Can AI detect cognitive impairment before it progresses to Alzheimer's?

Can AI detect cognitive impairment before it progresses to Alzheimer's? ...

Alzheimer''s disease is the main cause of dementia globally. Although there is no cure, early detection is considered crucial to being able to develop effective treatments that act before its development is irreversible.

A study conducted by scientists at the University of Catalunya (UOC) has successfully identified people who are stable with dementia and those who willprogress to having Alzheimer''s. The new technique, which is used by specific artificial intelligence techniques to study magnetic resonance images, is more effective than other methods currently being used.

Fine-tuning the diagnosis

Alzheimer''s disease affects over 50 million people worldwide, and the ageing of the population means that there may be many more patients in the future decades. While it is usually developed without any symptoms over many years, it is usually preceded by a mild cognitive impairment, which is much less severe than it is expected for someone from their age. "These patients may progress and worsen or remain in the same condition as time passes," says Mona Ashtari-Majlan, a UOC researcher at the AIWELL group, which

Identifying these cases appropriately might improve the quality of clinical trials used to perform diagnostic treatments, which increasingly seek to identify the initial stages of the disease. To do so, researchers developed a multi-stream convolutional neural network, which is a technique that is well-known for image recognition and classification.

"We first compared MRIs from Alzheimer''s patients and healthy people to discover clear landmarks," Ashtari-Majlan said. After developing the system, researchers fine-tuned the proposed architecture with resonance images from individuals who had already been diagnosed with severe cognitive impairment with significantly less differences. In total, nearly 700 images from publicly available datasets were used.

The process, according to Ashtari-Majlan, "overcomes the complexity of learning caused by the subtle structural changes that occur between the two forms of mild cognitive impairment, which are much smaller than those between a normal brain and a brain affected by the disease." Additionally, the proposed technique might address the small sample size issue, where the number of MRIs for mild cognitive impairment cases is decreased than for Alzheimer''s."

The new technique allows the two forms of mild cognitive impairment to be distinguished and classified with an accuracy rate of 85%. "Our evaluation criteria show that our proposed method outperforms existing ones," she said, implying that even when combined with biomarkers such as age and cognitive tests, this technique will "aide professionals to further expand the research."

You may also like: