Measuring consciousness from brainwaves to detect Alzheimer's disease using machine learning

What is it about?

Alzheimer’s disease affects memory and awareness, and doctors need better ways to detect it early. This study uses brainwave recordings (EEG) from people with and without Alzheimer’s to measure how conscious they are while resting. A theory called Integrated Information Theory helps turn these brain signals into a value (called Phi) that reflects how connected and aware the brain is. By comparing these values between healthy individuals and Alzheimer’s patients, and analyzing them with machine learning models, we were able to identify patterns that signal the disease. Our method outperformed earlier attempts, suggesting that measuring brain activity in this way could offer a more comfortable and non-invasive tool for early diagnosis.

Featured Image

Photo by julien Tromeur on Unsplash

Photo by julien Tromeur on Unsplash

Why is it important?

This research offers a new way to detect Alzheimer’s disease by focusing on consciousness, a key aspect of brain function that is often overlooked in traditional diagnosis. By combining a modern theory of consciousness with brainwave analysis and machine learning, the study goes beyond standard cognitive tests or signal processing techniques. It proposes a non-invasive, stress-free method suitable for elderly patients, which is especially important because conventional tests can be uncomfortable or difficult for people with dementia. As Alzheimer's is increasingly understood as a disorder of consciousness, this timely work may open the door to more accurate, early-stage diagnosis and personalized care strategies.

Perspectives