Abstract
Early identification of cognitive decline in the elderly is essential for timely and effective intervention. Current neuroimaging and clinical biomarkers have largely focused on patients with mild cognitive impairment (MCI) and dementias, and though effective, have not been demonstrated to be sensitive to the earliest signs of functional abnormalities. The electroencephalogram (EEG), with a millisecond time base, allows a precise exploration of synaptic dysfunction even at the initial stages of the damage. This study introduces a novel non-invasive EEG-based biomarker to predict cognitive decline of participants showing only subjective cognitive impairment (SCI). Baseline EEG recordings from 88 SCI participants who had yearly assessment of cognitive changes and staging for 5–7 years were included for study. Quantitative EEG (qEEG) features were calculated from eyes closed resting surface EEG, including those reflecting broad band power spectra, connectivity, and complexity. Machine learning (ML) classifiers were trained on the qEEG features to estimate the likelihood of future progression to MCI or dementia. A feature selection pipeline optimized predictive accuracy of the ML algorithms while reducing the number of features. Prediction performance for the biomarker was over 80% in accuracy, with an area under the curve of 0.90. Independent validation on two external cohorts confirmed the biomarker’s robustness. Dominant contributors to the final locked models aligned with existing literature on neurodegenerative disorders. Features contributing most were those reflecting disruption in neuronal transmission (phase lag and asymmetry) with abnormalities in the alpha and theta frequency bands. Changes in measures of connectivity in the subjective cognitive impairment (SCI) population provide evidence of changes in neuronal transmission within frontal networks. These findings suggest that these EEG-based brain activity biomarkers are reflective of the earliest signs of brain dysfunction. The qEEG features contributing to the biomarkers reflect the underlying physiological mechanisms related to neurodegeneration. Furthermore, the non-invasive and cost-effective nature of EEG makes it a promising tool for clinical implementation, allowing for early risk assessment, disease monitoring, and intervention planning.
Data availability
The datasets analyzed during the current study are not publicly available under the signed data use agreements. Additional information may be available upon reasonable request from the corresponding author.
References
Gauthier, S., Rosa-Neto, P., Morais, J. A. & Webster, C. World Alzheimer Report 2021: Journey Through the Diagnosis of Dementia (Alzheimer’s Disease International, 2021).
Babiloni, C. et al. Hippocampal volume and cortical sources of EEG alpha rhythms in mild cognitive impairment and Alzheimer disease. NeuroImage 44(1), 123–135. https://doi.org/10.1016/j.neuroimage.2008.08.005 (2009).
Silva-Spínola, A. et al. Blood biomarkers in mild cognitive impairment patients: Relationship between analytes and progression to Alzheimer disease dementia. Eur. J. Neurol. 30(6), 1565–1573. https://doi.org/10.1111/ene.15762 (2023).
Nallapu, B. T., Petersen, K. K., Lipton, R. B., Davatzikos, C. & Ezzati, A. Plasma biomarkers as predictors of progression to dementia in individuals with mild cognitive impairment. J. Alzheimers Dis. 98(1), 231–246. https://doi.org/10.3233/JAD-230620 (2024).
Grueso, S. & Viejo-Sobera, R. Machine learning methods for predicting progression from mild cognitive impairment to Alzheimer’s disease dementia: A systematic review. Alzheimers Res. Ther. 13(1), 162. https://doi.org/10.1186/s13195-021-00900-w (2021).
Rossini, P. M. et al. Neurophysiological hallmarks of neurodegenerative cognitive decline: The study of brain connectivity as A biomarker of early dementia. J. Personalized Med. 10(2), 34. https://doi.org/10.3390/jpm10020034 (2020a).
Bazarian, J. J. et al. Validation of a machine learning brain electrical activity–based index to aid in diagnosing concussion among athletes. JAMA Netw. Open 4(2), e2037349. https://doi.org/10.1001/jamanetworkopen.2020.37349 (2021).
Hanley, D. et al. Emergency department triage of traumatic head injury using brain electrical activity biomarkers: A multisite prospective observational validation trial. Acad. Emerg. Med. 24(5), 617–627. https://doi.org/10.1111/acem.13175 (2017).
Livint Popa, L., Dragos, H., Pantelemon, C., Verisezan Rosu, O. & Strilciuc, S. The role of quantitative EEG in the diagnosis of neuropsychiatric disorders. J. Med. Life 13(1), 8–15 https://doi.org/10.25122/jml-2019-0085 (2020).
Babiloni, C. et al. Resting state cortical electroencephalographic rhythms are related to Gray matter volume in subjects with mild cognitive impairment and Alzheimer’s disease. Hum. Brain Mapp. 34(6), 1427–1446. https://doi.org/10.1002/hbm.22005 (2013).
Brueggen, K. et al. Early changes in alpha band power and DMN BOLD activity in Alzheimer’s disease: A simultaneous resting state EEG-fMRI study. Front. Aging Neurosci. 9, 319. https://doi.org/10.3389/fnagi.2017.00319 (2017).
