Dynamically stabilized recurrent neural network optimized with Artificial Gorilla Troops espoused Alzheimer's...

Area of Science:

• Biomedical Engineering
• Computational Neuroscience
• Artificial Intelligence in Medicine

Background:

• Alzheimer's disease (AD) is a progressive neurological disorder impacting cognition, necessitating early detection for effective symptom management.
• The increasing demand for healthcare services highlights the need for automated diagnostic tools to assist clinicians and improve diagnostic efficiency.
• Electroencephalogram (EEG) signals offer a non-invasive method for brain activity monitoring, holding potential for early AD identification.

Purpose of the Study:

• To develop an automated computer diagnostic scheme for identifying Alzheimer's disease (AD) using Electroencephalogram (EEG) signals.
• To propose a novel deep learning model, Dynamically Stabilized Recurrent Neural Network Optimized with Artificial Gorilla Troops (DSRNN-AGTO-ADD), for enhanced AD detection.
• To evaluate the efficacy of the proposed model in improving diagnostic accuracy and reducing computational load compared to existing methods.

Main Methods:

• Preprocessing EEG signals using a Dynamic Context-Sensitive Filter (DCSF) to remove noise and interference.
• Feature extraction using Adaptive and Concise Empirical Wavelet Transform (ACEWT), incorporating signal characteristics like power, variance, and kurtosis.
• Classification of extracted features using a Dynamically Stabilized Recurrent Neural Network (DSRNN), optimized with the Artificial Gorilla Troops Optimization Algorithm (AGTOA).

Main Results:

• The DSRNN-AGTO-ADD approach demonstrated significant improvements in diagnostic performance.
• Achieved higher specificity (12.98%, 5.98%, 23.45%) and Receiver Operating Characteristic (ROC) scores (29.29%, 8.365%, 8.551%, 7.915%) compared to existing methods.
• Showcased reduced computation time (29.98%, 23.32%, 19.76%), indicating computational efficiency.

Conclusions:

• The proposed DSRNN-AGTO-ADD algorithm presents a promising automated tool for accurate and efficient Alzheimer's disease diagnosis from EEG signals.
• The integration of advanced signal processing and optimization techniques enhances the diagnostic capabilities for neurological disorders.
• This research contributes to the development of AI-driven healthcare solutions for early disease detection and management.