3640–3651.

    https://doi.org/10.1523/JNEUROSCI.4085-09.2010

    • Google Scholar
74. 1. Smith SM
    2. Vidaurre D
    3. Alfaro-Almagro F
    4. Nichols TE
    5. Miller KL

    (2019) Estimation of brain age delta from brain imaging

    NeuroImage 200:528–539.

    https://doi.org/10.1016/j.neuroimage.2019.06.017

    • PubMed
    • Google Scholar
75. 1. Sperling RA
    2. Aisen PS
    3. Beckett LA
    4. Bennett DA
    5. Craft S
    6. Fagan AM

    (2011) Toward defining the preclinical stages of alzheimer’s disease: recommendations from the national institute on aging and the alzheimer’s association workgroup

    Alzheimers Dement 7:280–292.

    https://doi.org/10.1016/j.jalz.2011.03.003

    • Google Scholar
76. 1. Su Y
    2. D’Angelo GM
    3. Vlassenko AG
    4. Zhou G
    5. Snyder AZ
    6. Marcus DS
    7. Blazey TM
    8. Christensen JJ
    9. Vora S
    10. Morris JC
    11. Mintun MA
    12. Benzinger TLS

    (2013) Quantitative analysis of PIB-PET with freesurfer rois

    PLOS ONE 8:e73377.

    https://doi.org/10.1371/journal.pone.0073377

    • PubMed
    • Google Scholar
77. 1. Su Y
    2. Flores S
    3. Hornbeck RC
    4. Speidel B
    5. Vlassenko AG
    6. Gordon BA
    7. Koeppe RA
    8. Klunk WE
    9. Xiong C
    10. Morris JC
    11. Benzinger TLS

    (2018) Utilizing the centiloid scale in cross-sectional and longitudinal PIB PET studies

    NeuroImage. Clinical 19:406–416.

    https://doi.org/10.1016/j.nicl.2018.04.022

    • PubMed
    • Google Scholar
78. 1. Su Y
    2. Flores S
    3. Wang G
    4. Hornbeck RC
    5. Speidel B
    6. Joseph-Mathurin N
    7. Vlassenko AG
    8. Gordon BA
    9. Koeppe RA
    10. Klunk WE
    11. Jack CR
    12. Farlow MR
    13. Salloway S
    14. Snider BJ
    15. Berman SB
    16. Roberson ED
    17. Brosch J
    18. Jimenez-Velazques I
    19. van Dyck CH
    20. Galasko D
    21. Yuan SH
    22. Jayadev S
    23. Honig LS
    24. Gauthier S
    25. Hsiung GYR
    26. Masellis M
    27. Brooks WS
    28. Fulham M
    29. Clarnette R
    30. Masters CL
    31. Wallon D
    32. Hannequin D
    33. Dubois B
    34. Pariente J
    35. Sanchez-Valle R
    36. Mummery C
    37. Ringman JM
    38. Bottlaender M
    39. Klein G
    40. Milosavljevic-Ristic S
    41. McDade E
    42. Xiong C
    43. Morris JC
    44. Bateman RJ
    45. Benzinger TLS

    (2019) Comparison of pittsburgh compound B and florbetapir in cross-sectional and longitudinal studies

    Alzheimer’s & Dementia 11:180–190.

    https://doi.org/10.1016/j.dadm.2018.12.008

    • PubMed
    • Google Scholar
79. 1. Thomas JB
    2. Brier MR
    3. Snyder AZ
    4. Vaida FF
    5. Ances BM

    (2013) Pathways to neurodegeneration: effects of HIV and aging on resting-state functional connectivity

    Neurology 80:1186–1193.

    https://doi.org/10.1212/WNL.0b013e318288792b

    • PubMed
    • Google Scholar
80. 1. Van Dijk KRA
    2. Sabuncu MR
    3. Buckner RL

    (2012) The influence of head motion on intrinsic functional connectivity MRI

    NeuroImage 59:431–438.

    https://doi.org/10.1016/j.neuroimage.2011.07.044

    • PubMed
    • Google Scholar
81. Preprint

    1. Vidal-Piñeiro D
    2. Wang Y
    3. Krogsrud SK
    4. Amlien IK
    5. Baaré WFC
    6. Bartrés-Faz D
    7. Bertram L
    8. Brandmaier AM
    9. Drevon CA
    10. Düzel S
    11. Ebmeier KP
    12. Henson RN
    13. Junque C
    14. Kievit RA
    15. Kühn S
    16. Leonardsen E
    17. Lindenberger U
    18. Madsen KS
    19. Magnussen F
    20. Mowinckel AM
    21. Nyberg L
    22. Roe JM
    23. Segura B
    24. Smith SM
    25. Sørensen Ø
    26. Suri S
    27. Westerhausen R
    28. Zalesky A
    29. Zsoldos E
    30. Walhovd KB
    31. Fjell AM
    32. the Australian Imaging Biomarkers and Lifestyle flagship study of ageing

    (2021) Individual Variations in “Brain Age” Relate to Early Life Factors More than to Longitudinal Brain Change

    bioRxiv.

    https://doi.org/10.1101/2021.02.08.428915

    • Google Scholar
82. 1. Vlassenko AG
    2. McCue L
    3. Jasielec MS
    4. Su Y
    5. Gordon BA
    6. Xiong C
    7. Holtzman DM
    8. Benzinger TLS
    9. Morris JC
    10. Fagan AM

    (2016) Imaging and cerebrospinal fluid biomarkers in early preclinical Alzheimer disease

    Annals of Neurology 80:379–387.

    https://doi.org/10.1002/ana.24719

    • PubMed
    • Google Scholar
83. 1. Volluz KE
    2. Schindler SE
    3. Henson RL
    4. Xiong C
    5. Gordon BA
    6. Benzinger TLS
    7. Holtzman DM
    8. Morris JC
    9. Fagan AM

    (2021) Correspondence of CSF biomarkers measured by lumipulse assays with amyloid PET

    Alzheimer’s & Dementia 17:S5.

    https://doi.org/10.1002/alz.051085

    • Google Scholar
84. 1. Wales RM
    2. Leung HC

    (2021) The effects of amyloid and tau on functional network connectivity in older populations

    Brain Connectivity 11:599–612.

    https://doi.org/10.1089/brain.2020.0902

    • PubMed
    • Google Scholar
85. 1. Wang J
    2. Knol MJ
    3. Tiulpin A
    4. Dubost F
    5. de Bruijne M
    6. Vernooij MW
    7. Adams HHH
    8. Ikram MA
    9. Niessen WJ
    10. Roshchupkin GV

    (2019) Gray matter age prediction as a biomarker for risk of dementia

    PNAS 116:21213–21218.

    https://doi.org/10.1073/pnas.1902376116

    • PubMed
    • Google Scholar
86. 1. Wong DF
    2. Rosenberg PB
    3. Zhou Y
    4. Kumar A
    5. Raymont V
    6. Ravert HT
    7. Dannals RF
    8. Nandi A
    9. Brasić JR
    10. Ye W
    11. Hilton J
    12. Lyketsos C
    13. Kung HF
    14. Joshi AD
    15. Skovronsky DM
    16. Pontecorvo MJ

    (2010) In vivo imaging of amyloid deposition in Alzheimer disease using the radioligand 18F-AV-45 (florbetapir [ corrected ] F 18)

    Journal of Nuclear Medicine 51:913–920.

    https://doi.org/10.2967/jnumed.109.069088

    • PubMed
    • Google Scholar
87. 1. Yu M
    2. Linn KA
    3. Cook PA
    4. Phillips ML
    5. McInnis M
    6. Fava M
    7. Trivedi MH
    8. Weissman MM
    9. Shinohara RT
    10. Sheline YI

    (2018) Statistical harmonization corrects site effects in functional connectivity measurements from multi-site fMRI data

    Human Brain Mapping 39:4213–4227.

    https://doi.org/10.1002/hbm.24241

    • PubMed
    • Google Scholar

Decision letter after peer review:

Thank you for submitting your article "Multimodal brain age estimates relate to Alzheimer disease biomarkers and cognition in early stages: a cross-sectional observational study" for consideration by eLife. Your article has been reviewed by 3 peer reviewers, and the evaluation has been overseen by a Reviewing Editor and Jeannie Chin as the Senior Editor. The following individuals involved in the review of your submission have agreed to reveal their identity: James Cole (Reviewer #1); Didac Vidal-Pineiro (Reviewer #3).

The reviewers have discussed their reviews with one another, and the Reviewing Editor has drafted this to help you prepare a revised submission.

