Restricted accessResearch articleFirst published online 2026
Estimating cognitive function score from mild cognitive impairment to moderate dementia using a hybrid model combining plasma biomarkers with electroencephalogram signal
Predicting cognitive function across dementia stages remains challenging. Plasma biomarkers and electroencephalogram (EEG) features may provide complementary information, but their combined predictive value requires further study.
Objective
To evaluate the feasibility of integrating plasma biomarkers and EEG features to predict cognitive function in dementia and examine their correlations.
Methods
From September 2023 to October 2024, 75 patients from two medical centers with mild cognitive impairment, mild dementia, or moderate dementia were enrolled. Resting-state 19-channel EEG data yielded 2737 time-frequency and connectivity features. Plasma biomarkers included tau, p-Tau181, Aβ1−42, neurofilament light chain (NfL), brain-derived neurotrophic factor, apolipoprotein E genotype, and glial fibrillary acidic protein. Cognitive function was assessed using Cognitive Abilities Screening Instrument (CASI), Mini-Mental State Examination, Montreal Cognitive Assessment (MoCA), and Clinical Dementia Rating Sum of Boxes. Machine learning models were developed using plasma-only, EEG-only, and hybrid approaches.
Results
NfL was negatively correlated with CASI (t = −2.059, p < 0.05). Several EEG features showed moderate correlations with cognitive measures and plasma biomarkers, with delta-band relative power between left frontal and temporal regions (F7–FT7) showing the strongest correlation with MoCA. The hybrid model achieved the best performance, with R2 > 0.74 across all cognitive measures, outperforming plasma-only and EEG-only models.
Conclusions
Integrating EEG features with plasma biomarkers improves prediction of cognitive function from mild cognitive impairment to moderate dementia, pending external validation.
CassaniREstarellasMSan-MartinR, et al.Systematic review on resting-state EEG for Alzheimer's disease diagnosis and progression assessment. Dis Markers2018; 2018: 5174815.
3.
GoodmanRALochnerKAThambisettyM, et al.Prevalence of dementia subtypes in United States medicare fee-for-service beneficiaries, 2011–2013. Alzheimers Dement2017; 13: 28–37.
4.
PalmqvistSTidemanPMattsson-CarlgrenN, et al.Blood biomarkers to detect Alzheimer disease in primary care and secondary care. JAMA2024; 332: 1245–1257.
5.
ManlyJJJonesRNLangaKM, et al.Estimating the prevalence of dementia and mild cognitive impairment in the US: the 2016 health and retirement study harmonized cognitive assessment protocol project. JAMA Neurol2022; 79: 1242–1249.
6.
BradfordAKunikMESchulzP, et al.Missed and delayed diagnosis of dementia in primary care: prevalence and contributing factors. Alzheimer Dis Assoc Disord2009; 23: 306–314.
7.
AlberdiAAztiriaABasarabA. On the early diagnosis of Alzheimer's disease from multimodal signals: a survey. Artif Intell Med2016; 71: 1–29.
8.
Zabala-FindlayAPennyLKLofthouseRA, et al.Utility of blood-based tau biomarkers for mild cognitive impairment and Alzheimer's disease: systematic review and meta-analysis. Cells2023; 12: 1090.
9.
SahraiHNorouziAHamzehzadehS, et al.SIMOA-based analysis of plasma neurofilament light levels in MCI and AD patients: a systematic review and meta-analysis. BMC Neurol2023; 23: 331.
10.
NgTKSHoCSHTamWWS, et al.Decreased serum brain-derived neurotrophic factor levels in patients with Alzheimer's disease: a systematic review and meta-analysis. Int J Mol Sci2019; 20: 257.
11.
KimKYShinKYChangKA. GFAP As a potential biomarker for Alzheimer's disease: a systematic review and meta-analysis. Cells2023; 12: 1215.
12.
