Disentangling Accelerated Cognitive Decline from the Normal Aging Process and Unraveling Its Genetic Components: A Neuroimaging-Based Deep Learning Approach
Restricted accessResearch articleFirst published online February 13, 2024
Disentangling Accelerated Cognitive Decline from the Normal Aging Process and Unraveling Its Genetic Components: A Neuroimaging-Based Deep Learning Approach
The progressive cognitive decline, an integral component of Alzheimer’s disease (AD), unfolds in tandem with the natural aging process. Neuroimaging features have demonstrated the capacity to distinguish cognitive decline changes stemming from typical brain aging and AD between different chronological points.
Objective:
To disentangle the normal aging effect from the AD-related accelerated cognitive decline and unravel its genetic components using a neuroimaging-based deep learning approach.
Methods:
We developed a deep-learning framework based on a dual-loss Siamese ResNet network to extract fine-grained information from the longitudinal structural magnetic resonance imaging (MRI) data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) study. We then conducted genome-wide association studies (GWAS) and post-GWAS analyses to reveal the genetic basis of AD-related accelerated cognitive decline.
Results:
We used our model to process data from 1,313 individuals, training it on 414 cognitively normal people and predicting cognitive assessment for all participants. In our analysis of accelerated cognitive decline GWAS, we identified two genome-wide significant loci: APOE locus (chromosome 19 p13.32) and rs144614292 (chromosome 11 p15.1). Variant rs144614292 (G > T) has not been reported in previous AD GWA studies. It is within the intronic region of NELL1, which is expressed in neurons and plays a role in controlling cell growth and differentiation. The cell-type-specific enrichment analysis and functional enrichment of GWAS signals highlighted the microglia and immune-response pathways.
Conclusions:
Our deep learning model effectively extracted relevant neuroimaging features and predicted individual cognitive decline. We reported a novel variant (rs144614292) within the NELL1 gene.
(2021) 2021 Alzheimer’s disease facts and figures. Alzheimers Dement17, 327–406.
2.
GatzM, ReynoldsCA, FratiglioniL, JohanssonB, MortimerJA, BergS, FiskeA, PedersenNL (2006) Role of genes and environments for explaining Alzheimer disease. Arch Gen Psychiatry63, 168–174.
3.
SimsR, HillM, WilliamsJ (2020) The multiplex model of the genetics of Alzheimer’s disease. Nat Neurosci23, 311–322.
4.
KunkleBW, Grenier-BoleyB, SimsR, BisJC, DamotteV, NajAC, BolandA, VronskayaM, van der LeeSJ, Amlie-WolfA, et al. (2019) Genetic meta-analysis of diagnosed Alzheimer’s disease identifies new risk loci and implicates Aβ, tau, immunity and lipid processing. Nat Genet51, 414–430.
5.
PedersenNL, GatzM, BergS, JohanssonB (2004) How heritable is Alzheimer’s disease late in life? Findings from Swedish twins. Ann Neurol55, 180–185.
6.
WightmanDP, JansenIE, SavageJE, ShadrinAA, BahramiS, HollandD, RongveA, BørteS, WinsvoldBS, DrangeOK, MartinsenAE, SkogholtAH, WillerC, BråthenG, BosnesI, NielsenJB, FritscheLG, ThomasLF, PedersenLM, GabrielsenME, JohnsenMB, MeisingsetTW, ZhouW, ProitsiP, HodgesA, DobsonR, VelayudhanL, HeilbronK, AutonA, 23 and Me Research Team, SealockJM, DavisLK, PedersenNL, ReynoldsCA, KarlssonIK, MagnussonS, StefanssonH, ThordardottirS, JonssonPV, SnaedalJ, ZettergrenA, SkoogI, KernS, WaernM, ZetterbergH, BlennowK, StordalE, HveemK, ZwartJ-A, AthanasiuL, SelnesP, SaltvedtI, SandoSB, UlsteinI, DjurovicS, FladbyT, AarslandD, SelbækG, RipkeS, StefanssonK, AndreassenOA, PosthumaD (2021) A genome-wide association study with 1,126,563 individuals identifies new risk loci for Alzheimer’s disease. Nat Genet53, 1276–1282.