Essential revisions:

The overall consensus from the reviewers is that some of the hypotheses (and conclusions) are supported by the results (specifically, the Vol-BAG model) while others are much weaker (specifically, the FC-BAG models). In consultation between the reviewers, they agreed that the work is "useful" but found the evidence to be "incomplete" for the conclusions as presented.

1. The functional connectivity model provides a poor fit to the data. Given that the FC-based models have been recently published (Millar 2022), the reviewers feel that the authors should temper claims about the importance of the FC-based modelling.

2. The reviewers are skeptical about claims regarding the improvements afforded by multi-modal brain age models. In particular, the bootstrapping analyses actually support the claims that FC data improve the quality of brain age modelling.

3. Overall, the reviewers feel that some of the conclusions, such as the biphasic relationships between functional brain-age models and pathological status, are not strongly supported and need to be tempered. In particular, the reviewers object to referring to results as "marginal".

4. Discussion about the potential implications of sample size would be welcome.

Reviewer #1 (Recommendations for the authors):

– In the Methods, they say they used a Gaussian mixture model to define pTau positivity. There are multiple ways to implement GMMs, so more details should be included here.

– The presentation of the MRI Acquisition section in the Methods is not very clear. I suggest the authors consider an alternative format, possibly a supplementary table, where the acquisition details can be more easily appraised. Currently, the acquisition details on the DIAN participants are scarce relative to the ADRC participants.

– Can the authors explain and justify why the fMRI processing included registration to an older-adult template? Could this have caused a bias in the registration accuracy for younger participants?

– It is unclear to me why they chose to perform 10-fold CV and hold-out validation with 1000 bootstraps. To my mind, the latter would have been sufficient. If the authors think including the initial 10-fold CV as well is important, this should be clearly justified.

– It is important that R² is reported for each model performance, not just MAE. As R² is a ratio the values can readily be compared across published studies, while the MAE cannot as it is heavily dependent on the age distribution of the test set. For completeness, they could also consider reporting the Pearson's r correlation between predicted age and age, and the root mean square error as well.

– It is unclear how the model performance comparisons were conducted (Results, pg. 12). While t-tests are mentioned in the text, the exact details should be included in the Methods. My concern here is that the n (sample size) for these comparisons is based on the number of bootstraps (arbitrarily determined by the authors to be 1000), rather than the actual sample size. If that is the case (and Figure 1D suggests it is), this is procedure is incorrect as the sensitivity that these tests have to detect differences would be purely a factor of the number of bootstraps, rather than the number of observations. This means that the experimenter can simply choose to make smaller differences 'significant' simply by adding more bootstraps. This needs to be clarified and corrected if appropriate. One approach to achieve the goal of comparing model performances is to take Pearson's correlations with age from each model and use Z-transformations to test the alternative hypothesis that the correlations are different (e.g., the Steiger test). In that way, the n would be determined by the number of observations, so statistical power would appropriately reflect the data.

– I recommend avoiding saying things like 'marginally lower' when a p-value = 0.110. There's no real evidence that there's a difference here, so hard to say whether it's truly lower or not. Generally avoiding 'trends' at 0.1> p >0.05 is best practice. P-values are important, but effect sizes (with confidence intervals) are often more informative.

– In the Discussion, when comparing age prediction accuracy between studies, it's important not to rely on MAE alone as this can vary greatly as a function of the test set age distribution. They should use R² instead. Where R² is unavailable, it's essential that the age range of each study mentioned in comparison is reported to provide context to the MAE values.

– The evidence for a biphasic relationship between FC-BAG and pre-clinical/clinical status is somewhat over-interpreted, particularly given there was no difference between A+T- and A+T+ people (p=0.11) and the fit of FC brain age is quite poor (i.e., far from the line of identity in Figure 2A). I suggest more caution when discussing this.

– A key limitation that was not mentioned was the small sample size relative to other studies. Perhaps the model performance is similar but given that only MAE is used to compare studies it is hard to draw meaningful conclusions. My impression is that had larger datasets been available, then performance would have improved.

Reviewer #2 (Recommendations for the authors):

– As explained in the previous section, the FC-BAG model has very limited prediction power, and therefore the results from the FC-BAG model are not reliable while providing marginal benefit. The FC-BAG results should be moved to the supplementary materials.

– For the FC-BAG models and its relation to other clinical variables, please also another version of the model including mean, median, and maximum head motion during the entire rsfMRI scan as covariates in the model to further ensure the reliability of the results.

– It is not clear to me that the bootstrapped based t-test provides evidence in favor of the Vol+FC-BAG model. In other words, a stacked model combining FC-BAG and Vol-BAG will always perform as well or worse than each model. If the stacking approach takes this into account (not clear in the method section, needs further explanation) the marginal increase in performance can be explained to this unidirectional effect and needs further confirmation based on a model selection step (e.g. using new independent data not used in the training-validation of FC-BAG and Vol-BAG model to compare Vol+FC-BAG and Vol-BAG model).

– After the previous step authors can choose the best performing model (either Vol-BAG or Vol+FC-BAG model) and only present the data for the selected model since results between the two models are redundant and don't add extra information to the reader.

– The analysis of hippocampal volume (specially related to the preclinical AD) needs to be confirmed. To do so, hippocampal volume as well as volumetric features from regions highly correlated with hippocampal volume should be removed from the feature set of Vol-BAG and Vol+FC-BAG models. The models need to be retrained using the same procedure. The relationship between hippocampal volume and the newly calculated Vol-BAG and Vol+FC-BAG values should be reported alongside the current results.

Reviewer #3 (Recommendations for the authors):

Find below some recommendations on how (I think) the science in this manuscript might be improved in no particular order.

1. Training sample. It is unclear why one would like to minimize undetected AD pathology (amyloid positivity, that is) in the cognitively healthy training sample as many of these individuals (when Tau negative) have minimal changes in brain structure and function. Since you create a BA "norm" from these individuals, one may benefit from including a bigger, more representative sample using more lenient inclusion criteria. Decisions regarding the training sample can have a big impact on the subsequent interpretation of BA results (e.g. Hwang, 2022, Brain Comm).

2. Group descriptors. It is still a matter of ongoing debate, but I recommend using another descriptor for the amyloid positive group rather than "preclinical AD". Even in the NIAA-AA Research framework from 2018 (Jack Jr.) they only use this tag for individuals that are amyloid and tau positive.

3. Biomarker definition. I am not an expert on biomarkers, but the definition of pTau positivity is uncommon to me "Gaussian mixture model approach to defining pTau positivity based on the CSF pTau/Aβ40 ratio.". Could the authors justify and or cite the correspondent references?

4. Statistical analysis. If I have not misread, the methods section only mentions three test groups (A-, A+, and CDR>0) but the analysis is performed with four groups. This leads to confusion and should be corrected. Also, most higher-level analyses reported in the results are not described in this section. These analyses should be described in the methods section. It is difficult to evaluate whether the performed analyses are appropriate without this description. For example, (lines 323-7) the authors report three different regression models and then a fourth analysis combining the four groups, but only for FC-BAG. This procedure is unclear, not described (as far as I can see), and not justified. Another example is the analysis with NFL which is not mentioned until line 412 (p.20) in the Results section. Also, the authors use different samples for different tests, due to the lack of Biomarker information for some individuals. I suggest adding degrees of freedom/n when reporting the results, so the reader has some information regarding the sample used.

5. The authors are repeating the same analysis in three different modalities (also sometimes they repeat the analyses across several pairs of groups [e.g. lines 323-7]). Thus, I would strongly recommend using some type of multiple comparison corrections.

6. Table 2. The authors should mention what the units in the table represent. Also, I recommend adding df and exact significance values (at least if p >.001).

7. Atlas. The authors used the D-K atlas (not strictly the FS-defined) for BA computation. This is a suboptimal choice, and I would recommend in the future using more fine-grained parcellations. This is not a strong issue, but the choice surprised me since the authors used a 300-ROI parcellation for the rs-fMRI. Also, since the authors use cortical thickness for sampling the cortex, I would not use "Volumetric"-BA as a descriptor.

8. Movement and rs-fMRI. The rs-fMRI preprocessing used might still lead to a signal that is related to movement. Since movement is almost always related to age and disease [and thus can affect both the BA computation and the tests in the test sample], I would suggest taking additional steps in this regard. At the minimum, I would include total motion as an additional covariate in the higher-level analysis and discuss this issue in the limitations section.

9. The results in cognitively healthy samples are largely negative (i.e. do not differ with groups). One possible explanation is that the authors are using cross-sectional samples and thus – even when using BA metrics – have a signal that captures ongoing aging (accelerated aging, if you wish) and baseline (lifelong, preexisting) variability between individuals. The latter may obscure possible existing effects. I recommend the authors acknowledge the limitations of using cross-sectional data to study changes that ought to be longitudinal.