Höller, Y. et al. Combining SPECT and quantitative EEG analysis for the automated differential diagnosis of disorders with amnestic symptoms. Front. Aging Neurosci. 9, 290. https://doi.org/10.3389/fnagi.2017.00290 (2017).
Moretti, D. V. et al. Specific EEG changes associated with atrophy of hippocampus in subjects with mild cognitive impairment and Alzheimer’s disease. Int. J. Alzheimers Dis. 2012, 253153. https://doi.org/10.1155/2012/253153 (2012).
Moretti, D. V., Prestia, A., Binetti, G., Zanetti, O. & Frisoni, G. B. Increase of theta frequency is associated with reduction in regional cerebral blood flow only in subjects with mild cognitive impairment with higher upper alpha/low alpha EEG frequency power ratio. Front. Behav. Neurosci. 7, 188. https://doi.org/10.3389/fnbeh.2013.00188 (2013).
Moretti, D. V. Theta and alpha EEG frequency interplay in subjects with mild cognitive impairment: Evidence from EEG, MRI, and SPECT brain modifications. FrontAging Neurosci. 20, 7:31. https://doi.org/10.3389/fnagi.2015.00031 (2015a).
Moretti, D. V. Conversion of mild cognitive impairment patients in Alzheimer’s disease: Prognostic value of Alpha3/Alpha2 electroencephalographic rhythms power ratio. Alzheimers Res. Ther. 7, 80. https://doi.org/10.1186/s13195-015-0162-x (2015b).
Moretti, D. V. et al. Cerebral PET glucose hypometabolism in subjects with mild cognitive impairment and higher EEG high-alpha/low-alpha frequency power ratio. Neurobiol. Aging 58, 213–224. https://doi.org/10.1016/j.neurobiolaging.2017.06.009 (2017).
Rossini, P. M. et al. Early diagnosis of Alzheimer’s disease: The role of biomarkers including advanced EEG signals analysis. Report from the IFCN-sponsored panel of experts. Clin. Neurophysiol. 131(6), 1287–1310. https://doi.org/10.1016/j.clinph.2020.03.003 (2020b).
Gaubert, S. et al. EEG evidence of compensatory mechanisms in preclinical Alzheimer’s disease. Brain 142(7), 2096–2112. https://doi.org/10.1093/brain/awz150 (2019).
Poil, S. S. et al. Integrative EEG biomarkers predict progression to Alzheimer’s disease at the MCI stage. Front. Aging Neurosci. 5, 58. https://doi.org/10.3389/fnagi.2013.00058 (2013).
Lizio, R. et al. Neurophysiological assessment of Alzheimer’s disease individuals by a single electroencephalographic marker. J. Alzheimers Dis. 49(1), 159–177. https://doi.org/10.3233/JAD-143042 (2016).
Prichep, L. S. et al. Prediction of longitudinal cognitive decline in normal elderly with subjective complaints using electrophysiological imaging. Neurobiol. Aging 27 (3), 471–481. https://doi.org/10.1016/j.neurobiolaging.2005.07.021 (2006).
Rossini, P. M., Miraglia, F. & Vecchio, F. Early dementia diagnosis, MCI-to-dementia risk prediction, and the role of machine learning methods for feature extraction from integrated biomarkers, in particular for EEG signal analysis. Alzheimers Dement. 18(12), 2699–2706. https://doi.org/10.1002/alz.12645 (2022).
Yener, G. et al. Treatment effects on event-related EEG potentials and oscillations in Alzheimer’s disease. Int. J. Psychophysiol. 177, 179–201. https://doi.org/10.1016/j.ijpsycho.2022.05.008 (2022).
Jiang, Y. et al. Parallel electrophysiological abnormalities due to COVID-19 infection and to Alzheimer’s disease and related dementia. Alzheimer’s Dement. 20, 7296–7319. https://doi.org/10.1002/alz.14089 (2024).
Reisberg, B. et al. The pre-mild cognitive impairment, subjective cognitive impairment stage of Alzheimer’s disease. Alzheimer Dement. 4 (1), S98–S108. https://doi.org/10.1016/j.jalz.2007.11.017 (2008).
Reisberg, B., Ferris, S. H., de Leon, M. J. & Crook, T. Global deterioration scale (GDS). Psychopharmacol. Bull. 24(4), 661–663 (1988).
Reisberg, B. & Ferris, S. H. Global deterioration scale (GDS), brief cognitive rating scale (BCRS) and functional assessment staging (FAST) measures: The GDS staging system. In American Psychiatric Association, editor. Handbook of Psychiatric Measures, 450–5 (American Psychiatric Association Task Force for the Handbook of Psychiatric Measures, Washington, 2000).
Folstein, M. F., Folstein, S. E. & McHugh, P. R. Mini-mental state. A practical method for grading the cognitive state of patients for the clinician. J. Psychiatr Res. 12(3), 189–198 (1975).
