A recent study published in Neurology has developed an AI tool to improve diagnostics accuracy in Alzheimer’s disease and related dementias. The results showed that AIDD identified the two diseases with high accuracy, suggesting it could be a promising future tool for clinicians.
“The use of AI and advanced imaging technology holds considerable promise to uncover brain degeneration patterns for dementia,” said Dr David Vaillancourt, professor at UF Department of Applied Physiology & Kinesiology in the College of Health and Human Performance. Vaillancourt worked alongside Dr Angelos Barmpoutis, professor in the UF College of the Arts’ Digital Worlds Institute; and Dr Robin Chen, a postdoctoral student in the J. Crayton Pruitt Family Department of Biomedical Engineering.
How AIDD could prevent misdiagnosis
Researchers developed a tool called Automated Imaging Differentiation of Dementia (AIDD). It combines brain scans with AI to distinguish between two common forms of dementia: Alzheimer’s disease and dementia with Lewy bodies.
The two forms of dementia present differently. In Lewy body patients, dementia often begins with attention, alertness and movement issues. Meanwhile, Alzheimer’s patients may demonstrate memory problems. The two forms of dementia do not follow the same courses of treatment.
Despite their differences, Alzheimer’s and dementia with Lewy bodies clinicians frequently confuse the two. Up to 50% of patients living with dementia with Lewy bodies could be misdiagnosed as having Alzheimer’s. Misdiagnosis can lead to treatments that worsen cognitive and motor functions.
Currently, diagnosis methods comprise a mix of evaluations, testing and brain scans. In the study, three University of Florida researchers built the tool by analysing brain scans of dementia patients.
“To ensure the highest standards of reliability, we performed extensive validation experiments using data collected from multiple scanners and imaging centres,” said Barmpoutis.
About the research
In the study, researchers analysed 519 brain scans from patients with Alzheimer’s, dementia with Lewy bodies and no disease (control group), collected from January 2007 to March 2022 at multiple research data centres. From this group, researchers used a subset of 387 scans (129 Alzheimer’s, 129 dementia with Lewy bodies, 129 controls) to train and test the AI model. Researchers used 80% of the scans to train the machine, and the remaining 20% to test it.
The scans used a specialised MRI technique that measures extra fluid in the brain, often signalling brain cell damage and inflammation. AI analysed these subtle water-movement patterns in the brain, allowing for more accurate identification of each disease. Across multiple brain scan comparisons, the tool demonstrated strong performance.
To further test the system, researchers applied the tool to a separate group of 13 patients whose diagnoses were confirmed after death through autopsy. The tool correctly identified all 13 cases.
“Since the therapies for Alzheimer’s disease and dementia with Lewy bodies differ, developing precision biomarkers will offer better outcomes for patients,” Vaillancourt said. Early intervention and precise treatment is becoming increasingly crucial, as Alzheimer’s disease and related dementias are expected to more than double by 2060.