MonllorPCervera-FerriALloretMA, et al.Electroencephalography as a non-invasive biomarker of Alzheimer's disease: a forgotten candidate to substitute CSF molecules?Int J Mol Sci2021; 22: 10341.
13.
Livint PopaLDragosHMStrilciucS, et al.Added value of QEEG for the differential diagnosis of common forms of dementia. Clin EEG Neurosci2021; 52: 201–210.
14.
AzamiHMirjaliliMRajjiTK, et al.Electroencephalogram and event-related potential in mild cognitive impairment: recent developments in signal processing, machine learning, and deep learning. IEEE J Sel Areas Sensors2025; 2: 162–184.
15.
MartinTGiordaniBKavcicV. EEG Asymmetry and cognitive testing in MCI identification. Int J Psychophysiol2022; 177: 213–219.
16.
SekerMOzerdemMS. Dementia rhythms: unveiling the EEG dynamics for MCI detection through spectral and synchrony neuromarkers. J Neurosci Methods2024; 409: 110216.
17.
ChenCCHsuCYChiuHW, et al.Frequency power and coherence of electroencephalography are correlated with the severity of Alzheimer's disease: a multicenter analysis in Taiwan. J Formos Med Assoc2015; 114: 729–735.
18.
FruehwirtWDorffnerGRobertsS, et al.Associations of event-related brain potentials and Alzheimer's disease severity: a longitudinal study. Prog Neuropsychopharmacol Biol Psychiatry2019; 92: 31–38.
19.
GarnHWaserMDeistlerM, et al.Quantitative EEG markers relate to Alzheimer's disease severity in the prospective dementia registry Austria (PRODEM). Clin Neurophysiol2015; 126: 505–513.
20.
KhatunSMorshedBIBidelmanGM. Monitoring disease severity of mild cognitive impairment from single-channel EEG data using regression analysis. Sensors (Basel)2024; 24: 1145.
21.
JiaoBLiRZhouH, et al.Neural biomarker diagnosis and prediction to mild cognitive impairment and Alzheimer's disease using EEG technology. Alzheimers Res Ther2023; 15: 32.
22.
American Psychiatric Association. Diagnostic and statistical manual of mental disorders. 5th ed. Arlington, VA: American Psychiatric Publishing, 2013.
23.
World Health Organization. ICD-10: international statistical classification of diseases and related health problems. 2nd ed. Geneva: World Health Organization, 2004.
24.
WilliamsMMStorandtMRoeCM, et al.Progression of Alzheimer's disease as measured by clinical dementia rating sum of boxes scores. Alzheimers Dement2013; 9: S39–S44.
25.
TengELHasegawaKHommaA, et al.The cognitive abilities screening instrument (CASI): a practical test for cross-cultural epidemiological studies of dementia. Int Psychogeriatr1994; 6: 45–58.
26.
FolsteinMFFolsteinSEMcHughPR. Mini-mental state: a practical method for grading the cognitive state of patients for the clinician. J Psychiatr Res1975; 12: 189–198.
27.
NasreddineZSPhillipsNABedirianV, et al.The Montreal cognitive assessment, MoCA: a brief screening tool for mild cognitive impairment. J Am Geriatr Soc2005; 53: 695–699.
28.
CedarbaumJMJarosMHernandezC, et al.Rationale for use of the clinical dementia rating sum of boxes as a primary outcome measure for Alzheimer's disease clinical trials. Alzheimers Dement2013; 9: S45–S55.
NystromAHughesJ. Leveraging sparsity to speed up polynomial feature expansions of CSR matrices using K-simplex numbers. arXiv 2018; arXiv:1803.06418.
31.
BuziGFornariCPerinelliA, et al.Functional connectivity changes in mild cognitive impairment: a meta-analysis of M/EEG studies. Clin Neurophysiol2023; 156: 183–195.
32.
Garcia-EscobarGManeroRMFernandez-LebreroA, et al.Blood biomarkers of Alzheimer's disease and cognition: a literature review. Biomolecules2024; 14: 72.