HadjichrysanthouC, EvansS, BajajS, SiakallisLC, McRae-McKeeK, de WolfF, AndersonRM, Alzheimer’s Disease Neuroimaging Initiative (2020) The dynamics of biomarkers across the clinical spectrum of Alzheimer’s disease. Alzheimers Res Ther12, 74.
9.
LogueMW, PanizzonMS, ElmanJA, GillespieNA, HattonSN, GustavsonDE, AndreassenOA, DaleAM, FranzCE, LyonsMJ, NealeMC, ReynoldsCA, TuX, KremenWS (2019) Use of an Alzheimer’s disease polygenic risk score to identify mild cognitive impairment in adults in their 50s. Mol Psychiatry24, 421–430.
10.
Arevalo-RodriguezI, SmailagicN, Roqué-FigulsM, CiapponiA, Sanchez-PerezE, GiannakouA, PedrazaOL, Bonfill CospX, CullumS (2021) Mini-Mental State Examination (MMSE) for the early detection of dementia in people with mild cognitive impairment (MCI). Cochrane Database Syst Rev7, CD010783.
11.
KueperJK, SpeechleyM, Montero-OdassoM (2018) The Alzheimer’s Disease Assessment Scale-Cognitive Subscale (ADAS-Cog): Modifications and responsiveness in pre-dementia populations. A narrative review. J Alzheimers Dis63, 423–444.
12.
DevenneyE, HodgesJR (2017) The Mini-Mental State Examination: Pitfalls and limitations. Pract Neurol17, 79–80.
13.
RiesML, CarlssonCM, RowleyHA, SagerMA, GleasonCE, AsthanaS, JohnsonSC (2008) Magnetic resonance imaging characterization of brain structure and function in mild cognitive impairment: A review. J Am Geriatr Soc56, 920–934.
14.
LedigC, SchuhA, GuerreroR, HeckemannRA, RueckertD (2018) Structural brain imaging in Alzheimer’s disease and mild cognitive impairment: Biomarker analysis and shared morphometry database. Sci Rep8, 11258.
15.
StephenR, LiuY, NganduT, AntikainenR, HulkkonenJ, KoikkalainenJ, KemppainenN, LötjönenJ, LevälahtiE, ParkkolaR, PippolaP, RinneJ, StrandbergT, TuomilehtoJ, VanninenR, KivipeltoM, SoininenH, SolomonA, FINGER study group (2019) Brain volumes and cortical thickness on MRI in the Finnish Geriatric Intervention Study to Prevent Cognitive Impairment and Disability (FINGER). Alzheimers Res Ther11, 53.
16.
CountsSE, IkonomovicMD, MercadoN, VegaIE, MufsonEJ (2017) Biomarkers for the early detection and progression of Alzheimer’s disease. Neurotherapeutics14, 35–53.
17.
HuttonJS, DudleyJ, Horowitz-KrausT, DeWittT, HollandSK (2020) Associations between screen-based media use and brain white matter integrity in preschool-aged children. JAMA Pediatr174, e193869.
18.
van MaurikIS, VosSJ, BosI, BouwmanFH, TeunissenCE, ScheltensP, BarkhofF, FrolichL, KornhuberJ, WiltfangJ, MaierW, PetersO, RütherE, NobiliF, FrisoniGB, SpiruL, Freund-LeviY, WallinAK, HampelH, SoininenH, TsolakiM, VerheyF, KłoszewskaI, MecocciP, VellasB, LovestoneS, GalluzziS, HerukkaS-K, SantanaI, BaldeirasI, de MendonçaA, SilvaD, ChetelatG, EgretS, PalmqvistS, HanssonO, VisserPJ, BerkhofJ, van der FlierWM, Alzheimer’s Disease Neuroimaging Initiative (2019) Biomarker-based prognosis for people with mild cognitive impairment (ABIDE): A modelling study. Lancet Neurol18, 1034–1044.
19.
FjellAM, McEvoyL, HollandD, DaleAM, WalhovdKB, Alzheimer’s Disease Neuroimaging Initiative (2014) What is normal in normal aging? Effects of aging, amyloid and Alzheimer’s disease on the cerebral cortex and the hippocampus. Prog Neurobiol117, 20–40.
