Scientists at Örebro University in Sweden have developed two new AI models that can differentiate between healthy individuals and patients with dementia, including Alzheimer’s disease.
These models are capable of analysing the brain’s electrical activity to interpret electroencephalogram (EEG) signals for diagnostic purposes.
Go deeper with GlobalData
Discover B2B Marketing That Performs
Combine business intelligence and editorial excellence to reach engaged professionals across 36 leading media platforms.
In one study, ‘An explainable and efficient deep learning framework for EEG-based diagnosis of Alzheimer’s disease and frontotemporal dementia’, the researchers combined temporal convolutional networks and long short-term memory (LSTM) for analysing the signals.
The method distinguishes between Alzheimer’s, frontotemporal dementia, and healthy individuals with an accuracy of more than 80%.
Additionally, the researchers used an explanatory AI technique to show which parts of the EEG signal affect the diagnosis.
Örebro University informatics researcher Muhammad Hanif said: “Early diagnosis is crucial in order to be able to take proactive measures that slow down the progression of the disease and improve the patient’s quality of life.
US Tariffs are shifting - will you react or anticipate?
Don’t let policy changes catch you off guard. Stay proactive with real-time data and expert analysis.
By GlobalData“Traditional machine learning models often lack transparency and are challenged by privacy concerns. Our study aims to address both issues.”
A second study from the research team introduced a small AI model, under one megabyte in size, that preserves patient privacy.
The study is titled ‘Privacy–preserving dementia classification from EEG via hybrid–fusion EEGNetv4 and federated learning’.
Using federated learning, healthcare providers can partner to train the AI system without sharing patient data.
This model achieved an accuracy of over 97% in dementia classification.
The AI models interpret EEG signals by dividing them into alpha, beta, and gamma wave frequency bands, enabling the detection of patterns related to dementia.
The algorithms identify long-term changes and small differences between diagnoses, and the explainable AI technology provides transparency in decision-making.
Örebro University conducted the studies in collaboration with international institutions, including universities in the UK, Australia, Pakistan, and Saudi Arabia.
