Towards conversational assistants for health applications: using ChatGPT to generate conversations about heart failure
This work addresses the challenge of creating conversational assistants for health applications, specifically for a domain with limited datasets, but it is incremental as it focuses on prompt engineering with existing models.
The study tackled the problem of generating conversations about heart failure self-care for African-American patients using ChatGPT, finding that effective prompt design, including social determinants of health, improves dialogue quality but the model lacks empathy and engagement for meaningful healthcare communication.
We explore the potential of ChatGPT (3.5-turbo and 4) to generate conversations focused on self-care strategies for African-American heart failure patients -- a domain with limited specialized datasets. To simulate patient-health educator dialogues, we employed four prompting strategies: domain, African American Vernacular English (AAVE), Social Determinants of Health (SDOH), and SDOH-informed reasoning. Conversations were generated across key self-care domains of food, exercise, and fluid intake, with varying turn lengths (5, 10, 15) and incorporated patient-specific SDOH attributes such as age, gender, neighborhood, and socioeconomic status. Our findings show that effective prompt design is essential. While incorporating SDOH and reasoning improves dialogue quality, ChatGPT still lacks the empathy and engagement needed for meaningful healthcare communication.