Essential revisions:

The overall consensus from the reviewers is that some of the hypotheses (and conclusions) are supported by the results (specifically, the Vol-BAG model) while others are much weaker (specifically, the FC-BAG models). In consultation between the reviewers, they agreed that the work is "useful" but found the evidence to be "incomplete" for the conclusions as presented.

1. The functional connectivity model provides a poor fit to the data. Given that the FC-based models have been recently published (Millar 2022), the reviewers feel that the authors should temper claims about the importance of the FC-based modelling.

Although the reviewers are correct that the FC model indeed provided a relatively poor fit, compared to structural MRI data, a major goal of this project was to test whether each modality (structural MRI and FC) captures unique patterns related to AD progression. As we are primarily motivated to evaluate these models in their associations with AD, it is important to consider that the most accurate BAG models for age prediction are not necessarily the ones that are most sensitive to disease. Indeed, at least one study suggests that models with “moderate” age prediction accuracy might be the most useful in detecting deviation related to disease, as compared to overly “loose” or “tight” age prediction models (Bashyam et al., 2020). We now justify our motivations more clearly in the “Introduction”:

“This project aimed to develop multimodal models of brain-predicted age, incorporating both FC and structural MRI. Participants with presymptomatic AD pathology were excluded from the training set to maximize sensitivity. We hypothesized that BAG estimates would be sensitive to the presence of AD biomarkers and early cognitive impairment. We further considered whether estimates were continuously associated with AD biomarkers of amyloid and tau, as well as cognition. We hypothesized that FC and structural MRI would capture complementary signals related to age and AD. Thus, we systematically compared models trained on unimodal FC, structural MRI, and combined modalities, to test the added utility of multimodal integration in accurately predicting age and whether each modality captures unique relationships with AD biomarkers and cognition.”

Moreover, in the current revision, we aim to focus the discussion on novel associations with this biphasic FC pattern (including the tests of continuous associations with biomarkers and cognition), rather than recapitulating the previously published finding. We also discuss the potential relevance of this result to emerging results from MEG (Ranasinghe et al., 2022) and metabolic PET studies (Goyal et al., 2022). Finally, we now also acknowledge the poor prediction performance of the FC model as a potential spurious explanation of these findings. The discussion of this result now tempers prior claims about the importance of FC:

“As we have previously reported (31), FC-BAG was lower in presymptomatic AD participants compared to amyloid-negative controls. Extending beyond this group difference, we now also note that FC-BAG was negatively associated with amyloid PET in CN/A+ participants. The combined reduction of FC-BAG in the presymptomatic phase and increase in the symptomatic phase suggest a biphasic functional response to AD progression, which is partially consistent with some prior suggestions (77–81) (see ref 31 for a more detailed discussion).

Interpretation of this biphasic pattern is still unclear, although the present results provide at least one novel insight. Specifically, one potential interpretation is that the “younger” appearing FC pattern in the preclinical phase may reflect a compensatory response to early AD pathology (82). This interpretation leads to the prediction that reduced FC-BAG should be associated with better cognitive performance in the preclinical stage. However, this interpretation is not supported by the current results, as FC-BAG did not correlate with cognition in any of the analysis samples.

Alternatively, pathological AD-related FC disruptions may be orthogonal to healthy age-related FC differences, as supported by our previous observation that age and AD are predicted by mostly non-overlapping FC networks (31). For instance, the “younger” FC pattern in CN/A+ participants may be driven by hyper-excitability in the preclinical stage (83,84). It is also worth considering that patterns of younger FC-BAG in CN/A+ participants may somehow correspond to a recent observation that patterns of youthful-appearing aerobic glycolysis are relatively preserved in the preclinical stage of AD (85). Finally, this effect may simply be spuriously driven by poor performance of the FC brain age model, sample-specific noise, and/or statistical artifacts related to regression dilution and its correction (71). Hence, future studies should attempt to replicate these results in independent samples and further test potential theoretical interpretations.”

2. The reviewers are skeptical about claims regarding the improvements afforded by multi-modal brain age models. In particular, the bootstrapping analyses actually support the claims that FC data improve the quality of brain age modelling.

We thank the reviewers for pointing out this flaw in the comparison of model performance. We now test for significant differences between z-transformed Pearson correlations with age in each model using a Williams’s test (as these correlations are dependent in that they share a common variable, age, as opposed to the Steiger test of correlations between different variables). We now report these test results in the

“Comparison of Model Performance” section:

“All models accurately predicted chronological age in the training sets, as assessed using 10-fold cross validation, as well as in the held-out test sets. Overall, prediction accuracy was lowest in the FC model (MAEFC/Train = 8.67 years, R2FC/Train = 0.68, MAEFC/Test = 8.25 years, R2FC/Test = 0.73, see Figure 1A and B). The structural MRI model (MAES/Train = 5.97 years, R2S/Train = 0.81, MAES/Test = 6.26 years, R2S/Test = 0.82, see Figure 1C and D) significantly outperformed the FC model in age prediction accuracy, Williams’s tS vs. FC = 5.39, p <.001. Finally, the multimodal model (MAES+FC/Train = 5.34 years, R2S+FC/Train = 0.86, MAES+FC/Test = 5.25 years, R2S+FC/Test = 0.87, see Figure 1E and F) significantly outperformed both the FC model (Williams’s tS+FC vs. FC = 11.20, p <.001) and the structural MRI model (Williams’s tS+FC vs. S = 5.67, p <.001).”

3. Overall, the reviewers feel that some of the conclusions, such as the biphasic relationships between functional brain-age models and pathological status, are not strongly supported and need to be tempered. In particular, the reviewers object to referring to results as "marginal".

We appreciate the reviewers’ concern over the weak support for some of the results, particularly in the biphasic relationship observed in the multimodal BAG model. In the revised analyses, which focus on a three group comparison (CN/A- vs. CN/A+ vs. CI), the biphasic pattern in the FC-BAG model is clearly reproduced and survives FDR correction for multiple comparisons. However, the previously noted “marginal” biphasic pattern in the S+FC-BAG model is no longer apparent. Thus, we limit our discussion of the biphasic pattern to the FC model, and not the multimodal model. Moreover, we no longer refer to results as “marginal” throughout the revised submission.

4. Discussion about the potential implications of sample size would be welcome.

We agree with the reviewers that the sample size of the training set was relatively small compared to prior models. We now acknowledge this issue as a limitation and an avenue for future development:

“Additionally, the training set (N = 390) was relatively small compared to prior models, which have included training samples over 1000 (e.g., 5,76). Future studies may further improve model performance by including larger samples of well-characterized participants in the training set.”

Reviewer #1 (Recommendations for the authors):

– In the Methods, they say they used a Gaussian mixture model to define pTau positivity. There are multiple ways to implement GMMs, so more details should be included here.

We apologize for the lack of clarity in the GMM methods, as multiple reviewers also noted similar concerns. Specifically, we fit a two-component GMM to the continuous pTau data, and then used the model classification to define pTau- and pTau+ participants. However, in order to simplify the analyses and interpretation of results, we have removed the analyses stratifying by pTau positivity and instead focus only on A- vs. A+ participants (see responses below to reviewer #3, comments #3 and 4).

– The presentation of the MRI Acquisition section in the Methods is not very clear. I suggest the authors consider an alternative format, possibly a supplementary table, where the acquisition details can be more easily appraised. Currently, the acquisition details on the DIAN participants are scarce relative to the ADRC participants.

We apologize for the lack of clarity. In the revision, we now provide more specific details on the acquisition parameters for DIAN participants in the main text (“MRI Acquisition” section) and also provide a summary table of the parameters in the Supplementary Material.

“All MRI data were obtained using a Siemens 3T scanner, although there was a variety of specific models within and across studies. As described previously (Millar et al., 2022), participants in the Knight ADRC and Ances lab studies completed one of two comparable structural MRI protocols, varying by scanner (sagittal T1-weighted magnetization-prepared rapid gradient echo sequence [MPRAGE] with repetition time [TR] = 2400 or 2300 ms, echo time [TE] = 3.16 or 2.95 ms, flip angle = 8° or 9°, frames = 176, field of view = sagittal 256x256 or 240x256 mm, 1-mm isotropic or 1x1x1.2 mm voxels; oblique T2-weighted fast spin echo sequence [FSE] with TR = 3200 ms, TE = 455 ms, 256 x 256 acquisition matrix, 1-mm isotropic voxels) and an identical resting-state fMRI protocol (interleaved whole-brain echo planar imaging sequence [EPI] with TR = 2200 ms, TE = 27 ms, flip angle = 90°, field of view = 256 mm, 4-mm isotropic voxels for two 6-minute runs [164 volumes each] of eyes open fixation). DIAN participants completed a similar MPRAGE protocol (TR = 2300 ms, TE = 2.95 ms, flip angle = 9°, field of view = 270 mm, 1.1x1.1x1.2 mm voxels)(McKay et al., 2022). Resting-state EPI sequence parameters for the DIAN participants differed across sites and scanners with the most notable difference being shorter resting-state runs (one 5-minute run of 120 volumes; see Supplementary File 1 for summary of structural and functional MRI parameters) (McKay et al., 2022).”

