University of Florida researchers have developed an AI-powered diagnostic tool that can distinguish between Alzheimer's disease and dementia with Lewy bodies with near-perfect accuracy.
The tool, called Automated Imaging Differentiation for Dementia (AIDD), combines advanced MRI imaging with artificial intelligence to identify disease-specific brain changes.
Researchers say the technology could reduce misdiagnoses, improve treatment decisions, and help clinicians provide earlier, more precise care as dementia cases continue to rise.
Baby boomers, America’s largest generation, are getting older and doctors are bracing for a significant increase in dementia-related diseases. To help meet that challenge, researchers at the University of Florida have unveiled a new artificial intelligence-based tool designed to help physicians more accurately diagnose two of the most commonly confused forms of the disease.
The tool is called Automated Imaging Differentiation for Dementia, or AIDD. It uses specialized MRI scans and artificial intelligence algorithms to distinguish between Alzheimer's disease and dementia with Lewy bodies, conditions that often present similar symptoms but require different treatment approaches. Researchers reported that the technology achieved near-perfect accuracy in identifying the two diseases during testing.
The development comes at a critical time. Alzheimer's disease and related dementias are expected to more than double by 2060, increasing the need for faster and more accurate diagnostic methods. Early diagnosis can help patients access appropriate treatments sooner and avoid therapies that may be ineffective—or even harmful—for the wrong condition.
"AI and advanced imaging technology hold significant promise for identifying patterns of brain degeneration associated with dementia," said David Vaillancourt, a distinguished professor in the University of Florida's Department of Applied Physiology and Kinesiology and one of the study's lead researchers.
Significant differences
Although both Alzheimer's disease and dementia with Lewy bodies cause cognitive decline, they often affect patients differently. Alzheimer's typically begins with memory impairment, while dementia with Lewy bodies is more likely to cause problems with attention, alertness, movement and visual hallucinations. Researchers estimate that up to half of patients with dementia with Lewy bodies are initially misdiagnosed with Alzheimer's disease.
To develop AIDD, the research team analyzed 519 brain scans collected from patients with Alzheimer's disease, dementia with Lewy bodies and healthy control participants. A subset of 387 scans was used to train and test the AI system. The model learned to recognize subtle differences in brain tissue by analyzing MRI measurements of excess fluid in the brain, a potential indicator of cell damage and inflammation.
Researchers said the system underwent extensive validation using data gathered from multiple imaging centers and MRI scanners to ensure reliability. The tool also was tested on a separate group of 13 patients whose diagnoses had been confirmed through autopsy. According to the researchers, AIDD correctly identified every case.
While additional research will be needed before the technology becomes widely available in clinical settings, the findings suggest AI-assisted imaging could become an important tool in dementia care. Researchers believe more precise diagnosis will help clinicians match patients with the most effective treatments and improve long-term outcomes.