Researchers at Stony Brook University are working to improve early detection of Alzheimer’s disease using artificial intelligence. Shan Lin, associate professor of Electrical and Computer Engineering, and PhD candidate Heming Fu, in collaboration with Guoliang Xing from The Chinese University of Hong Kong, have developed a generative AI framework called SHADE-AD (Synthesizing Human Activity Datasets Embedded with AD features). This system creates synthetic data that mirrors the motor behaviors seen in patients with Alzheimer’s.
Alzheimer’s currently affects nearly seven million Americans over the age of 65, a number expected to almost double by 2060. Early diagnosis and ongoing monitoring are important for improving patient care and maintaining independence. However, there is a shortage of high-quality, Alzheimer’s-specific data available to train AI systems for this purpose.
SHADE-AD addresses this gap by generating three-dimensional “skeleton videos” that capture detailed joint motion patterns specific to Alzheimer’s patients. These synthetic datasets were validated against real-world patient data. According to researchers, SHADE-AD was able to reproduce subtle differences in speed, angle, and range of motion that distinguish movements associated with Alzheimer’s from those of healthy older adults.
The findings were presented at the 23rd ACM Conference on Embedded Networked Sensor Systems (SenSys 2025). Activity recognition systems trained with SHADE-AD data showed improved accuracy compared to those trained on more generic datasets. In particular, the system performed well at recognizing actions such as walking and standing up—activities where early signs of decline often appear.
“If we can provide tools that spot these changes before they become severe, patients will have more options, and families will have more time to plan,” Lin said.
With September designated as Healthy Aging Month in the United States, Lin emphasized the broader goal of supporting older adults through technology: “Healthy aging isn’t only about treating illness, but also about creating systems that allow people to thrive as they grow older,” he said. “AI can be a powerful ally in that mission.”