To text this article to a friend,[SMS]Tap
Researchers at the University of Florida have developed a new artificial intelligence tool to help doctors more accurately distinguish between Alzheimer’s disease and Lewy body dementia, which are often confused during diagnosis.
The tool, called Automated Imaging Differentiation for Dementia (AIDD), uses advanced MRI brain scans and AI to analyze subtle patterns of water movement in the brain. These patterns can signal brain cell damage or inflammation, helping researchers identify signs associated with different forms of dementia.
The findings were published in a recent study in the journal Neurology. The researchers said that AIDD was able to distinguish between Alzheimer’s disease dementia and Lewy body dementia with near-perfect accuracy.
“The use of AI and advanced imaging techniques has great potential to reveal patterns of brain degeneration in dementia,” said David Vaillancourt, Ph.D., Distinguished Professor and Orchid Endowed Chair in the Department of Applied Physiology and Kinesiology at the University of California Health and Human Performance College.
The study comes as Alzheimer’s disease and related dementias are expected to more than double by 2060. June is also Alzheimer’s Disease and Brain Awareness Month, which brings even more attention to the need for earlier and more accurate diagnosis.
Alzheimer’s disease and Lewy body dementia are both types of dementia, but they often affect patients differently. Lewy body dementia can begin with problems with attention, alertness, and movement, while Alzheimer’s disease is more commonly associated with memory loss.
It is important to distinguish between the two conditions as they require different treatment approaches. Up to 50 percent of patients with Lewy body dementia are misdiagnosed as having Alzheimer’s disease, according to UF researchers. In some cases, incorrect diagnosis can lead to treatments that worsen cognitive and motor symptoms.
The late actor Robin Williams was diagnosed with Parkinson’s disease, but an autopsy later revealed he had diffuse Lewy body disease/Lewy body dementia. His widow, Susan Schneider Williams, said the disease helped explain the symptoms he experienced near the end of his life, including anxiety, paranoia, sleep problems, cognitive changes, hallucinations and movement disorders. Lewy body dementia is often confused with symptoms associated with Alzheimer’s disease and Parkinson’s disease, as symptoms can overlap. It can affect thinking, movement, mood, attention, sleep, and perception. Johns Hopkins University points out that Lewy bodies are usually only definitively identified after an autopsy.
To develop AIDD, researchers looked at 519 brain scans of people with Alzheimer’s disease, Lewy body dementia, and controls without the disease. Scans were collected from multiple research data centers between January 2007 and March 2022.
A subset of 387 scans, including 129 Alzheimer’s disease cases, 129 Lewy body dementia cases, and 129 control cases, was used to train and test the AI model. The researchers used 80% of these scans to train the system and the remaining 20% for testing.
“To ensure the highest standards of reliability, we conducted extensive validation experiments using data collected from multiple scanners and imaging centers,” said Dr. Angelos Burnputis, professor in the Digital World Institute at the University of Florida College of Art.
Barmpoutis worked on the research with Vaillancourt and Dr. Robin Chen, a postdoctoral fellow in the J. Crayton Pruitt Family Department of Biomedical Engineering.
The MRI scans used in the study measured excess fluid in the brain, which can be associated with brain cell damage and inflammation. By analyzing these patterns through AI, researchers are now able to more accurately identify disease-specific differences.
The researchers also tested the tool on another group of 13 patients whose diagnosis was later confirmed by autopsy. AIDD correctly identified all 13 cases.
“The treatments for Alzheimer’s disease and Lewy body dementia are different, so developing highly accurate biomarkers will lead to better outcomes for patients,” Vaillancourt said.
Source: Alisha Katz, Director of Communications, College of Health and Human Performance, University of Florida.
