Towards conversational assistants for health applications: using ChatGPT to generate conversations about heart failure

TL;DR

This study investigates ChatGPT's ability to generate health-related conversations for African-American heart failure patients, highlighting the importance of prompt design and the current limitations in empathy and engagement.

Contribution

It demonstrates how different prompting strategies influence the quality of health dialogues generated by ChatGPT in a specialized domain.

Findings

Effective prompt design is crucial for quality conversations.

Incorporating SDOH and reasoning improves dialogue relevance.

ChatGPT lacks sufficient empathy and engagement for healthcare use.

Abstract

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.