63/100

Moderate evidence

GainPublished recordHealthGood Space

Large Language Models Predict Functional Outcomes After Acute Ischemic Stroke

Truvace record
TRV-2026-3059raw data (JSON)
Version
v1Published
First published
Evidence type
Observational study
Sources
1 sourcePeer-reviewed
sha256
77f0de421e7c…check it

Background and objectives: Accurate prediction of functional outcomes after acute ischemic stroke can guide clinical decision-making and resource allocation. Prior work has relied predominantly on structured predictors and conventional machine learning, while the ability of large language models (LLMs) to infer modified Rankin Scale (mRS) scores from routine clinical admission notes is largely unexplored. Methods: We evaluated encoder (Bidirectional Encoder Representations from Transformers [BERT], NYUTron) and…

The gain

In a retrospective NYU Langone analysis of 1,898 stroke patients' admission notes, a fine-tuned Llama model predicted 90-day functional outcome with an AUROC of 0.87, beating four published baselines that scored 0.79 to 0.82.

What this doesn’t fix

The models were built and tested retrospectively on registry notes from a single health system, and differences between model classes varied by metric, so they cannot be attributed to architecture alone.

Sources

1 on file
  1. Neurosurgerydoi:10.1227/neu.0000000000004298
    Peer-reviewed2026-11-19

Cite this record

v1

Truvace Impact Record TRV-2026-3059, v1: “Large Language Models Predict Functional Outcomes After Acute Ischemic Stroke.” Truvace, 2026-11-19. /record/TRV-2026-3059 (accessed on the day you copy it). sha256 77f0de421e7c3e0d…

Change history

1 version

Every change made to this record since it was first published, and why. Nothing has changed since it went up.

  1. Publishedv177f0de421e7c…

    Certified into the record

Check this record hasn’t been altered

Check this record hasn’t been altered
How to check it yourself, without trusting this page

Download any version from /api/record/TRV-2026-3059 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.