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

2025-05-06

AI Summary

This study addresses the scarcity of health dialogue data tailored to Black American patients with heart failure. We propose the first multi-strategy dialogue generation framework integrating Social Determinants of Health (SDOH), African American Vernacular English (AAVE) linguistic style, and structured reasoning prompts. Leveraging GPT-3.5-turbo and GPT-4, we implement four prompt engineering strategies: domain adaptation, AAVE fine-tuning, SDOH attribute injection, and SDOH-guided reasoning—generating 5-, 10-, and 15-turn simulated clinician–patient dialogues covering diet, exercise, hydration, and related topics. Empirical evaluation shows that SDOH-enhanced prompting significantly improves content relevance and cultural appropriateness; however, empathic expression and interactive engagement remain suboptimal. This work establishes a novel paradigm and methodological foundation for generating interpretable, culturally responsive health dialogues for underserved populations.

Technology Category

• Natural Language Processing: Conversational AI/Dialog Systems
• Humans and AI: Learning Human Values and Preferences
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• Generating health-focused conversations for African-American heart failure patients
• Exploring ChatGPT's ability to simulate patient-educator dialogues with SDOH factors
• Assessing dialogue quality and empathy gaps in AI-generated healthcare communication

Innovation

• Using ChatGPT to generate health-focused dialogues
• Employing diverse prompting strategies for realism
• Incorporating patient-specific attributes in conversations