Health & Medicinearticle2026-11-14

Personas shift clinical action thresholds in large language models

Open access1 citations

Abstract

Clinical large language model (LLM) deployment is shifting from feasibility to liability, while current guidance largely treats model behavior as a control problem. We tested whether decision-style system prompts shift clinical action thresholds when clinical facts are held constant, and whether these shifts are consistent across settings and models. We defined nine physician personas by crossing three ethical orientations (duty-based, care-based, utilitarian) with three cognitive styles (intuitive, integrative, analytic). Twenty open-weight LLMs were evaluated on 2500 simulated emergency department vignettes and 2500 MIMIC-IV-Note discharge summaries. For each text, models answered five binary decision items (safety, autonomy, treatment, resource use, follow-up). Each condition was repeated ten times, yielding 5,000,000 total decisions. Under baseline prompting, models answered “Yes” to 42.8% of decisions. Persona prompts shifted affirmative rates from 36.9% to 46.4%, a 9.5 percentage-point swing under fixed clinical evidence. Effects were largest in autonomy and treatment and were consistent across corpora (85.7% directional agreement; r = 0.82 for effect sizes). Susceptibility varied by model (4.9–16.1 points), with no consistent protection from medical fine-tuning or model size. Decision-style system prompts reliably change clinical action thresholds in LLMs under fixed evidence. Prompting is a policy-setting layer, not just a communication layer, and should be treated as a first-class deployment configuration.

// Source

View paper (DOI)Open access versionOpenAlexnpj Health SystemsPublished 2026-11-14

Authors: Eyal Klang, Alon Gorenshtein, Mahmud Omar

Institutions: Icahn School of Medicine at Mount Sinai, Harvard University, Beth Israel Deaconess Medical Center, Mount Sinai Hospital, Mount Sinai Health System