Alzheimer’s disease and related dementias are expected to more than double by 2060. As June marks Alzheimer’s and Brain Awareness Month, three University of Florida researchers are working to improve clinicians’ ability to distinguish these diseases—a critical step toward early diagnosis and better outcomes.
In a recent study published in Neurology, researchers developed a new tool called Automated Imaging Differentiation for Dementia, or AIDD. The tool combines brain scans with artificial intelligence to distinguish between two common forms of dementia: Alzheimer’s disease dementia and dementia with Lewy bodies. The results showed that AIDD identified the two diseases with almost perfect accuracy, suggesting that it could be a promising future tool for clinicians.
“The use of artificial intelligence and advanced imaging technology holds promise for revealing patterns of brain degeneration in dementia,” said David Vaillancourt, Ph.D., Distinguished Professor and the Orchid Endowed Chair for the UF Department of Applied Physiology & Kinesiology in the College of Health and Human Performance.
While both conditions are forms of dementia, they can present differently. For example, dementia with Lewy bodies often begins with problems with attention, alertness, and movement, while Alzheimer’s patients present with memory problems. Unlike Alzheimer’s disease, dementia with Lewy bodies requires different treatment.
Unfortunately, the two diseases are often confused, with up to 50% of patients living with dementia with Lewy bodies misdiagnosed as having Alzheimer’s. Today’s diagnostic methods rely on a mix of assessments, tests and brain scans rather than a single definitive test. In some cases, misdiagnosis can lead to treatments that worsen cognitive and motor functions.
To build this tool, the researchers analyzed 519 brain scans from patients with Alzheimer’s, dementia with Lewy bodies and no disease (a control group), collected from January 2007 to March 2022 at several research data centers. From this group, a subset of 387 scans (129 Alzheimer’s, 129 dementia with Lewy bodies, 129 controls) was used to train and test the AI model. Eighty percent of the scans were used to train the machine, while the remaining 20% were used to test it.
“To ensure the highest standards of reliability, we performed extensive validation experiments using data collected from multiple scanners and imaging centers,” said Angelos Barboutis, Ph.D., a professor in the UF College of the Arts’ Digital Worlds Institute, who worked on the study with Vaillancourt and Robin Chen, Ph.D., Ph.D., Ph.D. Engineering.
The scans used a specialized MRI technique that measures extra fluid in the brain, often signaling brain cell damage and inflammation. These subtle patterns of water movement in the brain were analyzed with AI, allowing for more accurate identification of each disease. In several brain scan comparisons, the tool showed strong performance. To further test the system, the researchers applied the tool to a separate group of 13 patients whose diagnoses were confirmed postmortem through autopsy. The tool correctly identified all 13 cases.
“Since the treatments for Alzheimer’s disease and dementia with Lewy bodies differ, the development of precision biomarkers will provide better outcomes for patients,” Vaillancourt said.