– Can the authors explain and justify why the fMRI processing included registration to an older-adult template? Could this have caused a bias in the registration accuracy for younger participants?

We apologize for the lack of clarity. In fact, we used two separate templates (one for younger adults and one for older adults). All participants were registered to the age-appropriate template. We now specify this procedure more clearly in “FC Preprocessing and Features”:

“Transformation to an age-appropriate in-house atlas template (based on independent samples of either younger adults or CN older adults) was performed using a composition of affine transforms connecting the functional volumes with the T2-weighted and MPRAGE images.”

– It is unclear to me why they chose to perform 10-fold CV and hold-out validation with 1000 bootstraps. To my mind, the latter would have been sufficient. If the authors think including the initial 10-fold CV as well is important, this should be clearly justified.

We agree with the reviewer that the 10-fold CV and bootstrapped hold-out validation are somewhat redundant. The hold-out validation step was initially performed to facilitate comparison across models. However, several reviewers have critiqued this approach. We have now removed the bootstrapping approach and instead focus on cross validation in the training set, as well as a non-bootstrapped validation in the testing set. We now specify this approach in the “Gaussian Process Regression (GPR)” section:

“Model performance in the training set was assessed using 10-fold cross validation via the Pearson correlation coefficient (r), the proportion of variance explained (R2), the mean absolute error (MAE), and root-mean-square error (RMSE) between true chronological age and the cross-validated age predictions merged across the 10 folds. We then evaluated generalizability of the models to predict age in unseen data by applying the trained models to the held-out test set of healthy controls.”

– It is important that R² is reported for each model performance, not just MAE. As R² is a ratio the values can readily be compared across published studies, while the MAE cannot as it is heavily dependent on the age distribution of the test set. For completeness, they could also consider reporting the Pearson's r correlation between predicted age and age, and the root mean square error as well.

We agree with the reviewer that R² (as well as Pearson’s r and RMSE) are important metrics of model performance, especially for comparison with other studies. We now report these measures in Figure 1, as well as in the “Comparison of Model Performance”:

“All models accurately predicted chronological age in the training sets, as assessed using 10-fold cross validation, as well as in the held-out test sets. Overall, prediction accuracy was lowest in the FC model (MAEFC/Train = 8.67 years, R2FC/Train = 0.68, MAEFC/Test = 8.25 years, R2FC/Test = 0.73, see Figure 1A and B). The structural MRI model (MAES/Train = 5.97 years, R2S/Train = 0.81, MAES/Test = 6.26 years, R2S/Test = 0.82, see Figure 1C and D) significantly outperformed the FC model in age prediction accuracy, Williams’s tS vs. FC = 5.39, p <.001. Finally, the multimodal model (MAES+FC/Train = 5.34 years, R2S+FC/Train = 0.86, MAES+FC/Test = 5.25 years, R2S+FC/Test = 0.87, see Figure 1E and F) significantly outperformed both the FC model (Williams’s tS+FC vs. FC = 11.20, p <.001) and the structural MRI model (Williams’s tS+FC vs. S = 5.67, p <.001).”

– It is unclear how the model performance comparisons were conducted (Results, pg. 12). While t-tests are mentioned in the text, the exact details should be included in the Methods. My concern here is that the n (sample size) for these comparisons is based on the number of bootstraps (arbitrarily determined by the authors to be 1000), rather than the actual sample size. If that is the case (and Figure 1D suggests it is), this is procedure is incorrect as the sensitivity that these tests have to detect differences would be purely a factor of the number of bootstraps, rather than the number of observations. This means that the experimenter can simply choose to make smaller differences 'significant' simply by adding more bootstraps. This needs to be clarified and corrected if appropriate. One approach to achieve the goal of comparing model performances is to take Pearson's correlations with age from each model and use Z-transformations to test the alternative hypothesis that the correlations are different (e.g., the Steiger test). In that way, the n would be determined by the number of observations, so statistical power would appropriately reflect the data.

We thank the reviewer for pointing out this flaw in the comparison of model performance. We now test for significant differences between z-transformed Pearson correlations with age in each model using a Williams’s test (as these correlations are dependent in that they share a common variable, age, as opposed to the Steiger test of correlations between different variables). We now report these test results in the “Comparison of Model Performance” section:

“All models accurately predicted chronological age in the training sets, as assessed using 10-fold cross validation, as well as in the held-out test sets. Overall, prediction accuracy was lowest in the FC model (MAEFC/Train = 8.67 years, R2FC/Train = 0.68, MAEFC/Test = 8.25 years, R2FC/Test = 0.73, see Figure 1A and B). The structural MRI model (MAES/Train = 5.97 years, R2S/Train = 0.81, MAES/Test = 6.26 years, R2S/Test = 0.82, see Figure 1C and D) significantly outperformed the FC model in age prediction accuracy, Williams’s tS vs. FC = 5.39, p <.001. Finally, the multimodal model (MAES+FC/Train = 5.34 years, R2S+FC/Train = 0.86, MAES+FC/Test = 5.25 years, R2S+FC/Test = 0.87, see Figure 1E and F) significantly outperformed both the FC model (Williams’s tS+FC vs. FC = 11.20, p <.001) and the structural MRI model (Williams’s tS+FC vs. S = 5.67, p <.001).”

– I recommend avoiding saying things like 'marginally lower' when a p-value = 0.110. There's no real evidence that there's a difference here, so hard to say whether it's truly lower or not. Generally avoiding 'trends' at 0.1> p >0.05 is best practice. P-values are important, but effect sizes (with confidence intervals) are often more informative.

We appreciate the reviewer’s concern with over-interpretation of non-significant relationships. We now avoid using the terms “marginal” and “trend” throughout the manuscript. We also report effect sizes (partial η²) for all regression-based analyses.

– In the Discussion, when comparing age prediction accuracy between studies, it's important not to rely on MAE alone as this can vary greatly as a function of the test set age distribution. They should use R² instead. Where R² is unavailable, it's essential that the age range of each study mentioned in comparison is reported to provide context to the MAE values.

We thank the reviewer for pointing out this flaw. We now discuss our model performance in comparison to prior models using R², instead of MAE, in “Predicting Brain Age with Multiple Modalities”:

“We found that a GPR model trained on structural MRI features predicted chronological age in a cognitively normal, amyloid-negative adult sample with an R2 of 0.81. This level of performance is comparable to other structural models, which have reported R2s ranging from 0.80 to 0.95 (Bashyam et al., 2020; Cole and Franke, 2017; Eavani et al., 2018; Gong et al., 2021; Lee et al., 2022; Liem et al., 2017; Ly et al., 2020; Wang et al., 2019). As previously reported (Millar et al., 2022), the FC-trained model predicted age with an R2 of 0.68, again consistent with previous FC models, which have achieved R2s from 0.53 to 0.80 (Eavani et al., 2018; Gonneaud et al., 2021; Liem et al., 2017). Our observation that structural MRI outperformed FC in age prediction is also consistent with previous direct comparisons between modalities (Dunås et al., 2021; Eavani et al., 2018; Liem et al., 2017).”

– The evidence for a biphasic relationship between FC-BAG and pre-clinical/clinical status is somewhat over-interpreted, particularly given there was no difference between A+T- and A+T+ people (p=0.11) and the fit of FC brain age is quite poor (i.e., far from the line of identity in Figure 2A). I suggest more caution when discussing this.

In the revised analyses, which focus on a three group comparison (CN/A- vs. CN/A+ vs. CI), the biphasic pattern in the FC-BAG model is clearly reproduced and survives FDR correction for multiple comparisons. However, the previously noted “marginal” biphasic pattern in the S+FC-BAG model is no longer apparent. Thus, we limit our discussion of the biphasic pattern to the FC model, and not the multimodal model. Moreover, we aim to focus the discussion on novel associations with this biphasic FC pattern (including the tests of continuous associations with biomarkers and cognition), rather than recapitulating the previously published finding. We also discuss the potential relevance of this result to emerging results from MEG (Ranasinghe et al., 2022) and metabolic PET studies (Goyal et al., 2022). Finally, we now also acknowledge the poor prediction performance of the FC model as a potential spurious explanation of these findings. The discussion of this result now reads as follows:

“As we have previously reported (31), FC-BAG was lower in presymptomatic AD participants compared to amyloid-negative controls. Extending beyond this group difference, we now also note that FC-BAG was negatively associated with amyloid PET in CN/A+ participants. The combined reduction of FC-BAG in the presymptomatic phase and increase in the symptomatic phase suggest a biphasic functional response to AD progression, which is partially consistent with some prior suggestions (77–81) (see ref 31 for a more detailed discussion).

