Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-1807
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-10-18T10:41:44.541285Z
status: published
lens: trace
sector: health
headline: Relationship extraction for adverse drug events in clinical notes using large language models: a retrospective cross-sectional study
dek: 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…
gain_title: 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.
problem_title: Both models made characteristic errors, including misclassifying pre-existing allergies and conflating therapeutic indications with adverse effects, and overall F1 scores stayed modest.
trace_subject: LLM extraction of adverse drug events from clinical notes
gain_reading: 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.
gain_evidence: GPT-4o consistently outperformed GPT-4o-mini in ADE extraction across both datasets | GPT-4o achieved higher exact match coverage and fewer errors across clinical notes
problem_reading: Both models made characteristic errors, including misclassifying pre-existing allergies and conflating therapeutic indications with adverse effects, and overall F1 scores stayed modest.
problem_evidence: limitations included misclassification of pre-existing allergies and occasional conflation of therapeutic indications with adverse effects
quick_read: Researchers compared GPT-4o, GPT-4o-mini and Llama 3.2-3B, along with fine-tuned variants, on identifying links between adverse drug events and drugs in free-text notes. The data came from the 2018 n2c2 inpatient dataset and outpatient encounters at a large New England academic medical center. GPT-4o and GPT-4o-mini performed best, and GPT-4o led on F1 score.

Adverse drug events are an important patient-safety indicator, yet they are often recorded only in free text, so automated extraction could support surveillance. The reported F1 scores are moderate, and the errors seen in manual review show that clinical use would require care. The study frames its results as a foundation, not proof of deployed safety gains.
limitation: Reported F1 scores were modest, and both top models misclassified pre-existing allergies and sometimes confused therapeutic indications with adverse effects.
tag: Dual reading
key_points: Of 1048 notes in the local test split, 450 (42.9%) contained at least one adverse drug event. | The n2c2 test set had 202 notes, and 155 (76.7%) contained at least one adverse drug event. | GPT-4o reached an F1 of 0.524 versus 0.381 for GPT-4o-mini, with a more balanced precision-recall profile. | Manual review of the two best models used categories such as exact semantic match, partial match, missing ADE and wrong.
rundown: The study was a retrospective cross-sectional analysis using 505 inpatient notes from the n2c2 dataset and 2555 outpatient notes from October 2018 to December 2019. Notes were split into snippets before being given to the models.

Models tested were GPT-4o, GPT-4o-mini, Llama 3.2-3B and instruction fine-tuned variants, including low-rank adapters for Llama. Performance was scored with strict and relaxed precision, recall and F1.

The two best models were then manually assessed. The authors report that both captured adverse drug events in explicit and complex contexts, but they also misclassified pre-existing allergies and sometimes confused indications with adverse effects.
sources:
- peer_reviewed | eBioMedicine | https://doi.org/10.1016/j.ebiom.2026.106516 | 2026-10-17
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

e2d0aa0dc5d517e0ad7418fc0d190f8ba9669d4964b0d21a23c38adc17469cb7

previous

0000000000000000000000000000000000000000000000000000000000000000