20.
GonneaudJ, BariaAT, Pichet BinetteA, GordonBA, ChhatwalJP, CruchagaC, JuckerM, LevinJ, SallowayS, FarlowM, GauthierS, BenzingerTLS, MorrisJC, BatemanRJ, BreitnerJCS, PoirierJ, Vachon-PresseauE, VilleneuveS, Alzheimer’s Disease Neuroimaging Initiative (ADNI), Dominantly Inherited Alzheimer Network (DIAN) Study Group, Pre-symptomatic Evaluation of Experimental or Novel Treatments for Alzheimer’s Disease (PREVENT-AD) Research Group (2021) Accelerated functional brain aging in pre-clinical familial Alzheimer’s disease. Nat Commun12, 5346.
21.
OuyangJ, ZhaoQ, AdeliE, ZaharchukG, PohlKM (2022) Disentangling normal aging from severity of disease via weak supervision on longitudinal MRI. IEEE Trans Med Imaging41, 2558–2569.
22.
LorenziM, PennecX, FrisoniGB, AyacheN, Alzheimer’s Disease Neuroimaging Initiative (2015) Disentangling normal aging from Alzheimer’s disease in structural magnetic resonance images. Neurobiol Aging36 Suppl 1, S42–52.
23.
VeitchDP, WeinerMW, AisenPS, BeckettLA, DeCarliC, GreenRC, HarveyD, JackCRJr, JagustW, LandauSM, MorrisJC, OkonkwoO, PerrinRJ, PetersenRC, Rivera-MindtM, SaykinAJ, ShawLM, TogaAW, TosunD, TrojanowskiJQ, Alzheimer’s Disease Neuroimaging Initiative (2022) Using the Alzheimer’s Disease Neuroimaging Initiative to improve early detection, diagnosis, and treatment of Alzheimer’s disease. Alzheimers Dement18, 824–857.
24.
van LoenhoudAC, van der FlierWM, WinkAM, DicksE, GrootC, TwiskJ, BarkhofF, ScheltensP, OssenkoppeleR, Alzheimer’s Disease Neuroimaging Initiative (2019) Cognitive reserve and clinical progression in Alzheimer disease: A paradoxical relationship. Neurology93, e334–e346.
25.
LiuM, ZhangJ, AdeliE, ShenD (2019) Joint classification and regression via deep multi-task multi-channel learning for Alzheimer’s disease diagnosis. IEEE Trans Biomed Eng66, 1195–1206.
26.
SarvamangalaDR, KulkarniRV (2022) Convolutional neural networks in medical image understanding: A survey. Evol Intell15, 1–22.
27.
FarooqA, AnwarS, AwaisM, RehmanS (2017) A deep CNN based multi-class classification of Alzheimer’s disease using MRI. In 2017 IEEE International Conference on Imaging Systems and Techniques (IST) IEEE, pp. 1–6.
28.
AbdulAzeemY, BahgatWM, BadawyM (2021) A CNN based framework for classification of Alzheimer’s disease. Neural Comput Appl33, 10415–10428.
29.
AlSaeedD, OmarSF (2022) Brain MRI analysis for Alzheimer’s disease diagnosis using CNN-based feature extraction and machine learning. Sensors (Basel)22, 2911.
30.
DyrbaM, HanzigM, AltensteinS, BaderS, BallariniT, BrosseronF, BuergerK, CantréD, DechentP, DobischL, DüzelE, EwersM, FliessbachK, GlanzW, HaynesJ-D, HenekaMT, JanowitzD, KelesDB, KilimannI, LaskeC, MaierF, MetzgerCD, MunkMH, PerneczkyR, PetersO, PreisL, PrillerJ, RauchmannB, RoyN, SchefflerK, SchneiderA, SchottBH, SpottkeA, SpruthEJ, WeberM-A, Ertl-WagnerB, WagnerM, WiltfangJ, JessenF, TeipelSJ, for the ADNI, AIBL, DELCODE study groups (2021) Improving 3D convolutional neural network comprehensibility via interactive visualization of relevance maps: Evaluation in Alzheimer’s disease. Alzheimers Res Ther13, 191.
31.
