Which AI doctor would you like to see? Emulating healthcare provider–patient communication models with GPT-4
Proof-of-concept and ethical exploration
Bibliographic Data
| ID | 21514503 |
|---|---|
| Authors | Hazem Zohny (0000-0002-7734-2186, University of Oxford, corresponding author), Jemima Winifred Allen (0000-0002-3950-9950, Philosophy, University of Oxford Uehiro Centre for Practical Ethics, Oxford, UK), Dominic Wilkinson (0000-0003-3958-8633, University of Oxford), Julian Savulescu (0000-0003-1691-6403, National University of Singapore) |
| Year | 2026 |
| Volume | 52 |
| Issue | e1 |
| Pages | e36-e43 |
| Publication date | 2026-05-01 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Journal of Medical Ethics (JOURNAL) |
| Journal identifiers | ISSN: 0306-6800 • E-ISSN: 1473-4257 |
| Publisher | BMJ (PUBLISHER • GB) |
| DOI | 10.1136/jme-2024-110256 |
| PMID | 40032513 |
| OpenAlex | W4408100950 |
| Language | EN |
| Citations received | 7 |
| References cited | 42 |
Large language models (LLMs) have demonstrated potential in enhancing various aspects of healthcare, including health provider–patient communication. However, some have raised the concern that such communication may adopt implicit communication norms that deviate from what patients want or need from talking with their healthcare provider. This paper explores the possibility of using LLMs to enable patients to choose their preferred communication style when discussing their medical cases. By providing a proof-of-concept demonstration using ChatGPT-4, we suggest LLMs can emulate different healthcare provider–patient communication approaches (building on Emanuel and Emanuel’s four models: paternalistic, informative, interpretive and deliberative). This allows patients to engage in a communication style that aligns with their individual needs and preferences. We also highlight potential risks associated with using LLMs in healthcare communication, such as reinforcing patients’ biases and the persuasive capabilities of LLMs that may lead to unintended manipulation
Health care · Health communication · Internet privacy · Paternalism · Political science · Public relations · Unintended consequences · Artificial Intelligence in Healthcare and Education · Communication · Computer Science · Law · Medicine · Palliative Care and End-of-Life Issues · Patient-Provider Communication in Healthcare · Psychology · Social Psychology
Reframing ‘dehumanisation’
Academic freedom, artificial intelligence and the blandification of ethics
On the risks of depersonalizing consent and the safe implementation of LLMs in medical decision-making
Ethics of AI in medicine
Empowering Patient Autonomy
AI and shared decision-making
Algorithmic nudging for clinical trial participation
Comparing Physician and Artificial Intelligence Chatbot Responses to Patient Questions Posted to a Public Social Media Forum
Durably reducing conspiracy beliefs through dialogues with AI
Not all patients want to participate in decision making
Computer knows best? The need for value-flexibility in medical AI
Patient preferences for shared decisions
The Relationship between Health Literacy and Health Disparities
Reimagining Health—Flourishing
Four Models of the Physician-Patient Relationship
Consent-GPT
Artificial intelligence and the doctor–patient relationship expanding the paradigm of shared decision making
In principle obstacles for empathic AI
Abandoning Informed Consent
It’s only a computer
Cultural targeting and tailoring of shared decision making technology
| Unique citing works | 7 |
|---|---|
| Citations per year | 7 |
| Citation span | 2025 - 2026 (2) |
| Citation velocity | current |
| Highly cited | No |
| Citation types | Neutral: 7 |