A Dataset and Resources for Identifying Patient Health Literacy Information from Clinical Notes

arXiv cs.CL / 3/20/2026

📰 NewsTools & Practical UsageModels & Research

共有:

Key Points

HEALIX is the first publicly available annotated health literacy dataset derived from real clinical notes, comprising 589 notes across 9 note types and labeled as low, normal, or high health literacy.
The dataset was curated using a combination of social worker note sampling, keyword-based filtering, and LLM-based active learning to ensure quality annotations.
To validate its usefulness, the authors benchmark zero-shot and few-shot prompting across four open-source large language models (LLMs).
The work aims to enable automated detection of health literacy information in unstructured clinical notes, addressing challenges in documenting health literacy in structured electronic health records and highlighting potential improvements in patient-outcome research and clinical workflow.

Abstract

Health literacy is a critical determinant of patient outcomes, yet current screening tools are not always feasible and differ considerably in the number of items, question format, and dimensions of health literacy they capture, making documentation in structured electronic health records difficult to achieve. Automated detection from unstructured clinical notes offers a promising alternative, as these notes often contain richer, more contextual health literacy information, but progress has been limited by the lack of annotated resources. We introduce HEALIX, the first publicly available annotated health literacy dataset derived from real clinical notes, curated through a combination of social worker note sampling, keyword-based filtering, and LLM-based active learning. HEALIX contains 589 notes across 9 note types, annotated with three health literacy labels: low, normal, and high. To demonstrate its utility, we benchmarked zero-shot and few-shot prompting strategies across four open source large language models (LLMs).