aceRelationship extraction for adverse drug events in clinical notes using large language models: a retrospective cross-sectional study
Background: Adverse drug events (ADEs) are a critical indicator of patient safety but are often documented only in free-text clinical notes. The potential of recent advances in natural language processing (NLP), particularly generative large language models (LLMs), to identify ADEs remains understudied. This study aimed to compare the performance of multiple LLMs in identifying ADE-Drug relationships in inpatient and ambulatory clinical notes. Methods: We used clinical notes from the 2018 National NLP Clinical C…
GPT-4o identified adverse drug event and drug relationships in inpatient and outpatient notes better than GPT-4o-mini, suggesting a basis for LLM-assisted drug safety surveillance.
Both models made characteristic errors, including misclassifying pre-existing allergies and conflating therapeutic indications with adverse effects, and overall F1 scores stayed modest.
Reported F1 scores were modest, and both top models misclassified pre-existing allergies and sometimes confused therapeutic indications with adverse effects.
Evidence
- Peer-reviewedeBioMedicine2026-10-17
How should this claim be treated?
Truvace Impact Record TRV-2026-1807, v1: “Relationship extraction for adverse drug events in clinical notes using large language models: a retrospective cross-sectional study.” Truvace, 2026-10-18. /record/TRV-2026-1807 (accessed at citation time). sha256 e2d0aa0dc5d517e0…
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-2026-1807 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.