UW Ph.D. Student Publishes Study Comparing Communication of Doctors and AI Chatbots

We may not yet be seeking medical care from hologram doctors as envisioned by the “Star Trek: Voyager” television series of the 1990s, but the medical field is increasingly turning to artificial intelligence (AI) to assist in patient care. How, then, do the responses given by AI chatbots compare to those of flesh-and-blood doctors?

Danny Burns, a Ph.D. student in the data science track of the University of Wyoming's biomedical sciences program, launched a study to find answers to this question. Burns, from Wall Township, N.J., has a background in biology and completed his master’s degree in statistics at UW in 2023.

His research, conducted in collaboration with four co-authors who range in expertise from statistics to medicine to journalism, was recently published in the Journal of Medical Internet Research, the top-ranked medical informatics journal in the world. The article is titled “Comparison of Emotional Content in Text Responses from Physicians and AI Chatbots to Patient Health Queries: Cross-Sectional Study.”

“Recent research has been showing that people are increasingly willing to use chatbots for (their medical care) and that they prefer the responses they get from them over those from physicians, while also saying overwhelmingly that the chatbots are more empathetic,” Burns says.

Burns and his team were motivated to pursue this line of inquiry because, he says, they wanted to know “what other emotional differences might exist between chatbot and physician responses to text-based messages, such as those you would send to your doctor via a secure online portal.”

“This is important because people often seek information to address the emotional dimensions of health concerns, not just to find facts,” he adds.

The benefits of understanding the emotional content of communications in the medical field can be crucial.

“Supportive and emotionally responsive information has been shown to alleviate health-related stress, worry and depression, while also enhancing individuals’ commitment to managing health risks,” Burns says.

For the study, Burns compared physician responses to 100 real-world patient telehealth questions with answers generated by leading AI chatbots. He and his colleagues then analyzed these exchanges for emotional tone, readability, length and use of medical disclaimers such as, “I’m not a doctor, but here is information you need.”

Results showed AI responses were generally longer and more emotionally varied, while physician responses were more concise and easier to read.

The study offers important insights for rural states like Wyoming where telehealth plays a critical role in expanding access to care. Wyoming has invested heavily in telehealth access, broadband expansion and digital health services, all of which generally incorporate the use of AI. The team’s research provides Wyoming decision-makers with local expertise when evaluating AI integration into rural health care systems.

The applications for Burns’ research are potentially much broader, however, having already drawn international attention, including through presentations to investigators in South Africa in July 2025 and New Zealand during February 2026.

The research and associated publication are the result of collaboration among its co-authors from across multiple disciplines and institutions, including Channing Bice, a Ph.D. candidate at Colorado State University’s Department of Journalism and Media Communication; Dr. Paul Johnson, of the WWAMI Medical Education Program and the Ivinson Medical Group; Nicholas Chia, a computational biologist at Argonne National Laboratory; and Timothy Robinson, a professor of statistics at UW and Burns’ Ph.D. adviser.

Robinson is enthusiastic about the way this research positions Wyoming at the forefront of AI research.

“These cross-disciplinary and institutional partnerships signal that Wyoming is not just a consumer of AI tools but is contributing to shaping how AI is evaluated in medicine,” Robinson says. “And this type of impactful research positions UW well for grant funding, workforce development and recruitment.”

Read the full article at https://www.jmir.org/2026/1/e85516.