33.
LiuMZhangJAdeliE, et al.Joint classification and regression via deep multi-task multi-channel learning for Alzheimer's disease diagnosis. IEEE Trans Biomed Eng2019; 66: 1195–1206.
34.
ClevertDAUnterthinerTHochreiterS. Fast and accurate deep network learning by exponential linear units. arXiv 2015; arXiv:1511.07289.
35.
HollensteinNRenggliCGlausB, et al.Decoding EEG brain activity for multi-modal natural language processing. Front Hum Neurosci2021; 15: 659410.
36.
MohammadFAl MansoorKM. SLA-MLP: enhancing sleep stage analysis from EEG signals using multilayer perceptron networks. Diagnostics (Basel)2024; 14: 2594.
37.
SrivastavaNHintonGKrizhevskyA, et al.Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res2014; 15: 1929–1958.
38.
KuhnMJohnsonK. Applied predictive modeling. New York: Springer, 2013.
39.
HastieTTibshiraniRFriedmanJ. The elements of statistical learning. 2nd ed. New York: Springer, 2009.
40.
NugrohoWHHandoyoSHsiehHC, et al.Modeling multioutput response using ridge regression and MLP neural network with tuning hyperparameters through cross-validation. Int J Adv Comput Sci Appl2022; 13: 777–787.
41.
BreimanL. Random forests. Mach Learn2001; 45: 5–32.
ChenSXuDLiS, et al.Monitoring soil organic carbon using vis-NIR spectroscopy and multilayer perceptron. Land Degrad Dev2020; 31: 1026–1038.
44.
DauphinotVCalviSMoutetC, et al.Reliability of the assessment of the clinical dementia rating scale from medical records compared with the reference method. Alzheimers Res Ther2024; 16: 198.
45.
NyuntMSChongMSLimWS, et al.Reliability and validity of the clinical dementia rating for community-living elderly subjects without an informant. Dement Geriatr Cogn Dis Extra2013; 3: 407–416.
46.
WojdalaALBellomoGGaetaniL, et al.Trajectories of CSF and plasma biomarkers across the Alzheimer's disease continuum. Neurobiol Dis2023; 189: 106356.
47.
DongYHouTLiY, et al.Plasma amyloid-beta, total tau, and neurofilament light chain across the Alzheimer's disease clinical spectrum. J Alzheimers Dis2023; 96: 845–858.
48.
RiemenschneiderMWagenpfeilSDiehlJ, et al.Tau and Abeta42 protein in CSF of patients with frontotemporal degeneration. Neurology2002; 58: 1622–1628.
49.
GrangeonLPaquetCBomboisS, et al.Differential diagnosis of dementia with high levels of cerebrospinal fluid tau protein. J Alzheimers Dis2016; 51: 905–913.
50.
TherriaultJSchindlerSESalvadoG, et al.Biomarker-based staging of Alzheimer disease: rationale and clinical applications. Nat Rev Neurol2024; 20: 232–244.
51.
DhauriaMMondalRDebS, et al.Blood-based biomarkers in Alzheimer's disease. Int J Mol Sci2024; 25: 10890.
52.
JackCRJrWisteHJAlgeciras-SchimnichA, et al.Predicting amyloid PET and tau PET stages with plasma biomarkers. Brain2023; 146: 2029–2044.
53.
IbarraRRadanovicMPaisMV, et al.AD-related CSF biomarkers across distinct levels of cognitive impairment. J Geriatr Psychiatry Neurol2021; 34: 659–667.
54.
ChouliarasLThomasAMalpettiM, et al.Differential plasma biomarkers in Lewy body dementia, Alzheimer's disease, and frontotemporal dementia. J Neurol Neurosurg Psychiatry2022; 93: 651–658.
55.
GiustinianiADanesinLBozzettoB, et al.Functional changes in brain oscillations in dementia: a review. Rev Neurosci2023; 34: 25–47.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
