Monitoring Disease Severity of Mild Cognitive Impairment from Single-Channel EEG Data Using Regression Analysis

Abstract

A deviation in the soundness of cognitive health is known as mild cognitive impairment (MCI), and it is important to monitor it early to prevent complicated diseases such as dementia, Alzheimer’s disease (AD), and Parkinson’s disease (PD). Traditionally, MCI severity is monitored with manual scoring using the Montreal Cognitive Assessment (MoCA). In this study, we propose a new MCI severity monitoring algorithm with regression analysis of extracted features of single-channel electro-encephalography (EEG) data by automatically generating severity scores equivalent to MoCA scores. We evaluated both multi-trial and single-trail analysis for the algorithm development. For multi-trial analysis, 590 features were extracted from the prominent event-related potential (ERP) points and corresponding time domain characteristics, and we utilized the lasso regression technique to select the best feature set. The 13 best features were used in the classical regression techniques: multivariate regression (MR), ensemble regression (ER), support vector regression (SVR), and ridge regression (RR). The best results were observed for ER with an RMSE of 1.6 and residual analysis. In single-trial analysis, we extracted a time–frequency plot image from each trial and fed it as an input to the constructed convolutional deep neural network (CNN). This deep CNN model resulted an RMSE of 2.76. To our knowledge, this is the first attempt to generate automated scores for MCI severity equivalent to MoCA from single-channel EEG data with multi-trial and single data.

ChatGPT and BCI-VR: a new integrated diagnostic and therapeutic perspective for the accurate diagnosis and personalized treatment of mild cognitive impairment

“…MCI serves as a critical transitional stage between normal aging and dementia. Diagnosis involves clinical observation (Rodriguez-Santiago et al, 2024 ), neuroimaging (Chouliaras and O'Brien, 2023 ), biomarkers (An et al, 2024 ; Carpi et al, 2024 ; Kim S. et al, 2024 ; Kim S. K. et al, 2024 ; Perneczky et al, 2024 ; Plassman et al, 2024 ; Wu et al, 2024 ; Zuo et al, 2024 ), and electroencephalography (EEG) (Amato et al, 2024 ; Faghfouri et al, 2024 ; Khatun et al, 2024 ; Rutkowski et al, 2024 ; Sun et al, 2024 ), as well as neuropsychological assessments.…”

Exploring the Relationship between Behavioral and Neurological Impairments Due to Mild Cognitive Impairment: Correlation Study between Virtual Kiosk Test and EEG-SSVEP

“…Although MRI allows for the quantitative assessment of brain structure, it could be considered invasive and less suitable for early aMCI screening due to the loud noise [16], potential thermal damage from high-frequency energy [17,18], and the risk of side effects from MRI contrast agents [19]. EEG, on the other hand, can monitor real-time changes in brain activity with temporal accuracy to observe responses to stimuli, albeit with sensitivity to noise [20][21][22][23][24][25]. While various diagnostic tools are employed in clinical settings, each tool presents distinct advantages and limitations.…”