Use of Generative Artificial Intelligence for Consultation Preparation in Shared Decision Making: Can a Handbook Provide Support?

Background: Shared Decision Making (SDM) is considered the gold standard of patient-centered care but often fails in clinical routine due to time constraints and a lack of patient preparation. While patients often struggle to articulate their preferences and questions, new developments in the field of Generative Artificial Intelligence (GenAI) and Large Language Models (LLMs) offer the potential to bridge this gap. Objective: This paper examines the potential of GenAI as a supportive tool for preparing doctor-patient consultations. The aim is to conceptualize an evidence-based handbook providing patients and physicians with guidance (prompts) to make SDM processes more efficient and personalized. Results: The literature review indicates that GenAI can meaningfully complement traditional decision aids through personalization and interactivity. Specific areas of application include translating complex medical information into patient-friendly language, supporting value clarification, and generating individualized Question Prompt Lists. However, a handbook for using these technologies must address critical risks, particularly "hallucinations" (factual errors), bias in training data, and data privacy issues. Effective "prompt engineering" is identified as a new key competency for both patients and providers. Conclusion: A structured handbook for the use of GenAI has the potential to reduce asymmetry in the doctor-patient relationship and increase consultation efficiency. However, prerequisites for implementation include strict safety mechanisms, consideration of health literacy, and ethical validation of AI outputs.