Skip to content
Member Login
Blood Pathology Lab혈액병리 연구실

EEG and machine learning for dementia screening

We use resting-state EEG, neuropsychological tests and machine learning to tell healthy ageing, mild cognitive impairment and Alzheimer's disease apart.

Resting-state EEG is quick, inexpensive and needs no injection, which makes it a candidate for screening older adults for cognitive decline. We record quantitative EEG (qEEG) with eyes open and eyes closed and look for patterns that separate stages of the Alzheimer's disease continuum: power in different frequency bands, time-frequency features, EEG microstates, and which scalp regions matter most to a classifier.

We also apply machine learning to standard neuropsychological tests, such as the Rey Complex Figure and the Trail-Making Test, and compare algorithms for predicting cognitive impairment. Some studies link these measures to other evidence, for example qEEG ratios to plasma amyloid-β oligomer levels, and test scores to grey matter volume. Related work measures gait and balance in Parkinson's disease.

Key methods

  • Resting-state qEEG, eyes open and eyes closed
  • Spectral, time-frequency and microstate analysis
  • Machine learning and deep learning classifiers
  • Neuropsychological tests (Rey Complex Figure, Trail-Making Test)
  • Gait and Timed Up and Go measures

Related publications

  1. Chanda Simfukwe, Seong Soo A. An, Young Chul Youn

    Resting-State EEG Microstate Dynamics as Neurophysiological Biomarkers Across the Alzheimer’s Disease Continuum: A Systematic Review

    Diagnostics 16(18):3019 (2026)

    DOIPubMed

  2. Chanda Simfukwe, Seong Soo A. An, Young Chul Youn

    EEG Microstate Alterations in Eyes-Open and Eyes-Closed Resting States Across the Alzheimer’s Disease Continuum

    Journal of Clinical Medicine 15(15):5863 (2026)

    DOIPubMed

  3. Danyeong Kim, Minji Son, Jeanhong Jeon, Da-Eun Jeong, Hyun Kyung Yi, Min Ju Kang

    Quantitative Analysis of Timed Up and Go Metrics Across Parkinson’s Disease Severity and Their Clinical Correlations

    Diagnostics 16(14):2283 (2026)

    DOIPubMed

  4. Chanda Simfukwe, Seong Soo A. An, Young Chul Youn

    Associations Between Trail-Making Test Black and White Performance and Gray Matter Volume in Community-Dwelling Cognitively Healthy Adults Aged 40 to 80 Years

    Journal of Clinical Medicine 14(12):4041 (2025)

    DOIPubMedPDF

  5. Chanda Simfukwe, Seong Soo A. An, Young Chul Youn

    Difference between eyes-open and eyes-closed resting state quantitative electroencephalography (qEEG) for predicting cognitive impairment using deep learning

    Applied Neuropsychology Adult:1–11 (2025)

    DOIPubMed

  6. Chanda Simfukwe, Seong Soo A. An, Young Chul Youn

    Investigating Gamma Frequency Band PSD in Alzheimer’s Disease Using qEEG from Eyes-Open and Eyes-Closed Resting States

    Journal of Clinical Medicine 14(12):4256 (2025)

    DOIPubMedPDF

  7. Chanda Simfukwe, Seong Soo A. An, Young Chul Youn

    Time-Frequency Domain Analysis of Quantitative Electroencephalography as a Biomarker for Dementia

    Diagnostics 15(12):1509 (2025)

    DOIPubMedPDF

  8. Danyeong Kim, Da-Eun Jeong, Hyunkyung Yi, Min Ju Kang

    Gait Patterns and Balance Impairment in Parkinson’s Disease With Correlation to Disease Severity

    Dementia and Neurocognitive Disorders 24(4):259 (2025)

    DOIPubMedPDF

  9. Chanda Simfukwe, Seong Soo A. An, Young Chul Youn

    Contribution of Scalp Regions to Machine Learning-Based Classification of Dementia Utilizing Resting-State qEEG Signals

    Neuropsychiatric Disease and Treatment Volume 20:2375–2389 (2024)

    DOIPubMedPDF

  10. Chanda Simfukwe, Seong Soo A. An, Young Chul Youn

    Comparison of machine learning algorithms for predicting cognitive impairment using neuropsychological tests

    Applied Neuropsychology Adult 33(3):696–707 (2024)

    DOIPubMed

  11. Chanda Simfukwe, Su‐Hyun Han, Ho Tae Jeong, Young Chul Youn

    qEEG as Biomarker for Alzheimer’s Disease: Investigating Relative PSD Difference and Coherence Analysis

    Neuropsychiatric Disease and Treatment Volume 19:2423–2437 (2023)

    DOIPubMedPDF

  12. Chanda Simfukwe, Young Chul Youn, Minjae Kim, Joonki Paik, Su‐Hyun Han

    CNN for a Regression Machine Learning Algorithm for Predicting Cognitive Impairment Using qEEG

    Neuropsychiatric Disease and Treatment Volume 19:851–863 (2023)

    DOIPubMedPDF

  13. Chanda Simfukwe, Young Chul Youn, Ho Tae Jeong

    A machine-learning algorithm for predicting brain age using Rey–Osterrieth complex figure tests of healthy participants

    Applied Neuropsychology Adult 32(1):225–230 (2023)

    DOIPubMed

  14. Chanda Simfukwe, Reeree Lee, Young Chul Youn, Alzheimer’s Disease and Related Dementias in Zambia (ADDIZ) Group

    Classification of Aβ State From Brain Amyloid PET Images Using Machine Learning Algorithm

    Dementia and Neurocognitive Disorders 22(2):61 (2023)

    DOIPubMedPDF

  15. Chanda Simfukwe, Reeree Lee, Young Chul Youn

    Prediction of Aβ State from Brain Amyloid PET Images Using Machine Learning Algorithm

    Alzheimer s & Dementia 18(S7) (2022)

    DOIPDF

  16. Chanda Simfukwe, SangYun Kim, Seong Soo A. An, Young Chul Youn, Clinical Research Center for Dementia of South Korea (CREDOS) Study

    Neuropsychological test using machine learning for cognitive impairment screening

    Applied Neuropsychology Adult 31(5):825–830 (2022)

    DOIPubMed

  17. Chanda Simfukwe, Young Chul Youn

    Prediction of East Asian Brain Age using Machine Learning Algorithms Trained With Community-based Healthy Brain MRI

    Dementia and Neurocognitive Disorders 21(4):138 (2022)

    DOIPubMed

  18. Chanda Simfukwe, Seong Soo A. An, Young Chul Youn

    Comparison of RCF Scoring System to Clinical Decision for the Rey Complex Figure Using Machine-Learning Algorithm

    Dementia and Neurocognitive Disorders 20(4):70 (2021)

    DOIPubMed