Large language models for patient-centred evidence generation and use

Preprint. Not peer reviewed. For people with multimorbidity, disease-specific evidence can leave practical questions unanswered. We propose an evidence operating system (Evidence OS) that follows patient priorities through evidence synthesis, research and the return of findings to care. Large language models could assist these transitions. We specify responsibilities, distinguish evidence gaps from service gaps, and outline comparisons needed to test whether the framework improves decisions, workload and patient outcomes.