Chatbot Generates Quality, Empathetic Responses to Patient Questions

Chatbot generates higher proportion of responses rated as good or very good quality and empathetic or very empathetic.

HealthDay News — An artificial intelligence (AI) chatbot assistant generates quality and empathetic responses to patient questions, according to a study published online April 28 in JAMA Internal Medicine.

John W. Ayers, Ph.D., from the University of California San Diego in La Jolla, and colleagues examined the ability of an AI chatbot assistant to provide quality and empathetic responses to patient questions. A total of 195 exchanges were randomly drawn from a public social media forum where a verified physician responded to a public question. Chatbot responses were generated by entering the original question into a fresh session. A team of licensed health care professionals evaluated the original question together with anonymized and randomly ordered physician and chatbot responses in triplicate.

The researchers found that in 78.6 percent of the 585 evaluations, evaluators preferred chatbot responses to physician responses. Compared with chatbot responses, mean physician responses were significantly shorter (52 versus 211 words). Chatbot responses were rated as being of significantly higher quality than physician responses; for example, the proportion of responses rated as good or very good was higher for chatbot than physician (78.5 versus 22.1 percent). Chatbot responses were also significantly more empathetic, with 45.1 and 4.6 percent of chatbot and physician responses, respectively, rated as empathetic or very empathetic.

“We can hope that emerging AI systems may help tame laborious tasks that overwhelm modern medicine and empower physicians to return our focus to treating human patients,” write the authors of an accompanying editorial.

Two authors disclosed financial ties to biopharmaceutical and technology companies, including Lifelink, a health care chatbot company.

Abstract/Full Text