The Internet of Medical Things (IoMT) is poised to play a pivotal role in future medical support systems, enabling pervasive health monitoring in smart cities. Alzheimer's disease (AD) afflicts millions globally, and this paper explores the potential of electroencephalogram (EEG) data in addressing this challenge. We propose the Convolutional Learning Attention-Bidirectional Time-Aware Long-Short-Term Memory (CL-ATBiLSTM) model, a deep learning approach designed to classify different AD phases through EEG data analysis. The model utilizes Discrete Wavelet Transform (DWT) to decompose EEG data into distinct frequency bands, allowing for targeted analysis of AD-related brain activity patterns. Additionally, the data is segmented into smaller windows to handle the dynamic nature of EEG signals, and these segments are transformed into spectrogram images, visually depicting brain activity distribution over time and frequency. The CL-ATBiLSTM model incorporates convolutional layers to capture spatial features, attention mechanisms to emphasize crucial data, and BiLSTM networks to explore temporal relationships within the sequences. To optimize the model's performance, Bayesian optimization is employed to fine-tune the hyperparameters of the ATBiLSTM network, enhancing its ability to generalize and accurately classify AD stages. Incorporating Bayesian learning ensures the most effective model configuration, improving sensitivity and specificity for identifying AD-related patterns. Our model extracts discriminative features from EEG data to differentiate between AD, Mild Cognitive Impairment (MCI), and healthy controls (CO), offering a more comprehensive approach than existing two-class detection algorithms. By including the MCI category, our method facilitates earlier identification and potentially more impactful therapy interventions. Achieving a 96.52% accuracy on Figshare datasets containing AD, MCI, and CO groups, our approach demonstrates strong potential for practical use, accelerating AD identification, enhancing patient care, and contributing to the development of targeted treatments for this debilitating condition.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11522596PMC
http://dx.doi.org/10.1038/s41598-024-77876-8DOI Listing

Publication Analysis

Top Keywords

eeg data
16
convolutional learning
8
eeg signals
8
cl-atbilstm model
8
brain activity
8
eeg
6
data
6
model
5
fusing convolutional
4
learning
4

Similar Publications

Unlabelled: Phenylalanine (PA) levels below 360 µmol/L do not require treatment; however, cognitive deficits have been observed in patients with elevated PA levels, necessitating a safe upper limit for treatment and therapeutic objectives. The main purpose of this study is to evaluate the correlation between developmental assessments (Denver Developmental Screening Test-II [DDST-II] and Ankara Developmental Screening Inventory [ADSI]) and electroencephalogram (EEG) findings with blood PA levels and genotypic data in non-phenylketonuria mild Hyperphenylalaninemia (HPA) patients, to re-evaluate their treatment status based on potential adverse outcomes. This study encompassed 40 patients aged 1-5 years diagnosed with HPA and not on treatment, identified through initial blood PA levels, and monitored for a minimum of 1 year on an unrestricted diet.

View Article and Find Full Text PDF

Exposure to organophosphorus nerve agents irreversibly inhibits acetylcholinesterase and may lead to cholinergic crisis and seizures. Although benzodiazepines are the standard of care after nerve agent-induced status epilepticus, when treatment is delayed for up to 30 min or more, refractory status epilepticus can develop. Adult male rodents are often utilized for evaluation of therapeutic efficacy against nerve agent exposure.

View Article and Find Full Text PDF

Perceiving emotions in the eyes: the biasing role of a fearful mouth.

Biol Psychol

December 2024

Research Center of Brain and Cognitive Neuroscience, Liaoning Normal University, Dalian 116029, China; Key laboratory of Brain and Cognitive Neuroscience, Liaoning Province, Dalian 116029, China. Electronic address:

The role of the eye region in interpersonal communication and emotional recognition is widely acknowledged. However, the influence of mouth expression on perceiving and recognizing genuine emotions in the eye region, especially with limited attentional resources, remains unclear. Thirty-four participants in this study completed a dual-target rapid serial visual presentation (RSVP) task while their event-related potential (ERP) data were simultaneously recorded.

View Article and Find Full Text PDF

Theta-Gamma Decoupling - A neurophysiological marker of impaired reward processing in Parkinson's disease.

Brain Res

December 2024

Human Motor Neurophysiology and Neuromodulation Lab, Department of Biosciences and Bioengineering, Indian Institute of Technology Bombay, India. Electronic address:

Individuals with Parkinson's disease (PD) exhibit altered reward processing, reflected by a decreased amplitude of an event-related potential (ERP) marker called reward positivity (RewP). Most studies have used RewP to investigate reward behavior due to the high temporal resolution of EEG and its high sensitivity. However, traditional single-electrode ERP analyses often overlook the intricate dynamics of non-phase-locked oscillatory activity and the complex interactions within these neural oscillatory patterns.

View Article and Find Full Text PDF

Objective: Alzheimer's disease (AD) and frontotemporal dementia (FTD) are prevalent neurodegenerative diseases characterized by altered brain functional connectivity (FC), affecting over 100 million people worldwide. This study aims to identify distinct FC patterns as potential biomarkers for differential diagnosis.

Methods: Resting-state EEG data from 36 AD patients, 23 FTD patients, and 29 healthy controls were analyzed using time-frequency and bandpass filtering FC metrics.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!