Interpretation of this biphasic pattern is still unclear, although the present results provide at least one novel insight. Specifically, one potential interpretation is that the “younger” appearing FC pattern in the preclinical phase may reflect a compensatory response to early AD pathology (82). This interpretation leads to the prediction that reduced FC-BAG should be associated with better cognitive performance in the preclinical stage. However, this interpretation is not supported by the current results, as FC-BAG did not correlate with cognition in any of the analysis samples.

Alternatively, pathological AD-related FC disruptions may be orthogonal to healthy age-related FC differences, as supported by our previous observation that age and AD are predicted by mostly non-overlapping FC networks (31). For instance, the “younger” FC pattern in CN/A+ participants may be driven by hyper-excitability in the preclinical stage (83,84). It is also worth considering that patterns of younger FC-BAG in CN/A+ participants may somehow correspond to a recent observation that patterns of youthful-appearing aerobic glycolysis are relatively preserved in the preclinical stage of AD (85). Finally, this effect may simply be spuriously driven by poor performance of the FC brain age model, sample-specific noise, and/or statistical artifacts related to regression dilution and its correction (71). Hence, future studies should attempt to replicate these results in independent samples and further test potential theoretical interpretations.”

– A key limitation that was not mentioned was the small sample size relative to other studies. Perhaps the model performance is similar but given that only MAE is used to compare studies it is hard to draw meaningful conclusions. My impression is that had larger datasets been available, then performance would have improved.

We agree with the reviewer that the sample size of the training set was relatively small compared to prior models. We now acknowledge this issue as a limitation and an avenue for future development:

“Additionally, the training set (N = 390) was relatively small compared to prior models, which have included training samples over 1000 (e.g., 5,76). Future studies may further improve model performance by including larger samples of well-characterized participants in the training set.”

Reviewer #2 (Recommendations for the authors):

– As explained in the previous section, the FC-BAG model has very limited prediction power, and therefore the results from the FC-BAG model are not reliable while providing marginal benefit. The FC-BAG results should be moved to the supplementary materials.

Although FC performed relatively poorly in predicting age, a major goal of this project was to test whether each modality (structural MRI and FC) captures unique patterns related to AD progression. In fact, the FC model indeed captures a unique pattern in that it is reduced in CN/A+ participants, but increased in CI participants, which stands in contrast to patterns observed in the S-BAG model. We view this as an important observation, which belongs in the main text, rather than a supplementary analysis. We now justify our motivations more clearly in the “Introduction”:

“This project aimed to develop multimodal models of brain-predicted age, incorporating both FC and structural MRI. Participants with presymptomatic AD pathology were excluded from the training set to maximize sensitivity. We hypothesized that BAG estimates would be sensitive to the presence of AD biomarkers and early cognitive impairment. We further considered whether estimates were continuously associated with AD biomarkers of amyloid and tau, as well as cognition. We hypothesized that FC and structural MRI would capture complementary signals related to age and AD. Thus, we systematically compared models trained on unimodal FC, structural MRI, and combined modalities, to test the added utility of multimodal integration in accurately predicting age and whether each modality captures unique relationships with AD biomarkers and cognition.”

– For the FC-BAG models and its relation to other clinical variables, please also another version of the model including mean, median, and maximum head motion during the entire rsfMRI scan as covariates in the model to further ensure the reliability of the results.

We agree with the reviewer (as well as Reviewer #3) that appropriate consideration and control for head motion artifact is a critical element in analysis of FC data. Hence, we now include mean framewise displacement (FD) as an additional covariate in all statistical analyses involving the FC and multimodal (S+FC) BAG estimates. We do not include median and maximum, as suggested by the reviewer, in order to minimize potential multi-collinearity in our regression models. As noted in “Statistical Analysis”:

“Given the potential confounding influence of head motion on FC-derived measures (60,76,77), we also included mean FD as an additional covariate of non-interest in the FC and S+FC models.”

– It is not clear to me that the bootstrapped based t-test provides evidence in favor of the Vol+FC-BAG model. In other words, a stacked model combining FC-BAG and Vol-BAG will always perform as well or worse than each model. If the stacking approach takes this into account (not clear in the method section, needs further explanation) the marginal increase in performance can be explained to this unidirectional effect and needs further confirmation based on a model selection step (e.g. using new independent data not used in the training-validation of FC-BAG and Vol-BAG model to compare Vol+FC-BAG and Vol-BAG model).

We appreciate the reviewer’s concern and agree that it is important to demonstrate that increases in model performance are meaningful, rather than driven by unidirectional effects of adding more features and/or capitalizing on chance. Thus, we performed a supplementary analysis, in which we combined the fully trained structural MRI brain age model with a model trained on “reshuffled” FC features using the same stacking approach in 1000 bootstrap samples. Thus, the distribution of R² in this analysis reflects the expected range of model performance from adding unrelated FC features to the structural brain age model. In fact, most of the bootstrapped models performed similarly or worse than the unimodal structural model (see Figure 1—figure supplement 4), suggesting that our stacking approach does not have a unidirectional effect of improvement from adding unrelated features. No simulation achieved performance as high or greater than the fully trained S+FC model, suggesting that the modestly sized increase in the stacked multimodal model (compared to the unimodal structural MRI model) is driven by meaningful age-related FC signal, rather than by simply capitalizing on chance in a larger feature set. We now describe this analysis in

“Comparison of Model Performance” and Figure 1—figure supplement 4:

“It is possible that the modest increase in the multimodal model was due to capitalizing on noise, simply by adding more features to the structural model. Hence, we also compared the observed R2S+FC to a bootstrapped distribution of R2 performance estimates from 1000 resamples using a model in which the original structural MRI model was stacked with a model trained on randomly reshuffled FC features. Thus, this distribution represents the expected improvements in model performance from simply adding new features to the structural MRI model with the stacked approach. The observed R2S+FC outperformed all R2 estimates from this bootstrapped distribution (p < 0.001, see Figure 1—figure supplement 4), suggesting that the modest increase in model performance observed in the stacked multimodal (S+FC) model over the unimodal structural model is due to meaningful age-related FC signal, rather than capitalizing on noise in a larger feature set.”

– After the previous step authors can choose the best performing model (either Vol-BAG or Vol+FC-BAG model) and only present the data for the selected model since results between the two models are redundant and don't add extra information to the reader.

Although our revised and supplementary analyses support the selection of the S+FC BAG model for most accurate prediction of age, as noted above in the response to comment #1, a major goal of this project was to test whether each modality (structural MRI and FC) captures unique patterns related to AD progression. As we are primarily motivated to evaluate these models in their associations with AD, it is important to consider that the most accurate BAG models for age prediction are not necessarily the ones that are most sensitive to disease. In fact, at least one study suggests that models with “moderate” age prediction accuracy might be the most useful in detecting deviation related to disease, as compared to overly “loose” or “tight” age prediction models (Bashyam et al., 2020). We now justify our motivations more clearly in the

“Introduction”:

“This project aimed to develop multimodal models of brain-predicted age, incorporating both FC and structural MRI. Participants with presymptomatic AD pathology were excluded from the training set to maximize sensitivity. We hypothesized that BAG estimates would be sensitive to the presence of AD biomarkers and early cognitive impairment. We further considered whether estimates were continuously associated with AD biomarkers of amyloid, tau, and neurodegeneration (Jack et al., 2016), as well as cognitive function. We hypothesized that FC and structural MRI would capture complementary signals related to age and AD. Thus, we systematically compared models trained on unimodal FC, structural MRI, and combined modalities, to test the added utility of multimodal integration in accurately predicting age and whether each modality captures unique relationships with AD biomarkers and cognition.”

– The analysis of hippocampal volume (specially related to the preclinical AD) needs to be confirmed. To do so, hippocampal volume as well as volumetric features from regions highly correlated with hippocampal volume should be removed from the feature set of Vol-BAG and Vol+FC-BAG models. The models need to be retrained using the same procedure. The relationship between hippocampal volume and the newly calculated Vol-BAG and Vol+FC-BAG values should be reported alongside the current results.

