aceA framework to assess clinical safety and hallucination rates of LLMs for medical text summarisation
Integrating large language models (LLMs) into healthcare can enhance workflow efficiency and patient care by automating tasks such as summarising consultations. However, the fidelity between LLM outputs and ground truth information is vital to prevent miscommunication that could lead to compromise in patient safety. We propose a framework comprising (1) an error taxonomy for classifying LLM outputs, (2) an experimental structure for iterative comparisons in our LLM document generation pipeline, (3) a clinical sa…
Refining prompts and workflows within the proposed framework reduced major errors below previously reported human note-taking rates, supporting safer clinical documentation.
LLM summarisation of consultations showed a 1.47% hallucination rate and 3.45% omission rate, creating fidelity gaps that could compromise patient safety.
Findings are bounded to 18 experimental configurations and 12,999 clinician-annotated sentences for clinical note generation, limiting generalizability beyond that evaluation set.
Evidence
- Peer-reviewednpj Digital Medicine2025-05-13
How should this claim be treated?
Truvace Impact Record TRV-2026-0522, v1: “A framework to assess clinical safety and hallucination rates of LLMs for medical text summarisation.” Truvace, 2026-07-24. /record/TRV-2026-0522 (accessed at citation time). sha256 5ce93b85276c3786…
Calibration history
Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.
Certified into the record
How to verify without trusting this page
Fetch the canonical text of any version from /api/record/TRV-2026-0522 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.