Publications

We developed an automated pipeline using ASR and NLP to detect social signals in 782 patient-provider conversations, achieving 90.1% accuracy and fair performance across racial groups. The system uncovered clear disparities—providers showed more warmth and engagement toward white patients—highlighting how AI can surface subtle, bias-related patterns in clinical communication.

We designed a human-centered, LLM-powered chatbot to support older adults in a retirement community, focusing on accessibility and digital literacy. Using interviews and persona development, we built a dual-function tool for information access and tech education. A pilot showed high satisfaction, leading to refinements with GPT-3.5 Turbo, Streamlit, and accessible UI features. The project demonstrates how LLMs can empower older adults through personalized, low-barrier digital support.

We developed an LLM-powered chatbot using a human-centered design approach to support older adults in a retirement community with low tech and eHealth literacy. The chatbot offers accessible, conversational assistance for both navigating community resources and improving digital literacy. Features like large text, high-contrast themes, and voice interaction enhance usability. In a pilot trial, residents successfully completed tasks and reported high satisfaction, suggesting the chatbot’s potential to empower older adults through intuitive, low-barrier technology.

No abstract available.

An analysis of NHANES data from 26,282 U.S. adults revealed widespread inadequacies in key immune-supporting micronutrients, with over 95% deficient in vitamin D and over 80% in vitamin E. Using nationally representative intake estimates, the study highlights how these gaps may impair immune function. Supplement use was associated with reduced prevalence of inadequacy. The findings underscore the need for public health efforts to promote adequate intake of vitamins A, C, D, E, and zinc to support immune health.