Alzheimer's disease (AD) affects 55 million people worldwide, projected to reach 139 million by 2050; yet, most machine learning (ML)-based AD classifiers have been developed in Non-Hispanic White (NHW) cohorts, limiting generalizability.
Objective
Assess ethnic differences in AD prediction using classification performance and feature importance derived from multimodal neuroimaging biomarkers across African American (AA), Hispanic, and NHW participants.
Methods
Support vector machine classifiers were applied to multimodal neuroimaging data from a multi-ethnic cohort, incorporating structural magnetic resonance imaging measures, diffusion tensor imaging metrics, and positron emission tomography-based amyloid and tau measures. Models classified cognitively unimpaired (CU) versus cognitively impaired (CI) individuals and mild cognitive impairment (MCI) versus AD dementia, with and without adjustment for age, sex, and education.
Results
Classification performance varied by ethnicity and disease stage. NHW participants showed the strongest overall performance, particularly for CU versus CI, while Hispanic participants demonstrated high sensitivity and balanced performance for MCI versus AD. AA participants exhibited lower AUC and accuracy across tasks but maintained high negative predictive value. Demographic adjustment improved performance primarily for AA and NHW participants. Feature importance analyses revealed shared and population-specific patterns: tau positron emission tomography (PET) measures, especially posterior cingulate and lateral parietal standardized uptake value ratios, consistently ranked highest for CU versus CI across groups, whereas MCI versus AD classification diverged, with amyloid PET predominating in AA participants, tau PET in NHW participants, and mixed medial temporal atrophy and white matter signatures in Hispanics.
Conclusions
Shared early AD neuroimaging signatures exist across ethnic groups, but biomarker importance diverges at later disease stages, underscoring the need for ethnicity-aware ML models to improve prediction and equitable clinical translation.
Alzheimer's Disease International. World Alzheimer Report 2023: Reducing Dementia Risk: Never too early, never too late. London: Alzheimer's Disease International, 2023.
HallJRJohnsonLAZhangF, et al.Using fractional anisotropy imaging to detect mild cognitive impairment and Alzheimer's disease among Mexican Americans and non-Hispanic whites: a HABLE study. Dement Geriatr Cogn Disord2021; 50: 266–273.
4.
ZhangXXTianYWangZT, et al.The epidemiology of Alzheimer’s disease modifiable risk factors and prevention. J Prev Alzheimers Dis2021; 8: 313–321.
BarkhofFPolvikoskiTMvan StraatenEC, et al.The significance of medial temporal lobe atrophy: a postmortem MRI study in the very old. Neurology2007; 69: 1521–1527.
7.
van de PolLAHenselABarkhofF, et al.Hippocampal atrophy in Alzheimer disease: age matters. Neurology2006; 66: 236–238.
8.
BraakHBraakE. Neuropathological stageing of Alzheimer-related changes. Acta Neuropathol1991; 82: 239–259.
9.
BraakHAlafuzoffIArzbergerT, et al.Staging of Alzheimer disease-associated neurofibrillary pathology using paraffin sections and immunocytochemistry. Acta Neuropathol2006; 112: 389–404.
10.
ZhangFPetersenMJohnsonL, et al.Recursive support vector machine biomarker selection for Alzheimer’s disease. J Alzheimers Dis2021; 79: 1691–1700.
CristianiniNShawe-TaylorJ. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods. Cambridge: Cambridge University Press, 2000.
13.
VapnikVN. An overview of statistical learning theory. IEEE Trans Neural Netw1999; 10: 988–999.
14.
El-SappaghSAlonsoJMIslamSMR, et al.A multilayer multimodal detection and prediction model based on explainable artificial intelligence for Alzheimer's disease. Sci Rep2021; 11: 2660.
15.
KodamPSai SwaroopRPradhanSS, et al.Integrated multi-omics analysis of Alzheimer's disease shows molecular signatures associated with disease progression and potential therapeutic targets. Sci Rep2023; 13: 3695.
16.
AlatranyASKhanWHussainA, et al.An explainable machine learning approach for Alzheimer's disease classification. Sci Rep2024; 14: 2637.
17.
MolnarC. Interpretable Machine Learning: A Guide for Making Black Box Models Explainable. 2nd ed. Victoria, BC, Canada: Independently published, 2022.
18.
BogdanovicBEftimovTSimjanoskaM. In-depth insights into Alzheimer's disease by using explainable machine learning approach. Sci Rep2022; 12: 6508.
19.
ZhangFPetersenMJohnsonL, et al.Comorbidities incorporated to improve prediction for prevalent mild cognitive impairment and Alzheimer’s disease in the HABS-HD study. J Alzheimers Dis2023; 96: 1529–1546.
20.
PetersenMEZhangFHallJR, et al.Characterization of Ptau181 among a diverse community-based cohort: a HABS-HD study. J Alzheimers Dis2024; 100: S63–S73.
21.
O'BryantSEZhangFPetersenM, et al.Proteomic profiles of neurodegeneration among Mexican Americans and non-Hispanic whites in the HABS-HD study. J Alzheimers Dis2022; 86: 1243–1254.
22.
O'BryantSEPetersenMHallJR, et al.Plasma biomarkers of Alzheimer's disease are associated with physical functioning outcomes among cognitively normal adults in the multiethnic HABS-HD cohort. J Gerontol A Biol Sci Med Sci2023; 78: 9–15.
23.
O'BryantSEPetersenMHallJ, et al.Metabolic factors are related to brain amyloid among Mexican Americans: a HABS-HD study. J Alzheimers Dis2022; 86: 1745–1750.