LeiB, LiangE, YangM, YangP, ZhouF, TanE-L, LeiY, LiuC-M, WangT, XiaoX, WangS (2022) Predicting clinical scores for Alzheimer’s disease based on joint and deep learning. Expert Syst Appl187, 115966.
32.
QiaoH, ChenL, ZhuF (2022) Ranking convolutional neural network for Alzheimer’s disease mini-mental state examination prediction at multiple time-points. Comput Methods Programs Biomed213, 106503.
33.
BellenguezC, KüçükaliF, JansenIE, KleineidamL, Moreno-GrauS, AminN, NajAC, Campos-MartinR, Grenier-BoleyB, AndradeV, et al. (2022) New insights into the genetic etiology of Alzheimer’s disease and related dementias. Nat Genet54, 412–436.
34.
MohsRC, KnopmanD, PetersenRC, FerrisSH, ErnestoC, GrundmanM, SanoM, BieliauskasL, GeldmacherD, ClarkC, ThalLJ (1997) Development of cognitive instruments for use in clinical trials of antidementia drugs: Additions to the Alzheimer’s Disease Assessment Scale that broaden its scope. The Alzheimer’s Disease Cooperative Study. Alzheimer Dis Assoc Disord11 Suppl 2, S13–S21.
GorgolewskiKJ, AuerT, CalhounVD, CraddockRC, DasS, DuffEP, FlandinG, GhoshSS, GlatardT, HalchenkoYO, HandwerkerDA, HankeM, KeatorD, LiX, MichaelZ, MaumetC, NicholsBN, NicholsTE, PellmanJ, PolineJ-B, RokemA, SchaeferG, SochatV, TriplettW, TurnerJA, VaroquauxG, PoldrackRA (2016) The brain imaging data structure, a format for organizing and describing outputs of neuroimaging experiments. Sci Data3, 160044.
37.
SledJG, ZijdenbosAP, EvansAC (1998) A nonparametric method for automatic correction of intensity nonuniformity in MRI data. IEEE Trans Med Imaging17, 87–97.
38.
ValverdeS, CollL, ValenciaL, ClèriguesA, OliverA, VilanovaJC, Ramió-TorrentàL, RoviraÀ, LladóX (2021) Assessing the accuracy and reproducibility of PARIETAL: A deep learning brain extraction algorithm. J Magn Reson Imaging, doi: 10.1002/jmri.27776.
39.
FischlB (2012) FreeSurfer. Neuroimage62, 774–781.
40.
SchaeverbekeJM, GabelS, MeersmansK, LuckettES, De MeyerS, AdamczukK, NelissenN, GoovaertsV, RadwanA, SunaertS, DupontP, Van LaereK, VandenbergheR (2021) Baseline cognition is the best predictor of 4-year cognitive change in cognitively intact older adults. Alzheimers Res Ther13, 75.
41.
McDonoughIM, PoppTE (2020) Linear and nonlinear relationships between cognitive subdomains of ability discrepancy and Alzheimer’s disease biomarkers. Neuropsychology34, 211–226.
BromleyJ, GuyonI, LeCunY, SäckingerE, ShahR (1993) Signature verification using a “Siamese” time delay neural network. Adv Neural Inf Process Syst6, 737–744.
46.
HeK, ZhangX, RenS, SunJ (2016) Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778.
47.
KingmaDP, BaJ (2014) Adam: A method for stochastic optimization. arXiv [csLG].
WangK, LiM, HakonarsonH (2010) ANNOVAR: Functional annotation of genetic variants from high-throughput sequencing data. Nucleic Acids Res38, e164.
55.
LiH (2011) A statistical framework for SNP calling, mutation discovery, association mapping and population genetical parameter estimation from sequencing data. Bioinformatics27, 2987–2993.
56.
DanecekP, AutonA, AbecasisG, AlbersCA, BanksE, DePristoMA, HandsakerRE, LunterG, MarthGT, SherryST, McVeanG, DurbinR, 1000 Genomes Project Analysis Group (2011) The variant call format and VCFtools. Bioinformatics27, 2156–2158.
57.
