Evidence map›Paper›PMID 42712287›Full record

ArticleBMJ digital health & AI2026

COPE: Chain-of-Thought Prediction Engine for open-source large language model-based stroke outcome prediction from clinical notes.

Yongkai Liu, Helena Feng, Bin Jiang, Yixin Wang, Max Wintermark, David Liebeskind, Michael Moseley, Maarten Lansberg, Gregory Albers, Jeremy Heit and 1 more

Abstract read
PubMed Full text at PMC Publisher
In one paragraph

Article in BMJ digital health & AI, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.

0numbers the graph read from it
0cells of the map it votes in
0citing papers in PubMed
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

0 citing papers in PubMed.

No citing paper in PubMed yet.

4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

11 authors.

Yongkai LiuDepartment of Radiology, Stanford University, Stanford, California, USA.ORCID 0000-0003-4478-4006
Helena FengDepartment of Radiology, Stanford University, Stanford, California, USA.
Bin JiangDepartment of Radiology, Stanford University, Stanford, California, USA.
Yixin WangDepartment of Radiology, Stanford University, Stanford, California, USA.
Max WintermarkDepartment of Neuroradiology, University of Texas MD Anderson Center, Houston, Texas, USA.
David LiebeskindUCLA, Los Angeles, California, USA.
Michael MoseleyDepartment of Radiology, Stanford University, Stanford, California, USA.
Maarten LansbergDepartment of Neurology, Stanford University, Stanford, California, USA.
Gregory AlbersDepartment of Neurology, Stanford University, Stanford, California, USA.
Jeremy HeitDepartment of Radiology, Stanford University, Stanford, California, USA.
Greg ZaharchukDepartment of Radiology, Stanford University, Stanford, California, USA.

Funding

Fused Imaging and Large Language Foundational Model for 90-day Stroke Outcome PredictionK99NS140547 · NINDS · STANFORD UNIVERSITY · PI Yongkai Liu · 2025 to 2026
$250k
NINDS NIH HHS K99 NS140547
6 · The paper itself

Abstract

Objective: To develop and evaluate Chain-of-Thought Outcome Prediction Engine (COPE), a reasoning-enhanced large language model, for predicting 90-day functional outcomes after acute ischaemic stroke (AIS) from unstructured clinical notes. Methods: We included 464 patients with AIS who had discharge summaries and 90-day modified Rankin Scale (mRS) outcomes. COPE uses a two-step chain-of-thought (CoT) framework based on sequential open-source models (LLaMA-3-8B): the first generates intermediate clinical reasoning and the second outputs an mRS prediction. We compared COPE's performance with GPT-4.1, ClinicalBERT, a structured variable-based machine learning model (XGBoost) and a single-step large language model (LLM) without CoT. Performance was evaluated using mean absolute error (MAE), accuracy within ±1 mRS point (±1 ACC) and exact accuracy (ACC). Results: COPE achieved an MAE of 1.01 (95% CI 0.92 to 1.11), ±1 ACC of 74.4% (95% CI 69.9% to 78.8%) and ACC of 32.8% (95% CI 28.0% to 37.6%), comparable to GPT-4.1 (MAE, 1.00 (95% CI 0.90 to 1.09); ±1 ACC, 77.9% (95% CI 73.7% to 82.0%); ACC, 32.5% (95% CI 28.0% to 37.4%); p=0.72, 0.11 and 0.96). COPE demonstrated performance comparable to a strong structured-data baseline using XGBoost (MAE, 1.03 (95% CI 0.93 to 1.13); ±1 ACC, 73.9% (95% CI 69.4% to 78.5%); ACC, 33.3% (95% CI 28.5% to 38.2%); p=0.77, 0.87 and 0.89), and outperformed ClinicalBERT and the single-step LLM. Subgroup analyses showed consistent performance across sex and age, with higher error among older patients, those undergoing thrombectomy and those with longer summaries. Conclusions: COPE, a reasoning-enhanced framework using lightweight, open-source LLMs, achieved performance comparable to a proprietary model and to strong traditional baselines while operating without model retraining or manual feature engineering. It offers an accurate and privacy-preserving solution for outcome prediction from unstructured clinical text.

Indexed as

Artificial intelligenceDecision Making, Computer-AssistedElectronic Health RecordsOutcome Assessment, Health Care

Identifiers

PMID42712287
PMCPMC13528327

What OpenQuestion holds

Textmetadata
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.