Our memory reflects the health of our brain and is often lost in old age, mainly due to dementia.
Dementia is primarily caused by a decline in brain function that affects memory, thinking, language and behavior.
A group of symptoms that affect social abilities to cope with daily life can vary across different categories.
Dementia can be classified into four main types, including Alzheimer’s disease, vascular disease, dementia with Lewy bodies, and frontotemporal dementia.
With the help of latest technological advancements, scientists have developed new AI models that can help detect dementia accurately so that it can be better treated before its time.
A group of researchers from Orebro University has developed two new AI models capable of analyzing the electrical activity of the brain and accurately distinguishing healthy individuals from patients with dementia, particularly Alzheimer’s disease.
Scientists believe that early diagnosis could be useful in medical science.
Muhammad Hanif, a computer science researcher at Orebro University, said that “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.”
In the new study titled An explainable and efficient deep learning framework for EEG-based diagnosis of Alzheimer’s disease and frontotemporal dementia, researchers combined two advanced AI methods.
“Traditional machine learning models often lack transparency and face privacy concerns. Our study aims to address both of these issues,” says Hanif.
Method 1 was named TCN “temporal convolutional networks” and the other method was described as “long-term and short-term memory” LSTM networks, to analyze EEG signals, a system that can determine whether a person is sick or healthy.
Researchers have successfully interpreted the brain’s electrical signals.
According to the results, Alzheimer’s disease, frontotemporal dementia, the method achieved an accuracy of more than 80%.
By dividing EEG signals into different frequency bands – alpha, beta and gamma waves – AI can identify patterns linked to dementia.
New AI algorithms can detect long-term changes in signals and recognize subtle differences between diagnoses.
In addition to this, the explainable technology shows how AI can become a fast, inexpensive and privacy-friendly tool for early diagnosis of dementia.
The researchers concluded that EEG electroencephalography is already a simple and inexpensive method used for primary care and that by combining it with AI models it can be used as a new potential for wider use in healthcare, from specialist clinics to new home tests.
Hanif, a researcher at Orebro University, informed that the research team is continuously striving to explore more AI methods to improve the efficiency and accuracy of medical diagnosis of this common disease.
“We plan to continue the research by expanding to larger and more diverse datasets, exploring more EEG features, 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,” Hanif explained.
