Cutting through complexity

When Morgan Ellithorpe's family moved from upstate New York to Delaware, they struggled to navigate state services for her brother, who has cerebral palsy.

"It was a huge administrative burden, and my mom isn't very tech-savvy. It was a months-long, multi-step process that required gathering a ton of paperwork and coordinating between a lot of different systems," said Ellithorpe, associate professor of communication at the University of Delaware College of Arts and Sciences.

That experience inspired Ellithorpe to pursue research aimed at reducing that burden.

Supported by the College of Health Sciences' Maggie E. Neumann Health Sciences Research Fund, Ellithorpe teamed up with Susan Conaty-Buck, assistant professor of nursing in the College of Health Sciences, to determine whether artificial intelligence (AI) could help people with disabilities and their caregivers navigate complex healthcare systems. The project team also includes two UD graduate students and an advisory board made up of community members who are disabled and caregivers of people with disabilities.

Researchers programmed and tested a closed-system generative AI chatbot trained on public disability-services documents. Half of the study's 334 participants used the chatbot to answer common questions about benefits and services, while the other half searched the original PDF documents themselves for answers.

Participants using the chatbot experienced significantly lower administrative burden and answered questions more accurately than those searching PDFs. The findings suggest AI could help people with disabilities and their caregivers find reliable information about benefits and services more quickly and with less frustration.