PurcellS, NealeB, Todd-BrownK, ThomasL, FerreiraMAR, BenderD, MallerJ, SklarP, de BakkerPIW, DalyMJ, ShamPC (2007) PLINK: A tool set for whole-genome association and population-based linkage analyses. Am J Hum Genet81, 559–575.
58.
IGSR: The International Genome Sample Resource, 1000 Genome Project ftp.
59.
McCawZR, LaneJM, SaxenaR, RedlineS, LinX (2020) Operating characteristics of the rank-based inverse normal transformation for quantitative trait analysis in genome-wide association studies. Biometrics76, 1262–1272.
60.
ZhengZ, HuangD, WangJ, ZhaoK, ZhouY, GuoZ, ZhaiS, XuH, CuiH, YaoH, WangZ, YiX, ZhangS, ShamPC, LiMJ (2020) QTLbase: An integrative resource for quantitative trait loci across multiple human molecular phenotypes. Nucleic Acids Res48, D983–D991.
61.
BryoisJ, CaliniD, MacnairW, FooL, UrichE, OrtmannW, IglesiasVA, SelvarajS, NutmaE, MarzinM, AmorS, WilliamsA, Castelo-BrancoG, MenonV, De JagerP, MalhotraD (2022) Cell-type-specific cis-eQTLs in eight human brain cell types identify novel risk genes for psychiatric and neurological disorders. Nat Neurosci25, 1104–1112.
62.
GiambartolomeiC, VukcevicD, SchadtEE, FrankeL, HingoraniAD, WallaceC, PlagnolV (2014) Bayesian test for colocalisation between pairs of genetic association studies using summary statistics. PLoS Genet10, e1004383.
63.
WangG, SarkarA, CarbonettoP, StephensM (2020) A simple new approach to variable selection in regression, with application to genetic fine mapping. J R Stat Soc Series B Stat Methodol82, 1273–1300.
64.
ManuelAM, DaiY, JiaP, FreemanLA, ZhaoZ (2023) A gene regulatory network approach harmonizes genetic and epigenetic signals and reveals repurposable drug candidates for multiple sclerosis. Hum Mol Genet32, 998–1009.
65.
ManuelAM, DaiY, FreemanLA, JiaP, ZhaoZ (2021) An integrative study of genetic variants with brain tissue expression identifies viral etiology and potential drug targets of multiple sclerosis. Mol Cell Neurosci115, 103656.
66.
Gagliano TaliunSA, VandeHaarP, BoughtonAP, WelchRP, TaliunD, SchmidtEM, ZhouW, NielsenJB, WillerCJ, LeeS, FritscheLG, BoehnkeM, AbecasisGR (2020) Exploring and visualizing large-scale genetic associations by using PheWeb. Nat Genet52, 550–552.
67.
de LeeuwCA, MooijJM, HeskesT, PosthumaD (2015) MAGMA: Generalized gene-set analysis of GWAS data. PLoS Comput Biol11, e1004219.
68.
WatanabeK, TaskesenE, van BochovenA, PosthumaD (2017) Functional mapping and annotation of genetic associations with FUMA. Nat Commun8, 1826.
69.
WatanabeK, Umićević MirkovM, de LeeuwCA, van den HeuvelMP, PosthumaD (2019) Genetic mapping of celltype specificity for complex traits. Nat Commun10, 3222.
70.
FernandesB, EnduruN, FernandesB, BahramiS, DaiY, AndreassenO, ZhaoZ (2023) Genetic overlap between Alzheimer’s disease and immune-mediated diseases: An atlas of shared genetic determinants and biological convergence. Research Square, doi: 10.21203/rs.3.rs-3346282/v1 [Preprint]. Posted September 28, 2023.
71.
LiberzonA, BirgerC, ThorvaldsdóttirH, GhandiM, MesirovJP, TamayoP (2015) The Molecular Signatures Database (MSigDB) hallmark gene set collection. Cell Syst1, 417–425.
DaiY, HuR, ManuelAM, LiuA, JiaP, ZhaoZ (2021) CSEA-DB: An omnibus for human complex trait and cell typeassociations. Nucleic Acids Res49, D862–D870.
76.
