Applications of large language model in general practice: a qualitative interview study with professionals and patients

In Netherlands general practice interviews (Oct–Dec 2025), the top large language model applications were consultation summarizing and triage/urgency classification (18/31; 58%).

• Why it matters: Rising workload creates a need to understand which specific LLM uses professionals and patients want, and what benefits, risks, and implementation requirements matter for day-to-day care.
• What they did: Semi-structured one-on-one interviews were conducted with 12 GPs, 7 GP assistants, 6 practice nurses, and 6 patient representatives, using a 21-application list spanning five task categories.
• The result: Priorities varied by group, and analysis highlighted three recurring checks: whether an LLM is needed, whether it reduces workload, and whether benefits outweigh risks like mistakes and reduced personal care.

AI summary of the abstract · may contain errors · not medical advice · read the paper.