We agree with the reviewer that the associations between hippocampal volume and S-BAG and S+FC-BAG create problems for interpretation, as the S-BAG and S+FC-BAG models include hippocampal volume as input features and are thus circular. Moreover, it is more of interest to this study to test associations with the biomarkers associated with earlier Alzheimer disease stages, including amyloid and tau. Thus, in the interest of simplifying the focus of the study, as well as the interpretation of results, we have decided to remove the analyses of the neurodegeneration markers (including hippocampal volume).

Reviewer #3 (Recommendations for the authors):

Find below some recommendations on how (I think) the science in this manuscript might be improved in no particular order.

1. Training sample. It is unclear why one would like to minimize undetected AD pathology (amyloid positivity, that is) in the cognitively healthy training sample as many of these individuals (when Tau negative) have minimal changes in brain structure and function. Since you create a BA "norm" from these individuals, one may benefit from including a bigger, more representative sample using more lenient inclusion criteria. Decisions regarding the training sample can have a big impact on the subsequent interpretation of BA results (e.g. Hwang, 2022, Brain Comm).

We agree with the reviewer that the composition of the training sample is critical for interpreting outputs from a brain age model. Indeed, this consideration motivated us to train our model in amyloid-negative participants for both theoretical and empirical reasons. Specifically, although individuals in the earliest preclinical stages of AD (i.e. A+T-N-) likely have minimal detectable structural changes, it is possible that structural changes might be observable in later stage participants (i.e., T+, N+) even if they are cognitively normal. Thus, removing all A+ participants from the training set is a conservative approach to minimize the potential influence of presymptomatic AD pathology in any stage.

Further, although amyloid positivity may lead to minimal structural differences, prior work from our lab (and others) suggests that amyloid may be associated with differences in functional connectivity, and critically that presymptomatic amyloid pathology may confound effects that are otherwise interpreted to reflect “healthy aging” (Brier et al., 2014). Thus, if these participants are included in the training set, the FC model would learn to associate these disease-related FC patterns with normative aging. When applied to an analysis set of amyloid-positive participants, such a model would be less likely to identify deviation in the BAG, as those disease-related differences are incorporated into the model of healthy aging.

This argument was recently tested by Ly and colleagues (2020), who compared two brain age models: one trained on amyloid-negative participants vs. another trained on cognitively normal participants regardless of amyloid status. They found that the amyloid-negative trained model was able to detect differences in brain age between an amyloid-positive and amyloid-negative test sets, but the model that did not exclude amyloid-positive participants was not sensitive to this difference. Although this study was limited in that the amyloid-positive and amyloid-negative samples were drawn from separate, unmatched cohorts, it represents an important proof of concept, upon we aim to expand in this paper.

We have now revised the introduction to make the motivation for this design decision more clear:

“One approach to maximize sensitivity of BAG to presymptomatic AD pathology may be to train brain age models exclusively on amyloid-negative participants. As undetected AD pathology might influence MRI measures, and thus confound effects otherwise attributed to “healthy aging” (Brier, Thomas, Snyder, et al., 2014), including the patterns learned by a traditional brain age model, an alternative model trained on amyloid-negative participants only might be more sensitive to detect presymptomatic AD pathology as deviations in BAG. Indeed, one recent study demonstrated that an amyloid-negative trained brain age model (Ly et al., 2020) is more sensitive to progressive stages of AD than a typical amyloid-insensitive model (Cole et al., 2015). However, this comparison included amyloid-negative and amyloid-positive test samples from two separate cohorts, and thus may be driven by cohort, scanner, and/or site differences. To validate the applicability of the brain-predicted age approach to preclinical AD, it is important to test a model’s sensitivity to amyloid status, as well as continuous relationships with preclinical AD biomarkers, within a single cohort. Another recent comparison demonstrated that both traditional and amyloid-negative trained brain age models were similarly related to molecular AD biomarkers, but that further attempts to “disentangle” AD from brain age by including more advanced AD continuum participants in the training sample significantly reduced relationships between brain age and AD markers (Hwang et al., 2022). Thus, in this study we will apply the amyloid-negative training approach to a multimodal MRI dataset, in order to maximize sensitivity to AD pathology in the presymptomatic stage.”

2. Group descriptors. It is still a matter of ongoing debate, but I recommend using another descriptor for the amyloid positive group rather than "preclinical AD". Even in the NIAA-AA Research framework from 2018 (Jack Jr.) they only use this tag for individuals that are amyloid and tau positive.

We have revised our terminology throughout the manuscript and figures to refer to our groups by clinical assessment and molecular categorization (e.g, CN/A-, CN/A+, CI), rather than staged progression terms (e.g., “preclinical AD”).

3. Biomarker definition. I am not an expert on biomarkers, but the definition of pTau positivity is uncommon to me "Gaussian mixture model approach to defining pTau positivity based on the CSF pTau/Aβ40 ratio.". Could the authors justify and or cite the correspondent references?

To clarify, we fit a two-component GMM to the continuous pTau data, and then used the model classification to define pTau- and pTau+ participants. However, in order to simplify the analyses and interpretation of results, we have removed the analyses stratifying by pTau positivity and instead focus only on A- vs. A+ participants (see response below to comment #4).

4. Statistical analysis. If I have not misread, the methods section only mentions three test groups (A-, A+, and CDR>0) but the analysis is performed with four groups. This leads to confusion and should be corrected. Also, most higher-level analyses reported in the results are not described in this section. These analyses should be described in the methods section. It is difficult to evaluate whether the performed analyses are appropriate without this description. For example, (lines 323-7) the authors report three different regression models and then a fourth analysis combining the four groups, but only for FC-BAG. This procedure is unclear, not described (as far as I can see), and not justified. Another example is the analysis with NFL which is not mentioned until line 412 (p.20) in the Results section. Also, the authors use different samples for different tests, due to the lack of Biomarker information for some individuals. I suggest adding degrees of freedom/n when reporting the results, so the reader has some information regarding the sample used.

We apologize for the lack of clarity in the statistical analysis. In the revision, we have improved the clarity of this section in the following ways:

A. We no longer analyze the data using a four group split (i.e., A-T- vs. A+T- vs. A+T+ vs. CI). Instead, we focus on analyses of three groups (CN/A- vs. CN/A+ vs. CI) consistently throughout the study.

B. We now provide more detail on the higher level analyses, in which we test for group differences between the three analysis sets and test continuous associations with biomarkers and cognitive measures:

“Group differences in each BAG estimate were tested using an omnibus analysis of variance (ANOVA) test with follow-up pairwise t tests on age-residualized BAG estimates, using a false discovery rate (FDR) correction for multiple comparisons. Assumptions of normality were tested by visual inspection of quantile-quantile plots (see Figure 2—figure supplement 1). Assumptions of equality of variance were tested with Levene’s test. Linear regression models tested the effects of cognitive impairment (CDR > 0 vs. CDR 0) and amyloid positivity (A- vs. A+) on BAG estimates from each model, controlling for true age (as noted above) and demographic covariates (sex, years of education, and race). Given the potential confounding influence of head motion on FC-derived measures (59,75,76), we also included mean FD as an additional covariate of non-interest in the FC and S+FC models. We tested continuous relationships with AD biomarkers and cognitive estimates using linear regression models, including the same demographic and motion covariates.”

C. As noted in the response to Reviewer #2, comment #3, analyses of neurodegeneration biomarkers are of less interest to this study, compared to earlier biomarkers of amyloid and tau. Thus, analyses of NfL have been removed from the study.

D. We now report degrees of freedom for our regression analyses of group differences (see Table 2). We also report the number of participants in each group with available measures of each biomarker throughout the results, for example:

“355 participants (144 CN/A-, 154 CN/A+, 57 CI) had an available amyloid PET scan and 300 (120 CN/A-, 137 CN/A+, 43 CI) had an available CSF estimate of Aβ42/40.”

5. The authors are repeating the same analysis in three different modalities (also sometimes they repeat the analyses across several pairs of groups [e.g. lines 323-7]). Thus, I would strongly recommend using some type of multiple comparison corrections.

We agree with the reviewer that appropriate correction for multiple comparisons is necessary for these analyses. We now apply a false discovery rate (FDR) correction to the pairwise t tests, as described in “Statistical Analysis”:

“Group differences in each BAG estimate were tested using an omnibus analysis of variance (ANOVA) test with follow-up pairwise t tests on age-residualized BAG estimates, using a false discovery rate (FDR) correction for multiple comparisons.”

6. Table 2. The authors should mention what the units in the table represent. Also, I recommend adding df and exact significance values (at least if p >.001).

Table 2 presents the β estimates and standard error for the terms in the linear regression models predicting each BAG estimate. We now label this information more explicitly with separated columns. Further, we now provide exact p values for all terms and df for each model.

