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

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).

Figure 1

Boxplots with marked median, quartile ranges, and whiskers extending to show the rest of the distributions (majority non-normal distributions), together with Wilcoxon rank-sums test p−values, U-statistics, common language effect sizes (CLES) (McGraw and Wong, 1992) and area under the ROC curve (AUC) (Hanley and McNeil, 1982) scores for TDA features, used in subsequent unsupervised clustering, classification and regression, in three experimental response settings of the oddball paradigm's target (TGT), ignored (IGN), and all (ALL) stimuli arranged in columns. The sample numbers in both subject groups are marked by n_healthy and n_MCI, respectively.

Figure 2

Unsupervised clustering (a machine learning training without class labels) scatter plots using UMAP (McInnes et al., 2018) in three experimental tasks and original data without any data augmentation.

Figure 3

The boxplot diagrams show the median, quartile, and 95−percentile ranges of LOOSCV-based MCI classification in (A, B), as well as MoCA regression results in (C–F). The chance level is set at 70% for classification results due to unequal class memberships (MCI vs. healthy). Accuracy is displayed in (A), while (B) shows f1−scores. Regression median errors for exact MoCA-score prediction are presented in (C), mean absolute percentage errors (MAPE) in (D), mean absolute errors (MAE) in (E), and mean squared errors (MSE) in (F).