New AI model uses brainwave signals to detect dementia with high accuracy

Researchers at Örebro University have developed two new AI models that can analyze electrical activity in the brain and accurately distinguish between healthy people and patients with dementia, including Alzheimer’s disease.

Early diagnosis is very important in order to take proactive measures to slow the progression of the disease and improve the patient’s quality of life. ”

Mohammad Hanif, informatics researcher at Örebro University

in research An explainable and efficient deep learning framework for EEG-based diagnosis of Alzheimer’s disease and frontotemporal dementia, The researchers combined two advanced AI techniques: temporal convolution networks and LSTM networks. This program analyzes brainwave signals and can almost perfectly determine whether a person is sick or healthy.

Can distinguish between healthy and sick people 80% of the time

The method achieved more than 80% accuracy when comparing three groups: Alzheimer’s disease, frontotemporal dementia, and healthy controls. The researchers are also using interpretive AI techniques to show which parts of the EEG signal influence the diagnosis. This helps doctors interpret how the system reaches its conclusions.

In the second study, Privacy-preserving dementia classification from EEG using hybrid fusion EEGNetv4 and federated learningResearchers have developed a small, resource-efficient AI model less than 1 megabyte in size that also protects patient privacy. With the help of federated learning, multiple healthcare providers can collaborate to train AI systems without sharing patient data. Despite privacy protection, this model achieves more than 97% accuracy.

“Traditional machine learning models often lack transparency and suffer from privacy issues. Our research aims to address both issues,” said Mohammad Hanif, Associate Senior Lecturer in Informatics at Örebro University.

AI detects patterns in brain electrical signals

Researchers have successfully combined different methods of interpreting the brain’s electrical signals. By splitting the EEG signal into different frequency bands (alpha, beta, and gamma waves), AI can identify patterns associated with dementia. The algorithm can detect long-term changes in the signal and recognize subtle differences between diagnoses. Additionally, explainable AI technology ensures that systems are no longer “black boxes” and have a clear basis for decision-making.

In their study, researchers demonstrate how AI can become a fast, low-cost, and privacy-secure tool for early diagnosis of dementia. EEG is already an easy and inexpensive method for use in primary care. Combined with AI models that can run on portable devices, this opens up a wide range of possibilities for use in the medical field, from specialized clinics to future home tests.

AI testing can be used at home in the future

“Early diagnosis is essential to take proactive measures to slow the progression of the disease and improve quality of life. Once fully implemented, such solutions could ease the burden on all involved: patients, care staff, relatives and health professionals,” said Muhammad Hanif.

The study was carried out in collaboration with researchers from Örebro University and several international organizations, including universities in the UK, Australia, Pakistan and Saudi Arabia.

“We plan to continue our research by expanding to larger and more diverse datasets, investigating more brainwave features, and including other types of dementia such as vascular dementia and dementia with Lewy bodies. At the same time, we will use explainable AI and ensure strict protection of patient data,” explains Muhammad Hanif.