Multifactorial Modeling of Cognitive Trajectories Using an Advanced Regression Technique: Improving Our Understanding of Biomarkers and Modifiable Variables that Support Cognition
Restricted accessArticle commentaryFirst published online May 16, 2023
Multifactorial Modeling of Cognitive Trajectories Using an Advanced Regression Technique: Improving Our Understanding of Biomarkers and Modifiable Variables that Support Cognition
Current research trends emphasize complex models of cognitive outcomes, with multiple, interacting predictors, including factors amenable to interventions toward sustaining healthy cognitive aging. Such models often require advanced analysis techniques. The article by Stark et al., ‘Partial least squares regression analysis of Alzheimer’s disease biomarkers, modifiable health variables, and cognitive change in older adults with mild cognitive impairment’, uses partial least squares regression to examine the associations to memory and executive change of 29 biomarker and demographic variables. This commentary discusses the significance of their results and methods within the context of current research foci.
Iturria-MedinaY, SoteroRC, ToussaintPJ, Mateos-PérezJM, EvansAC; Alzheimer’s Disease Neuroimaging Initiative (2016) Early role of vascular dysregulation on late-onset Alzheimer’s disease based on multifactorial data-driven analysis. Nat Commun7, 11934.
4.
Le GrandQ, SatizabalCL, SargurupremrajM, MishraA, SoumaréA, LaurentA, CrivelloF, TsuchidaA, ShinJ, MacalliM, SinghB, BeiserAS, DeCarliC, FletcherE, PausT, LathropM, AdamsHHH, BisJC, SeshadriS, TzourioC, MazoyerB, DebetteS (2022) Genomic studies across the lifespan point to early mechanisms determining subcortical volumes. Biol Psychiatry Cogn Neurosci Neuroimaging7, 616–628.
5.
OveisgharanS, WilsonRS, YuL, SchneiderJA, BennettDA (2020) Association of early-life cognitive enrichment with Alzheimer disease pathological changes and cognitive decline. JAMA Neurol77, 1217–1224.
6.
KoK, ByunMS, YiD, LeeJH, KimCH, LeeDY (2018) Early-life cognitive activity is related to reduced neurodegeneration in Alzheimer signature regions in late life. Front Aging Neurosci10, 70.
7.
SiscoS, GrossAL, ShihRA, SachsBC, GlymourMM, BangenKJ, BenitezA, SkinnerJ, SchneiderBC, ManlyJJ (2015) The role of early-life educational quality and literacy in explaining racial disparities in cognition in late life. J Gerontol B Psychol Sci Soc Sci70, 557–567.
8.
ZahodneLB, SternY, ManlyJJ (2015) Differing effects of education on cognitive decline in diverse elders with low versus high educational attainment. Neuropsychology29, 649–657.
9.
KivipeltoM, MangialascheF, NganduT (2018) Lifestyle interventions to prevent cognitive impairment, dementia and Alzheimer disease. Nat Rev Neurol14, 653–666.
10.
RosenbergA, NganduT, RusanenM, AntikainenR, BäckmanL, HavulinnaS, HänninenT, LaatikainenT, LehtisaloJ, LevälahtiE, LindströmJ, PaajanenT, PeltonenM, SoininenH, Stigsdotter-NeelyA, StrandbergT, TuomilehtoJ, SolomonA, KivipeltoM (2018) Multidomain lifestyle intervention benefits a large elderly population at risk for cognitive decline and dementia regardless of baseline characteristics: The FINGER trial. Alzheimers Dement14, 263–270.
11.
NganduT, LehtisaloJ, SolomonA, LevälahtiE, AhtiluotoS, AntikainenR, BäckmanL, HänninenT, JulaA, LaatikainenT, LindströmJ, MangialascheF, PaajanenT, PajalaS, PeltonenM, RauramaaR, Stigsdotter-NeelyA, StrandbergT, TuomilehtoJ, SoininenH, KivipeltoM (2015) A 2 year multidomain intervention of diet, exercise, cognitive training, and vascular risk monitoring versus control to prevent cognitive decline in at-risk elderly people (FINGER): A randomised controlled trial. Lancet385, 2255–2263.
12.
CaroliA, PrestiaA, WadeS, ChenK, AyutyanontN, LandauSM, MadisonCM, HaenseC, HerholzK, ReimanEM, JagustWJ, FrisoniGB (2015) Alzheimer disease biomarkers as outcome measures for clinical trials in MCI. Alzheimer Dis Assoc Disord29, 101–109.
13.
JackCR, ShiungMM, WeigandSD, O’BrienPC, GunterJL, BoeveBF, KnopmanDS, SmithGE, IvnikRJ, TangalosEG, PetersenRC, JackCJr (2005) Brain atrophy rates predict subsequent clinical conversion in normal elderly and amnestic MCI. Neurology65, 1227–1231.
14.
ChenT, GuestrinC (2016) XGBoost: A scalable tree boosting system. KDD ’16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785-794.
15.
NoharaY, MatsumotoK, SoejimaH, NakashimaN (2022) Explanation of machine learning models using shapley additive explanation and application for real data in hospital. Comput Methods Programs Biomed214, 106584.
16.
YinC, ImmsP, ChengM, AmgalanA, ChowdhuryNF, MassettRJ, ChaudhariNN, ChenX, ThompsonPM, BogdanP, IrimiaA (2023) Anatomically interpretable deep learning of brain age captures domain-specific cognitive impairment. Proc Natl Acad Sci U S A120, 1–11.