Shokouhi, S. & Albert, K. Subjective cognitive decline and biomarkers of preclinical Alzheimer’s disease. Curr. Behav. Neurosci. Rep. 6, 219–226. https://doi.org/10.1007/s40473-019-00191-4 (2019).
Prichep, L. S. et al. Classification of traumatic brain injury severity using informed data reduction in a series of binary classifier algorithms. IEEE Trans. Neural Syst. Rehabil Eng. 20(6), 806–822. https://doi.org/10.1109/TNSRE.2012.2206609 (2012).
Jacquin, A., Kanakia, S., Oberly, D. & Prichep, L. A multimodal biomarker for concussion identification, prognosis and management. Comput. Biol. Med. 102, 95–103 (2018).
Efron, B. & Tibshirani, R. Improvements on cross-validation: the 632 + bootstrap method. J. Am. Stat. Assoc. 92(438), 548–560 (1997).
Jiang, Y. et al. Memory-related frontal brainwaves predict transition to mild cognitive impairment in cognitively intact older individuals five years before diagnosis. J. Alzheimers Dis. 79(2), pp. https://doi.org/10.3233/JAD-200931 (2021). https://content.iospress.com/articles/journal-of-Alzheimers-disease/jad200931
Engedal, K. et al. The power of EEG to predict conversion from mild cognitive impairment and subjective cognitive decline to dementia. Dement. Geriatr. Cogn. Disord. 49(1), 38–47. https://doi.org/10.1159/000508392 (2020).
Vecchio, F. et al. Sustainable method for Alzheimer’s prediction in mild cognitive impairment: EEG connectivity and graph theory combined with ApoE. Ann. Neurol. 84(2), 302–314. https://doi.org/10.1002/ana.25289 (2018).
Babiloni, C. et al. Enriched Resting-State EEG biomarkers predict cognitive decline at 1-Year Follow-Up in old patients with prodromal Alzheimer’s disease: A combined Machine-Learning approach. SSRN Appeared Online January. 29. https://doi.org/10.2139/ssrn.4679495 (2024).
Lee, L. Y. et al. August. Robust and interpretable AI-guided marker for early dementia prediction in real-world clinical settings. eClinicalMedicine 74, 102725 (2024). https://doi.org/10.1016/j.eclinm.2024.102725
Höller, Y. et al. Prediction of cognitive decline in Temporal lobe epilepsy and mild cognitive impairment by EEG, MRI, and neuropsychology. Comput. Intell. Neurosci. 2020, 8915961. https://doi.org/10.1155/2020/8915961 (2020).
Acknowledgements
The NYU cohort was shared under a license agreement between NYU and BrainScope Company. The authors wish to acknowledge the past collaboration with the Silberstein Aging and Dementia Research Center at NYU School of Medicine where all clinical staging of the NYU cohort was collected under the direction of Dr. Barry Reisberg and Dr. Steven Ferris. Dr. Prichep wishes to acknowledge the original funding sources of the NYU School of Medicine database which was supported in part by NIH grants AG03051 and AG08051 from the National Institute of Aging and MH32577 from the National Institute of Mental Health, MO1 RR00096. We also acknowledge the technicians at the Brain Research Laboratories, NYUSOM, where the EEGs of the cohort were originally acquired. We gratefully acknowledge the participants and their families for their dedication to this longitudinal study. We also acknowledge Dr. Jiang (University of Kentucky) and Dr. Rossini (Neuroconnect) for the independent validation cohorts shared under a data use agreement with BrainScope Company. Dr Jiang acknowledges the funding sources for the UKY shared data from NIH K01AG000986, P50AG05144, R56AG060608-01 and P30AG072946, and by Oak Ridge National Laboratory, UT-Battelle LLC for the US Department of Energy DE-AC05-00OR22725.
Funding
This work was funded by the Alzheimer’s Drug Discovery Foundation (ADDF), # GC-202202-2022659.
Author information
Authors and Affiliations
Contributions
All authors reviewed the manuscript. L.P. and R.A.: Conception, and design of work, interpretation of data, draft of manuscript. S.Z., S.K. and B.L.: Analysis of data. S.Z. and R.A.: Creation of new software. K.B. and Y.J. : Draft and revision of manuscript. Y.J: Acquisition of data.
Corresponding author
Ethics declarations
Competing interests
Drs. Prichep, Zaidi, Liang and Ms. Kanakia were employees of BrainScope during the data analysis phase of this study. Drs. Brink and Armañanzas were consultant/advisors to BrainScope during the data analysis phase of this study. Data was collected through license and data use agreements with independent institutions. Dr. Jiang has no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Leslie S. Prichep is retired.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Prichep, L.S., Zaidi, S.N., Brink, K. et al. Derivation of an intrinsic brain activity biomarker for the earliest prediction of cognitive decline. Sci Rep (2026). https://doi.org/10.1038/s41598-026-35144-x
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-35144-x