24.
O'BryantSEPetersenMHallJ, et al.APOEε4 genotype is related to brain amyloid among Mexican Americans in the HABS-HD study. Front Neurol2022; 13: 834685.
25.
Molina-HenryDPRamanRLiuA, et al.Racial and ethnic differences in plasma biomarker eligibility for a preclinical Alzheimer's disease trial. Alzheimers Dement2024; 20: 3827–3838.
26.
PetersenMEZhouZHallJR, et al.Health and Aging Brain Study-Health Disparities (HABS-HD) methods and partner characteristics. Alzheimers Dement (N Y)2025; 11: e70140.
27.
PetersenMEZhangFHallJ, et al.Characterization of plasma AT(N) biomarkers among a racial and ethnically diverse community-based cohort: an HABS-HD study. Alzheimers Dement (N Y)2025; 11: e70045.
28.
O'BryantSELacritzLHHallJ, et al.Validation of the new interpretive guidelines for the clinical dementia rating scale sum of boxes score in the national Alzheimer's coordinating center database. Arch Neurol2010; 67: 746–749.
DesikanRSSégonneFFischlB, et al.An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest. Neuroimage2006; 31: 968–980.
31.
FischlB. Freesurfer. Neuroimage2012; 62: 774–781.
32.
MoriSOishiKFariaAV. White matter atlases based on diffusion tensor imaging. Curr Opin Neurol2009; 22: 362–369.
33.
BreimanL. Statistical modeling: the two cultures. Stat Sci2001; 16: 199–215.
34.
LundbergSMLeeS-I. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst2017; 30: 4765–4774.
35.
LundbergSMErionGChenH, et al.From local explanations to global understanding with explainable AI for trees. Nat Mach Intell2020; 2: 56–67.
36.
BeheshtiIDemirelHMatsudaH. Classification of Alzheimer's disease and prediction of mild cognitive impairment-to-Alzheimer's conversion from structural magnetic resource imaging using feature ranking and a genetic algorithm. Comput Biol Med2017; 83: 109–119.
37.
MárquezFYassaMA. Neuroimaging biomarkers for Alzheimer's disease. Mol Neurodegener2019; 14: 21.
38.
ZhangFPetersenMJohnsonL, et al.Accelerating hyperparameter tuning in machine learning for Alzheimer's disease with high performance computing. Front Artif Intell2021; 4: 798962.
39.
OssenkoppeleRSchonhautDRSchöllM, et al.Tau PET patterns mirror clinical and neuroanatomical variability in Alzheimer’s disease. Brain2016; 139: 1551–1567.
40.
MaassALandauSBakerSL, et al.Comparison of multiple tau-PET measures as biomarkers in aging and Alzheimer's disease. Neuroimage2017; 157: 448–463.
41.
BucknerRLSnyderAZShannonBJ, et al.Molecular, structural, and functional characterization of Alzheimer's disease: evidence for a relationship between default activity, amyloid, and memory. J Neurosci2005; 25: 7709–7717.
42.
LagardeJOlivieriPToniettoM, et al.Could tau-PET imaging contribute to a better understanding of the different patterns of clinical progression in Alzheimer's disease? A 2-year longitudinal study. Alzheimers Res Ther2023; 15: 91.
43.
MalpettiMRathoreSIaccarinoL, et al.Regional tau PET patterns predict prospective domain-specific cognitive decline in early symptomatic Alzheimer's disease. Alzheimers Res Ther2025; 17: 220.
44.
AbuwardaHTrainerAHorienC, et al.Whole-brain functional connectivity predicts regional tau PET in preclinical Alzheimer’s disease. Brain Commu2025; 7: fcaf274.
45.
FigleyCRUddinMNWongK, et al.Potential pitfalls of using fractional anisotropy, axial diffusivity, and radial diffusivity as biomarkers of cerebral white matter microstructure. Front Neurosci2021; 15: 799576.
46.
Acosta-CabroneroJAlleySWilliamsGB, et al.Diffusion tensor metrics as biomarkers in Alzheimer's disease. PLoS One2012; 7: e49072.
47.
SextonCEKaluUGFilippiniN, et al.A meta-analysis of diffusion tensor imaging in mild cognitive impairment and Alzheimer's disease. Neurobiol Aging2011; 32: 2322.e2325–2322.e2318.
48.
PlancheVManjonJVMansencalB, et al.Structural progression of Alzheimer's disease over decades: the MRI staging scheme. Brain Commun2022; 4: fcac109.
49.
SmithAD. Imaging the progression of Alzheimer pathology through the brain. Proc Natl Acad Sci U S A2002; 99: 4135–4137.
50.
Ramos Bernardes da Silva FilhoSOliveira BarbosaJHRondinoniC, et al.Neuro-degeneration profile of Alzheimer's patients: a brain morphometry study. Neuroimage Clin2017; 15: 15–24.
51.
CauncaMRBahorikAJiangX, et al.Neuroimaging markers of dementia across race/ethnicity and sex/gender using an intersectional approach within the HABS-HD cohort. Alzheimers Dement2025; 21: e70733.
52.
MohriMRostamizadehATalwalkarA. Foundations of Machine Learning. Cambridge, MA: The MIT Press, 2012.
53.
StrumbeljEKononenkoI. An efficient explanation of individual classifications using game theory. J Mach Learn Res2010; 11: 1–18.
54.
RibeiroMTSinghSGuestrinC. “Why should i trust you?” Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, 2016, pp.1135–1144.
55.
GuyonIElisseeffA. An introduction to variable and feature selection. J Mach Learn Res2003; 3: 1157–1182.
