Mild cognitive impairment prediction and cognitive score regression in the elderly using EEG topological data analysis and machine learning with awareness assessed in affective reminiscent paradigm

Tomasz M Rutkowski; Tomasz Komendziński; Mihoko Otake-Matsuura

doi:10.3389/fnagi.2023.1294139

Mild cognitive impairment prediction and cognitive score regression in the elderly using EEG topological data analysis and machine learning with awareness assessed in affective reminiscent paradigm

Front Aging Neurosci. 2024 Jan 4:15:1294139. doi: 10.3389/fnagi.2023.1294139. eCollection 2023.

Authors

Tomasz M Rutkowski^{1

2

3}, Tomasz Komendziński³, Mihoko Otake-Matsuura¹

Affiliations

¹ RIKEN Center for Advanced Intelligence Project, Tokyo, Japan.
² Graduate School of Education, The University of Tokyo, Tokyo, Japan.
³ Department of Cognitive Science, Institute of Information and Communication Research, Nicolaus Copernicus University, Toruń, Poland.

Abstract

Introduction: The main objective of this study is to evaluate working memory and determine EEG biomarkers that can assist in the field of health neuroscience. Our ultimate goal is to utilize this approach to predict the early signs of mild cognitive impairment (MCI) in healthy elderly individuals, which could potentially lead to dementia. The advancements in health neuroscience research have revealed that affective reminiscence stimulation is an effective method for developing EEG-based neuro-biomarkers that can detect the signs of MCI.

Methods: We use topological data analysis (TDA) on multivariate EEG data to extract features that can be used for unsupervised clustering, subsequent machine learning-based classification, and cognitive score regression. We perform EEG experiments to evaluate conscious awareness in affective reminiscent photography settings.

Results: We use EEG and interior photography to distinguish between healthy cognitive aging and MCI. Our clustering UMAP and random forest application accurately predict MCI stage and MoCA scores.

Discussion: Our team has successfully implemented TDA feature extraction, MCI classification, and an initial regression of MoCA scores. However, our study has certain limitations due to a small sample size of only 23 participants and an unbalanced class distribution. To enhance the accuracy and validity of our results, future research should focus on expanding the sample size, ensuring gender balance, and extending the study to a cross-cultural context.

Keywords: EEG; biomarker; machine learning (ML); mild cognitive impairment (MCI); prevention; topological data analysis (TDA).

Grants and funding

The author(s) declare financial support was received for the research, authorship, and/or publication of this article. MO-M was supported in part by the JSPS KAKENHI (Grant Numbers: JP19K14489, JP18KT0035, JP19H01138, JP20H05022, JP20H05574, JP22H04872, and JP22H00544) and the Japan Science and Technology Agency (Grant Numbers: JPMJST2168, JPMJPF2101, and JPMJMS2237). MO-M and TR were partly supported by the Japan Science and Technology Agency AIP Trilateral AI Research Grant No. JPMJCR20G1 from the Japan Science and Technology Agency. TR received support from Nicolaus Copernicus University in Toruń, Poland, through the 61/2022 Mobility Grant. TK received support from Nicolaus Copernicus University's Emerging Field projects Cognition and Language 2022 and Culture, Development & Wellbeing in Toruń, Poland.