.png){kind=icon}
.png){kind=icon}
Return
Developing a scalable pipeline for data extraction from clinical letters through resource-efficient prompt engineering
.png){kind=icon}
OA
AI
A
Q
J
F
M
D
L
E
Y
G
Y
A
P
DOI：10.1038/s41746-026-03136-w.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Free-text clinical records represent an untapped wealth of data for secondary use, but realising their potential is limited by resource demands necessary for accurate information extraction at scale. We introduce a scalable, resource-efficient, and high-performance information extraction pipeline that leverages large language models (LLMs) to address these challenges. Our pipeline was developed and tested using real-world dual specialist-annotated ophthalmic clinical letters, and achieved strong performance with a proprietary model in development, yielding a maximum micro-averaged F1 score of 0.954 (95% CI 0.941–0.967) for diagnosis across nine conditions through iterative prompt refinement alone, also demonstrating strong generalisability (micro-F1 0.945–0.980) in temporal validation. This approach was extended to other models in the same family and 17 LLMs from seven open-weight LLM families. Beyond performance, we develop a multi-dimensional assessment for deployment in data extraction tasks, including an error taxonomy and Pareto frontier analyses to systematically map the operational trade-offs across different LLM configurations. A robust approach to operationalisation in real-world workflows at scale may help lay the foundation for next-generation data pipelines that accelerate scientific discovery and power continuous learning health systems.
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
15.1
Papers:
3.1K
Citations:
1.5W
View more organizations