17.
LeeG, NhoK, KangB, SohnKA, KimD; for Alzheimer’s Disease Neuroimaging Initiative (2019) Predicting Alzheimer’s disease progression using multi-modal deep learning approach. Sci Rep9, 1952.
18.
StarkJ, PalomboDJ, HayesJP, HierscheKJ, HasselbachAN, HayesSM (2022) Partial least squares analysis of Alzheimer’s disease biomarkers, modifiable health variables, and cognition in older adults with mild cognitive impairment. J Int Neuropsychol Soc28, 781–789.
19.
KrishnanA, WilliamsLJ, McIntoshAR, AbdiH (2011) Partial least squares (PLS) methods for neuroimaging: A tutorial and review. Neuroimage56, 455–475.
20.
AbdiH (2007) Partial least square regression (PLSR). In Encyclopedia of Measurement and Statistics, Salkind N, ed. SAGE Publications, Inc., pp. 1-13.
21.
ErikssonS, LundquistA, GustafsonY, Lundin-OlssonL (2009) Comparison of three statistical methods for analysis of fall predictors in people with dementia: Negative binomial regression (NBR), regression tree (RT), and partial least squares regression (PLSR). Arch Gerontol Geriatr49, 383–389.
22.
AkarachantachoteN, ChadchamS, SaithanuK (2014) Cutoff threshold of variable importance in projection for variable selection. Int J Pure Appl Math94, 307–322.
23.
MaillardP, SeshadriS, BeiserA, HimaliJJ, AuR, FletcherE, CarmichaelO, WolfPA, DecarliC (2012) Effects of systolic blood pressure on white-matter integrity in young adults in the Framingham Heart Study: A cross-sectional study. Lancet Neurol11, 1039–1047.
24.
PaseMP, HimaliJJ, MitchellGF, BeiserA, MaillardP, TsaoC, LarsonMG, DeCarliC, VasanRS, SeshadriS (2016) Association of aortic stiffness with cognition and brain aging in young and middle-aged adults. Hypertension67, 513–519.
25.
PrinsND, ScheltensP (2015) White matter hyperintensities, cognitive impairment and dementia: An update. Nat Rev Neurol11, 157–165.
26.
HanJW, MaillardP, HarveyD, FletcherE, MartinezO, JohnsonDK, OlichneyJM, FariasST, VilleneuveS, JagustW, MungasD, DeCarliC (2020) Association of vascular brain injury, neurodegeneration, amyloid, and cognitive trajectory. Neurology95, e2622–e2634.
27.
BeckD, de LangeAMG, PedersenML, AlnæsD, MaximovII, VoldsbekkI, RichardG, SandersAM, UlrichsenKM, DørumES, KolskårKK, HøgestølEA, SteenNE, DjurovicS, AndreassenOA, NordvikJE, KaufmannT, WestlyeLT (2022) Cardiometabolic risk factors associated with brain age and accelerate brain ageing. Hum Brain Mapp43, 700–720.
28.
WahlD, Solon-BietSM, CoggerVC, FontanaL, SimpsonSJ, Le CouteurDG, RibeiroRV (2019) Aging, lifestyle and dementia. Neurobiol Dis130, 104481.
29.
JackCR, WisteHJ, TherneauTM, WeigandSD, KnopmanDS, MielkeMM, LoweVJ, VemuriP, MachuldaMM, SchwarzCG, GunterJL, SenjemML, Graff-RadfordJ, JonesDT, RobertsRO, RoccaWA, PetersenRC (2019) Associations of amyloid, tau, and neurodegeneration biomarker profiles with rates of memory decline among individuals without dementia. JAMA321, 2316–2325.
30.
OssenkoppeleR, SmithR, OhlssonT, StrandbergO, MattssonN, InselPS, PalmqvistS, HanssonO (2019) Associations between tau, Aβ, and cortical thickness with cognition in Alzheimer disease. Neurology92, e601–e612.
31.
TimmersT, OssenkoppeleR, VerfaillieSCJ, van der WeijdenCWJ, SlotRER, WesselmanLMP, WindhorstAD, WoltersEE, YaqubM, PrinsND, LammertsmaAA, ScheltensP, van der FlierWM, van BerckelBNM (2019) Amyloid PET and cognitive decline in cognitively normal individuals: The SCIENCe project. Neurobiol Aging79, 50–58.
32.
LittlejohnsTJ, HollidayJ, GibsonLM, GarrattS, OesingmannN, Alfaro-AlmagroF, BellJD, BoultwoodC, CollinsR, ConroyMC, CrabtreeN, DohertyN, FrangiAF, HarveyNC, LeesonP, MillerKL, NeubauerS, PetersenSE, SellorsJ, SheardS, SmithSM, SudlowCLM, MatthewsPM, AllenNE (2020) The UK Biobank imaging enhancement of 100,000 participants: Rationale, data collection, management and future directions. Nat Commun11, 2624.
33.
SudlowC, GallacherJ, AllenN, BeralV, BurtonP, DaneshJ, DowneyP, ElliottP, GreenJ, LandrayM, LiuB, MatthewsP, OngG, PellJ, SilmanA, YoungA, SprosenT, PeakmanT, CollinsR (2015) UK Biobank: An open access resource for identifying the causes of a wide range of complex diseases of middle and old age. PLoS Med12, e1001779.