7. Atlas. The authors used the D-K atlas (not strictly the FS-defined) for BA computation. This is a suboptimal choice, and I would recommend in the future using more fine-grained parcellations. This is not a strong issue, but the choice surprised me since the authors used a 300-ROI parcellation for the rs-fMRI. Also, since the authors use cortical thickness for sampling the cortex, I would not use "Volumetric"-BA as a descriptor.

We agree with the authors that the D-K atlas is a relatively coarse anatomical parcellation. However, as these analyses were based on large, existing datasets that had already been processed and QC’ed with a harmonized pipeline, it would require significant effort to re-parcellate and QC the full dataset. Moreover, despite this coarse parcellation, the structural MRI data still predicts age quite well and outperforms the FC data, which of course uses the finer grained set of ROIs. We now acknowledge the choice of the D-K parcellation as a potential limitation and area of future development in the “Limitations”:

“Structural MRI was quantified using the Desikan atlas (Desikan et al., 2006), which although widely used, provides a relatively coarse parcellation of structural anatomy, and moreover, does not align with the parcellation used to define FC regions (Seitzman et al., 2020). Although the structural MRI data still outperformed FC in predicting age, future brain age models may further improve performance by using more refined and harmonized anatomical parcellations to define brain regions.”

Additionally, we now refer to the “volumetric” brain age model as “structural”, e.g., S-BAG, throughout the manuscript and figures.

8. Movement and rs-fMRI. The rs-fMRI preprocessing used might still lead to a signal that is related to movement. Since movement is almost always related to age and disease [and thus can affect both the BA computation and the tests in the test sample], I would suggest taking additional steps in this regard. At the minimum, I would include total motion as an additional covariate in the higher-level analysis and discuss this issue in the limitations section.

We agree with the reviewer (as well as Reviewer #2) that appropriate consideration and control for head motion artifact is a critical element in analysis of FC data. Hence, we now include mean framewise displacement (FD) as an additional covariate in all statistical analyses involving the FC and multimodal (S+FC) BAG estimates. As noted in “Statistical Analysis”:

“Given the potential confounding influence of head motion on FC-derived measures (60,76,77), we also included mean FD as an additional covariate of non-interest in the FC and S+FC models.”

9. The results in cognitively healthy samples are largely negative (i.e. do not differ with groups). One possible explanation is that the authors are using cross-sectional samples and thus – even when using BA metrics – have a signal that captures ongoing aging (accelerated aging, if you wish) and baseline (lifelong, preexisting) variability between individuals. The latter may obscure possible existing effects. I recommend the authors acknowledge the limitations of using cross-sectional data to study changes that ought to be longitudinal.

We appreciate the reviewer’s suggestion and now discuss this issue as a limitation and area of future development:

“Moreover, estimates of BAG likely capture variance in early-life factors, which may obscure associations with Alzheimer disease and cognition, especially in cross-sectional designs (87). Future studies may improve the sensitivity of BAG estimates to disease-related markers by testing associations with longitudinal change.”

Author details

1. Peter R Millar

   Department of Neurology, Washington University in St. Louis, St Louis, United States

   Contribution

   Conceptualization, Software, Formal analysis, Investigation, Visualization, Methodology, Writing – original draft, Writing – review and editing

   For correspondence

   pmillar@wustl.edu

   Competing interests

   No competing interests declared

   "This ORCID iD identifies the author of this article:" 0000-0003-4588-739X

2. Brian A Gordon

   Department of Radiology, Washington University in St. Louis, St Louis, United States

   Contribution

   Resources, Supervision, Funding acquisition, Project administration, Writing – review and editing

   Competing interests

   No competing interests declared

3. Patrick H Luckett

   Department of Neurosurgery, Washington University in St. Louis, St Louis, United States

   Contribution

   Conceptualization, Software, Methodology, Writing – review and editing

   Competing interests

   No competing interests declared

4. Tammie LS Benzinger

   1. Department of Radiology, Washington University in St. Louis, St Louis, United States
   2. Department of Neurosurgery, Washington University in St. Louis, St Louis, United States

   Contribution

   Resources, Supervision, Funding acquisition, Project administration, Writing – review and editing

   Competing interests

   received doses (AV45, AV1451) and partial support for PET scanning through an investigator-initiated research grant awarded to Washington University from Avid Radiopharmaceuticals (a wholly-owned subsidiary of Eli Lilly and Company). The author received consulting fees from Eisai, Siemens, and received payment for Biogen speaker's bureau. Tammie Benzinger acts as site investigator in clinical trials sponsored by Avid Radiopharmaceuticals, Eli Lilly and Company, Biogen, Eisai, Jaansen and Roche. The author has no other competing interests to declare

5. Carlos Cruchaga

   Department of Psychiatry, Washington University in St. Louis, St Louis, United States

   Contribution

   Resources, Funding acquisition, Project administration, Writing – review and editing

   Competing interests

   has received research support from Biogen, EISAI, Alector and Parabon. Carlos Cruchaga is a member of the advisory board of Vivid Genetics, Circular Genomics and Alector. The author has no other competing interests to declare

6. Anne M Fagan

   Department of Neurology, Washington University in St. Louis, St Louis, United States

   Contribution

   Resources, Funding acquisition, Project administration, Writing – review and editing

   Competing interests

   has received consulting fees from DiamiR and Siemens Healthcare Diagnostics Inc and has received consulting fees for participation on Scientific advisory boards for Roche Diagnostics, Genentech and Diadem. The author has received travel support for in-person attendance at ABC-DS Meeting/Retreat and travel support/honorarium for in-person attendance at Scientific Advisory Board meeting for South Texas Alzheimer's Disease Research Center (ADRC). The author has no other competing interests to declare

7. Jason J Hassenstab

   Department of Neurology, Washington University in St. Louis, St Louis, United States

   Contribution

   Resources, Funding acquisition, Project administration, Writing – review and editing

   Competing interests

   has received consulting fees from Roche and Parabon Nanolabs. The author has no other competing interests to declare

8. Richard J Perrin

   1. Department of Neurology, Washington University in St. Louis, St Louis, United States
   2. Department of Pathology and Immunology, Washington University in St. Louis, St Louis, United States

   Contribution

   Resources, Funding acquisition, Project administration, Writing – review and editing

   Competing interests

   No competing interests declared

9. Suzanne E Schindler

   Department of Neurology, Washington University in St. Louis, St Louis, United States

   Contribution

   Resources, Funding acquisition, Project administration, Writing – review and editing

   Competing interests

   received personal honoraria for presenting lectures from the University of Wisconsin, St. Luke's Hospital, Houston Methodist Medical Center, personal Honoraria for serving on the Alzheimer Disease Center Clinical Task Force from University of Washington and personal honoraria for serving on the National Centralized Repository for Alzheimer's Disease biospecimen review committee from University of Indiana. The author received travel support from National Institute on Aging grant R01AG070941, and is a board member of the Greater Missouri Alzheimer's Association. The author received plasma Ab42/Ab40 data provided by C2N Diagnostics at no cost. No payments/research funding was provided by C2N Diagnostics. No gifts/financial incentives of any kind have been provided to Dr. Schindler by C2N Diagnostics. The author has no other competing interests to declare

10. Ricardo F Allegri

    Department of Cognitive Neurology, Institute for Neurological Research (FLENI), Buenos Aires, Argentina

    Contribution

    Resources, Funding acquisition, Project administration, Writing – review and editing

    Competing interests

    No competing interests declared

11. Gregory S Day

    Department of Neurology, Mayo Clinic Florida, Jacksonville, United States

    Contribution

    Resources, Funding acquisition, Project administration, Writing – review and editing

    Competing interests

    received fees for consulting and for acting as Dementia Topic Editor from DynaMed (EBSCO Health) and received fees for consulting, grant writing / implementation Parabon Nanonlabs. The author received payment for CME Content development from PeerView Media and Continuing Education Inc, payment for educational content development and focus group participation from Eli Lilly Co, and payment for continuum manuscript authorship from the American Academy of Neurology. The author received payment for expert testimony in the case of Wernicke encephalopathy from Barrow Law. Gregory S Day acts as Clinical Director for Anti-NMDA Receptor Encephalitis Foundation, Inc. The author has stock holdings at ANI Pharmaceuticals, Inc and stock options at Parabon Nanolabs. The author has no other competing interests to declare

12. Martin R Farlow

    Department of Neurology, Indiana University School of Medicine, Indianapolis, United States

    Contribution

    Resources, Funding acquisition, Project administration, Writing – review and editing

