A Novel Metric for Alzheimer's Disease Detection Based on Brain Complexity Analysis via Multiscale Fuzzy Entropy

Area of Science:

• Neuroscience
• Biomedical Engineering
• Medical Diagnostics

Background:

• Alzheimer's disease (AD) is a neurodegenerative disorder impacting memory and cognition.
• Current diagnostic methods for AD, like neuroimaging and cognitive tests, have limitations including cost, invasiveness, and subjectivity.
• Electroencephalography (EEG) offers a non-invasive, low-cost, high-temporal-resolution alternative for brain activity assessment.

Purpose of the Study:

• To introduce a novel metric, multiscale fuzzy entropy (MFE), for objective Alzheimer's disease detection using EEG.
• To develop and validate an EEG-based algorithm for assessing brain complexity abnormalities characteristic of AD.
• To provide clinicians with a cost-effective tool to aid in early AD intervention and patient care.

Main Methods:

• Investigated brain entropy patterns in different frequency bands using MFE for 35 healthy subjects (HS) and 35 AD patients.
• Developed a detection algorithm based on MFE values to identify AD-related brain complexity abnormalities.
• Validated the MFE-based algorithm on 24 EEG test recordings.

Main Results:

• The MFE-based method achieved 83% accuracy in differentiating between HS and AD patients.
• The algorithm demonstrated a diagnostic odds ratio of 25 and a Matthews correlation coefficient of 0.67.
• The method showed potential in identifying brain complexity anomalies in a subject with mild cognitive impairment (MCI).

Conclusions:

• Multiscale fuzzy entropy (MFE) analysis of EEG signals is a viable approach for Alzheimer's disease diagnosis.
• The developed MFE-based algorithm offers an objective and cost-effective tool for AD detection.
• Further research is warranted to explore the algorithm's potential for identifying MCI and its broader clinical application.