Comparison of EEG Preprocessing Techniques for Complexity Measures in Alzheimer's Disease Detection

Alzheimer's disease (AD) is a neurodegenerative condition characterized by memory loss, cognitive difficulties, and behavioral changes. Currently, there are no known permanent cure for this condition. Early and precise diagnosis is crucial for effective therapeutic intervention. This study introduces an unsupervised machine learning (ML)-based method for identifying patterns in electroencephalographic (EEG) signals from both healthy subjects and AD patients. Emphasis was placed on the preprocessing phase, examining the effects of various EEG data normalization techniques on the results. This generalized approach addresses the significant inter- and intra-subjective variability inherent in biological data, thereby enhancing method robustness and data consistency. Following the preprocessing phase, Multiscale Fuzzy Entropy (MFE) was derived from EEG signals. A k-means clustering algorithm was applied to identify distinct patterns. The efficacy of the clusters was assessed by using Silhouette Score (SS), Adjusted Rand Index Score (ARI), Adjusted Mutual Information Score (AMI) and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$V$</tex> -Measure Score. The method was validated using a public EEG dataset. The results indicated enhanced clustering efficacy when normalization was applied, underscoring the critical importance of data preprocessing in the detection of AD.