    Competing interests

    received grants from AbbVie, Eisai, Novartis, ADCS Posiphen, Genentech and Suven Life Sciences (no grant numbers available). The author has received consulting fees from Artery Therapeutics, Avanir, Biogen, Cyclo Therapeutics, Green Valley, Lexeo, McClena, Nervive, Oligomerix, Pinteon, Prothena, Vaxinity, Athira, AZTherapies, Cognition Therapeutics, Gemvax, Ionis, Longeveron, Merck, Neurotrope Biosciences, Otsuka, Proclara and SToP-AD. The author has no other competing interests to declare

13. Hiroshi Mori

    Department of Clinical Neuroscience, Osaka Metropolitan University Medical School, Nagaoka Sutoku University, Osaka, Japan

    Contribution

    Resources, Funding acquisition, Project administration, Writing – review and editing

    Competing interests

    No competing interests declared

14. Georg Nübling

    1. Department of Neurology, Ludwig-Maximilians University, Munich, Germany
    2. German Center for Neurodegenerative Diseases, Munich, Germany

    Contribution

    Resources, Funding acquisition, Project administration, Writing – review and editing

    Competing interests

    No competing interests declared

15. The Dominantly Inherited Alzheimer Network

    Contribution

    Data curation

    Competing interests

    received funding and non-financial support for the DIAN-TU-001 trial from Avid Radiopharmaceuticals, and funding for the DIAN-TU-001 trial from Janssen, Hoffman La-Roche/Genentech, Eli Lilly & Co., Eisai, Biogen, AbbVie and Bristol Meyer Squibb. The author has equity ownership interest in C2N Diagnostics and receives royalty income based on technology (stable isotope labeling kinetics and blood plasma assay) licensed by Washington University to C2N Diagnostics. The author received International Conference Lecture Honoraria from Korean Dementia Association and Conference Lecture Honoraria from Weill Cornell Medical College. The author received support for travel expenses from Alzheimer's Association Roundtable and Duke Margolis Alzheimer's Roundtable. The author participates on an unpaid Advisory Board for Roche Gantenerumab Steering Committee and Biogen - Combination Therapy for Alzheimer's Disease, and participates on an unpaid Scientific Advisory Board for UK Dementia Research Institute at University College London and Stanford University, Next Generation Translational Proteomics for Alzheimer's and Related Dementias. The author receives an income from C2N Diagnostics for serving on the scientific advisory board. The author has received equipment and materials from Avid Radiopharmaceuticals, Eli Lilly & Co, Hoffman La-Roche, Eisai and Janssen. Unrelated to this article, Randall Bateman serves as principal investigator of the DIAN-TU, which is supported by the Alzheimer's Association, GHR Foundation, an anonymous organization and the DIAN-TU Pharma Consortium (Active: Eli Lilly and Company/Avid Radiopharmaceuticals, F. Hoffman-La Roche/Genentech, Biogen, Eisai, and Janssen. Previous: Abbvie, Amgen, AstraZeneca, Forum, Mithridion, Novartis, Pfizer, Sanofi, and United Neuroscience). In addition, in-kind support has been received from CogState and Signant Health. Unrelated to this article Randall Bateman has submitted the US nonprovisional patent application "Methods for Measuring the Metabolism of CNS Derived Biomolecules In Vivo" and provisional patent application "Plasma Based Methods for Detecting CNS Amyloid Deposition". The author has no other competing interests to declare

    1. Adam Sarah
    2. Allegri Ricardo
    3. Araki Aki
    4. Barthelemy Nicolas
    5. Bateman Randall
    6. Bechara Jacob
    7. Benzinger Tammie
    8. Berman Sarah
    9. Bodge Courtney
    10. Brandon Susan
    11. Brooks William Bill
    12. Brosch Jared
    13. Buck Jill
    14. Buckles Virginia
    15. Carter Kathleen
    16. Cash Lisa
    17. Chen Charlie
    18. Chhatwal Jasmeer
    19. Mendez Patricio C
    20. Chua Jasmin
    21. Chui Helena
    22. Courtney Laura
    23. Cruchaga Carlos
    24. Day Gregory S
    25. DeLaCruz Chrismary
    26. Denner Darcy
    27. Diffenbacher Anna
    28. Dincer Aylin
    29. Donahue Tamara
    30. Douglas Jane
    31. Duong Duc
    32. Egido Noelia
    33. Esposito Bianca
    34. Fagan Anne
    35. Farlow Marty
    36. Feldman Becca
    37. Fitzpatrick Colleen
    38. Flores Shaney
    39. Fox Nick
    40. Franklin Erin
    41. Joseph-Mathurin Nelly
    42. Fujii Hisako
    43. Gardener Samantha
    44. Ghetti Bernardino
    45. Goate Alison
    46. Goldberg Sarah
    47. Goldman Jill
    48. Gonzalez Alyssa
    49. Gordon Brian
    50. Gräber-Sultan Susanne
    51. Graff-Radford Neill
    52. Graham Morgan
    53. Gray Julia
    54. Gremminger Emily
    55. Grilo Miguel
    56. Groves Alex
    57. Haass Christian
    58. Häsler Lisa
    59. Hassenstab Jason
    60. Hellm Cortaiga
    61. Herries Elizabeth
    62. Hoechst-Swisher Laura
    63. Hofmann Anna
    64. Holtzman David
    65. Hornbeck Russ
    66. Igor Yakushev
    67. Ihara Ryoko
    68. Ikeuchi Takeshi
    69. Ikonomovic Snezana
    70. Ishii Kenji
    71. Jack Clifford
    72. Jerome Gina
    73. Johnson Erik
    74. Jucker Mathias
    75. Karch Celeste
    76. Käser Stephan
    77. Kasuga Kensaku
    78. Keefe Sarah
    79. Klunk William
    80. Koeppe Robert
    81. Koudelis Deb
    82. Kuder-Buletta Elke
    83. Laske Christoph
    84. Levey Allan
    85. Levin Johannes
    86. Li Yan
    87. Lopez MD Oscar
    88. Marsh Jacob
    89. Martins Ralph
    90. Mason Neal S
    91. Masters Colin
    92. Mawuenyega Kwasi
    93. McCullough Austin
    94. McDade Eric
    95. Mejia Arlene
    96. Morenas-Rodriguez Estrella
    97. Morris John
    98. Mountz James
    99. Mummery Cath
    100. Nadkarni Neelesh
    101. Nagamatsu Akemi
    102. Neimeyer Katie
    103. Niimi Yoshiki
    104. Noble James
    105. Norton Joanne
    106. Nuscher Brigitte
    107. Obermüller Ulricke
    108. O'Connor Antoinette
    109. Patira Riddhi
    110. Perrin Richard
    111. Ping Lingyan
    112. Preische Oliver
    113. Renton Alan
    114. Ringman John
    115. Salloway Stephen
    116. Schofield Peter
    117. Senda Michio
    118. Seyfried Nicholas T
    119. Shady Kristine
    120. Shimada Hiroyuki
    121. Sigurdson Wendy
    122. Smith Jennifer
    123. Smith Lori
    124. Snitz Beth
    125. Sohrabi Hamid
    126. Stephens Sochenda
    127. Taddei Kevin
    128. Thompson Sarah
    129. Vöglein Jonathan
    130. Wang Peter
    131. Wang Qing
    132. Weamer Elise
    133. Xiong Chengjie
    134. Xu Jinbin
    135. Xu Xiong

16. Randall J Bateman

    Department of Neurology, Washington University in St. Louis, St Louis, United States

    Contribution

    Resources, Funding acquisition, Project administration, Writing – review and editing

    Competing interests

    has received consulting fees from Barcelona Brain Research Center BBRC and Native Alzheimer Disease-Related Resource Center in Minority Aging Research, Ext Adv Board. The author has received payment or honoraria for lectures from Montefiore Grand Rounds, NY and Tetra-Inst ADRC seminar series, Grand Rds, NY. The author has participated on the Research Strategy Council for the Cure Alzheimer's Fund, the Diverse VCID Observational Study Monitoring Board and the LEADS Advisory Board, Indiana University. The author has no other competing interests to declare

17. John C Morris

    Department of Neurology, Washington University in St. Louis, St Louis, United States

    Contribution

    Resources, Funding acquisition, Project administration, Writing – review and editing

    Competing interests

    No competing interests declared

18. Beau M Ances

    1. Department of Neurology, Washington University in St. Louis, St Louis, United States
    2. Department of Radiology, Washington University in St. Louis, St Louis, United States

    Contribution

    Conceptualization, Resources, Supervision, Funding acquisition, Methodology, Project administration, Writing – review and editing

    Competing interests

    No competing interests declared

    "This ORCID iD identifies the author of this article:" 0000-0003-3862-7397

• 1,282

  Page views

• 237

  Downloads

• 4

  Citations

Article citation count generated by polling the highest count across the following sources: Crossref, PubMed Central, Scopus.