COIOSDeep risk insights through multi-disciplinary research across the globe
a close up of a piece of white paper
Item new Preprint · not peer-reviewed Added

Language models identified in-hospital cardiac arrests better than ICD codes

On a hand-picked set of notes, a trained language model flagged encounters for in-hospital cardiac arrest of which 88% were genuine, against 68% for an ICD-code algorithm.

Researchers built language models to identify in-hospital cardiac arrest from hospital notes, judged against doctors' review of the same charts. On a hand-picked set of notes, 88% of the encounters the trained model flagged were genuine arrests, against 68% for an ICD-code algorithm. Across 45,525 unselected encounters, a version prompted with clinical guidance and checking its own answers flagged encounters of which 79% were genuine.

Why it is interesting: The model trained on examples did worse on unselected encounters than on the hand-picked notes.

Source
medRxiv, 27 September 2026
Paper
Beyond ICD Codes: Fine-Tuning LLMs for In-Hospital Cardiac Arrest Identification from EHR Notes
Authors
Weissenbacher D, Vo J, Uy-Evanado A, Reinier K, Chugh H, Kadiyala V et al.
DOI
10.64898/2026.09.24.26363973
Type
Preprint
Design
Retrospective LLM case-ascertainment study against physician-adjudicated chart review; curated evaluation corpus plus 45,525-encounter unselected validation cohort
Verdict
New finding
Driver
AI in medicine
Driver
Heart and stroke

Other drivers in Data, models and systems