Machine learning approach for early onset dementia neurobiomarker using EEG network topology features

Tomasz M Rutkowski; Masato S Abe; Tomasz Komendzinski; Hikaru Sugimoto; Stanislaw Narebski; Mihoko Otake-Matsuura

doi:10.3389/fnhum.2023.1155194

Machine learning approach for early onset dementia neurobiomarker using EEG network topology features

Front Hum Neurosci. 2023 Jun 16:17:1155194. doi: 10.3389/fnhum.2023.1155194. eCollection 2023.

Authors

Tomasz M Rutkowski^{1

2

3}, Masato S Abe^{1

4}, Tomasz Komendzinski³, Hikaru Sugimoto¹, Stanislaw Narebski³, Mihoko Otake-Matsuura¹

Affiliations

¹ RIKEN Center for Advanced Intelligence Project, Tokyo, Japan.
² The University of Tokyo, Tokyo, Japan.
³ Nicolaus Copernicus University, Toruń, Poland.
⁴ Doshisha University, Kyoto, Japan.

Abstract

Introduction: Modern neurotechnology research employing state-of-the-art machine learning algorithms within the so-called "AI for social good" domain contributes to improving the well-being of individuals with a disability. Using digital health technologies, home-based self-diagnostics, or cognitive decline managing approaches with neuro-biomarker feedback may be helpful for older adults to remain independent and improve their wellbeing. We report research results on early-onset dementia neuro-biomarkers to scrutinize cognitive-behavioral intervention management and digital non-pharmacological therapies.

Methods: We present an empirical task in the EEG-based passive brain-computer interface application framework to assess working memory decline for forecasting a mild cognitive impairment. The EEG responses are analyzed in a framework of a network neuroscience technique applied to EEG time series for evaluation and to confirm the initial hypothesis of possible ML application modeling mild cognitive impairment prediction.

Results: We report findings from a pilot study group in Poland for a cognitive decline prediction. We utilize two emotional working memory tasks by analyzing EEG responses to facial emotions reproduced in short videos. A reminiscent interior image oddball task is also employed to validate the proposed methodology further.

Discussion: The proposed three experimental tasks in the current pilot study showcase the critical utilization of artificial intelligence for early-onset dementia prognosis in older adults.

Keywords: EEG; artificial intelligence; biomarker; dementia; machine learning; mild cognitive impairment; network neuroscience; prevention.

Grants and funding

MO-M was supported in part by the JSPS KAKENHI (Grant Numbers: JP18KT0035, JP19H01138, JP20H05022, JP20H05574, JP22H04872, and JP22H00544) and the Japan Science and Technology Agency (Grant Numbers: JPMJST2168, JPMJPF2101, and JPMJMS2237). MA was supported in part by the KAKENHI, the Japan Society for the Promotion of Science Grant No. JP18K18140. MO-M and TR were supported in part by the Japan Science and Technology Agency AIP Trilateral AI Research Grant No. JPMJCR20G1 from the Japan Science and Technology Agency. TR was supported by Nicolaus Copernicus University in Torun, Poland, Mobility Grant 2022 and 2023 Editions. HS was partly supported by the JSPS KAKENHI (Grant Number: JP19K14489).