PeiG, HuR, DaiY, ManuelAM, ZhaoZ, JiaP (2021) Predicting regulatory variants using a dense epigenomic mapped CNN model elucidated the molecular basis of trait-tissue associations. Nucleic Acids Res49, 53–66.
77.
PeiG, HuR, JiaP, ZhaoZ (2021) DeepFun: A deep learning sequence-based model to decipher non-coding variant effect in a tissue- and cell type-specific manner. Nucleic Acids Res49, W131–W139.
HemaniG, ZhengJ, ElsworthB, WadeKH, HaberlandV, BairdD, LaurinC, BurgessS, BowdenJ, LangdonR, TanVY, YarmolinskyJ, ShihabHA, TimpsonNJ, EvansDM, ReltonC, MartinRM, Davey SmithG, GauntTR, HaycockPC (2018) The MR-Base platform supports systematic causal inference across the human phenome. Elife7, e34408.
80.
LiuA, ManuelAM, DaiY, ZhaoZ (2022) Prioritization of risk genes in multiple sclerosis by a refined Bayesian framework followed by tissue-specificity and cell type feature assessment. BMC Genomics23, 362.
Bulik-SullivanBK, LohP-R, FinucaneHK, RipkeS, YangJ, Schizophrenia Working Group of the Psychiatric Genomics Consortium, PattersonN, DalyMJ, PriceAL, NealeBM (2015) LD Score regression distinguishes confounding from polygenicity in genome-wide association studies. Nat Genet47, 291–295.
83.
LiC, ZhengZ, HaP, ChenX, JiangW, SunS, ChenF, AsatrianG, BerthiaumeEA, KimJK, ChenEC, PangS, ZhangX, TingK, SooC (2018) Neurexin superfamily cell membrane receptor contactin-associated protein like-4 (Cntnap4) is involved in neural EGFL-like 1 (Nell-1)-responsive osteogenesis. J Bone Miner Res33, 1813–1825.
84.
OkbayA, BeauchampJP, FontanaMA, LeeJJ, PersTH, RietveldCA, TurleyP, ChenG-B, EmilssonV, MeddensSFW, et al. (2016) Genome-wide association study identifies 74 loci associated with educational attainment. Nature533, 539–542.
85.
LiQS, De MuynckL (2021) Differentially expressed genes in Alzheimer’s disease highlighting the roles of microglia genes including OLR1 and astrocyte gene CDK2AP1. Brain Behav Immun Health13, 100227.
WisnerA, DufourE, MessaoudiM, NejdiA, MarcelA, UngeheuerM-N, RougeotC (2006) Human Opiorphin, a natural antinociceptive modulator of opioid-dependent pathways. Proc Natl Acad Sci U S A103, 17979–17984.
88.
El-AmouriSS, ZhuH, YuJ, MarrR, VermaIM, KindyMS (2008) Neprilysin: An enzyme candidate to slow the progression of Alzheimer’s disease. Am J Pathol172, 1342–1354.
89.
YangQ-Z, LuS-S, TianX-Z, YangA-M, GeW-W, ChenQ (2011) The antidepressant-like effect of human opiorphin via opioid-dependent pathways in mice. Neurosci Lett489, 131–135.
90.
GrahamSE, ClarkeSL, WuK-HH, KanoniS, ZajacGJM, RamdasS, SurakkaI, NtallaI, VedantamS, WinklerTW, et al. (2021) The power of genetic diversity in genome-wide association studies of lipids. Nature600, 675–679.
91.
Loera-ValenciaR, GoikoleaJ, Parrado-FernandezC, Merino-SerraisP, MaioliS (2019) Alterations in cholesterol metabolism as a risk factor for developing Alzheimer’s disease: Potential novel targets for treatment. J Steroid Biochem Mol Biol190, 104–114.
92.
HwangG, AbdulkadirA, ErusG, HabesM, PomponioR, ShouH, DoshiJ, MamourianE, RashidT, BilgelM, FanY, SotirasA, SrinivasanD, MorrisJC, AlbertMS, BryanNR, ResnickSM, NasrallahIM, DavatzikosC, WolkDA, from the iSTAGING consortium, ADNI (2022) Disentangling Alzheimer’s disease neurodegeneration from typical brain ageing using machine learning. Brain Commun4, fcac117.
