{"id":4635,"date":"2025-03-17T12:21:18","date_gmt":"2025-03-17T11:21:18","guid":{"rendered":"https:\/\/blogs.bmj.com\/medical-ethics\/?p=4635"},"modified":"2025-03-17T12:34:04","modified_gmt":"2025-03-17T11:34:04","slug":"the-doctor-will-speak-as-you-prefer-how-ai-could-personalize-medical-communication","status":"publish","type":"post","link":"https:\/\/blogs.bmj.com\/medical-ethics\/2025\/03\/17\/the-doctor-will-speak-as-you-prefer-how-ai-could-personalize-medical-communication\/","title":{"rendered":"The doctor will speak as you prefer? How AI could personalize medical communication"},"content":{"rendered":"

By Hazem Zohny, Jemima Winfried Allen, Dominic Wilkinson, and Julian Savulescu.<\/p>\n

When you go to the doctor, there\u2019s little telling what kind of communicator you\u2019ll get. Some doctors are on the paternalistic side, telling you what you should do without much discussion. Others just give you the facts and leave the decision entirely to you. Some try to help you explore your values and what matters to you. And others engage in a back-and-forth dialogue about what might be best for your health.<\/p>\n

The way a doctor \u2013 or healthcare provider more generally \u2013 communicates can make all the difference. It can empower patients, confuse them, reassure them, or frustrate them. But for the most part, patients don\u2019t get to choose \u2013 it\u2019s basically a lottery. You get assigned a doctor, and at least to some degree they communicate in whatever style they\u2019re comfortable with\u2014whether or not it works for you.<\/p>\n

Given the emphasis on patient autonomy in recent decades, one possible solution is to let patients choose how they want medical information delivered. Maybe you want a no-nonsense, just-the-facts approach. Or maybe you\u2019d rather have a doctor walk you through your values, helping you figure out what truly matters to you before making a decision.<\/p>\n

On the other hand, doctors don\u2019t necessarily have the skills to adapt their approach to every patient. And some communication styles\u2014especially those that require deep discussion\u2014are simply too time-consuming for the reality of modern healthcare.<\/p>\n

This is where large language models (LLMs) could play a role. These models are multilingual, have unlimited patience, and can adapt to individual patient health literacy levels. They can spend as much time as needed explaining things, answering questions, and helping you think through your options.<\/p>\n

They also appear remarkably good at mimicking different medical communication styles. In a recent JME paper titled ‘Which AI doctor would you like to see?’ <\/a>we tested this with GPT-4, instructing it to role-play as a doctor using four well-known models<\/a> of doctor-patient communication:<\/p>\n