A tensor decomposition scheme for EEG-based diagnosis of mild cognitive impairment
Related Experiment Video
Updated: Jul 2, 2025
Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke
Published on: July 14, 2023
Alireza Faghfouri1, Vahid Shalchyan1, Hamza Ghazanfar Toor2
1Neuroscience & Neuroengineering Research Lab, Biomedical Engineering Department, School of Electrical Engineering, Iran University of Science and Technology, Tehran, Iran.
Abstract:
Mild Cognitive Impairment (MCI) is the primary stage of acute Alzheimer's disease, and early detection is crucial for the person and those around him. It is difficult to recognize since this mild stage does not have clear clinical signs, and its symptoms are between normal aging and severe dementia. Here, we propose a tensor decomposition-based scheme for automatically diagnosing MCI using Electroencephalogram (EEG) signals. A new projection is proposed, which preserves the spatial information of the electrodes to construct a data tensor. Then, using parallel factor analysis (PARAFAC) tensor decomposition, the features are extracted, and a support vector machine (SVM) is used to discriminate MCI from normal subjects. The proposed scheme was tested on two different datasets. The results showed that the tensor-based method outperformed conventional methods in diagnosing MCI with an average classification accuracy of 93.96% and 78.65% for the first and second datasets, respectively. Therefore, it seems that maintaining the spatial topology of the signals plays a vital role in the processing of EEG signals.
Insights
This study introduces a novel tensor decomposition method for early Alzheimer's disease detection using electroencephalogram (EEG) signals. The new approach accurately identifies Mild Cognitive Impairment (MCI), outperforming traditional methods.
Area of Science:
- Neuroscience
- Biomedical Engineering
- Machine Learning
Background:
- Mild Cognitive Impairment (MCI) is an early stage of Alzheimer's disease, often difficult to diagnose due to subtle symptoms.
- Early detection of MCI is critical for timely intervention and management.
- Distinguishing MCI from normal aging and severe dementia requires sensitive diagnostic tools.
Purpose of the Study:
- To develop an automated scheme for diagnosing MCI using electroencephalogram (EEG) signals.
- To propose a novel tensor decomposition-based approach for enhanced MCI detection.
- To evaluate the effectiveness of preserving spatial information in EEG signal processing for MCI diagnosis.
Main Methods:
- A novel projection method was used to construct a data tensor from EEG signals, preserving electrode spatial information.
- Parallel Factor Analysis (PARAFAC) tensor decomposition was employed for feature extraction.
- A Support Vector Machine (SVM) classifier was utilized to differentiate between MCI patients and healthy subjects.
Main Results:
- The proposed tensor-based scheme achieved high classification accuracies of 93.96% and 78.65% on two independent datasets.
- The tensor method demonstrated superior performance compared to conventional approaches for MCI diagnosis.
- Preserving the spatial topology of EEG signals was identified as a crucial factor for accurate diagnosis.
Conclusions:
- Tensor decomposition of EEG signals offers a promising automated approach for early MCI detection.
- The proposed method highlights the importance of spatial information in EEG analysis for neurological disorders.
- This technique has the potential to improve the early diagnosis and management of Alzheimer's disease.
