Predicting Alzheimer’s earlier

Could the way we speak - from subtle stutters to repeated words - reveal the earliest signs of Alzheimer's disease? Researchers and data scientists worldwide think so, and their quest for answers just led to a major win for the University of Delaware.

Alyssa Lanzi, assistant professor of communication sciences and disorders (CSCD) in UD's College of Health Sciences, leads efforts to expand and diversify DementiaBank, a shared database of multimedia interactions for studying communication in dementia.

Her research, supported by a $3.7 million National Institute on Aging (NIA) grant, has recently earned national recognition after being selected among thousands of databases for use in the NIA's Pioneering Research for Early Prediction of Alzheimer's Disease & Related Dementias EUREKA (PREPARE) Challenge. The two-year challenge aims to develop novel and inclusive approaches for the early prediction of Alzheimer's disease and related dementias through three phases that build upon one another.

Phase I of the challenge, called FindIT!, focused on identifying or building a representative open science dataset that addresses biases in Alzheimer's research. Among thousands of datasets, Lanzi's DementiaBank emerged as the standout winner.

"If we really want to take a crack at early detection and make advancements, we need a team-based, collaborative approach-something much larger than a single research lab at any university," Lanzi said. "To see data scientists from all over the U.S. with industry backgrounds from Google and Amazon come together and use the data we're collecting at UD to build analytical approaches that will drive the early detection field could not be more motivating."

DrivenData, which organized the challenge, called DementiaBank impressive.

"We were looking for that unicorn dataset," said Christine Chung, a senior data scientist with DrivenData. "Dementia Bank is a well-structured, accessible dataset with diverse representation. It's an underexplored area, and machine learning and artificial intelligence now allow us to extract richer features from audio samples."

Phase II, BuildIT! focused on advancing state-of-the-art, ethical, and inclusive algorithms and analytical approaches for early detection and prediction. Phase III, Put IT All Together! brought top teams together to demonstrate their models and pitch solutions.

DementiaBank was the sole database selected for acoustic analysis and was used throughout the challenge.

"Recruiting participants and collecting data in a standardized way is hard work," said Lanzi. "We're still in active data collection - and not even close to finished, so to see the impact of our work beyond publications, paving the way for leading scientific approaches, is incredible."

Anna Saylor, a fourth-year student in the CSCD doctoral program, has been working in Lanzi's Resilient Cognitive Aging Lab since the project's inception. Having watched her late grandparents progress through Alzheimer's, the work feels deeply personal.