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

2026-03-19

AI Summary

Existing health literacy screening tools are difficult to integrate structurally into electronic health records and lack annotated data for automatically identifying health literacy from unstructured clinical notes. To address this gap, this study introduces HEALIX, the first publicly available health literacy annotation dataset derived from real-world clinical notes, comprising 589 samples across nine categories of social work notes and three health literacy labels. Annotation was efficiently performed using a hybrid approach combining keyword filtering with a large language model (LLM)-driven active learning strategy. The utility and validity of HEALIX were demonstrated through evaluations on four open-source LLMs under zero-shot and few-shot settings, confirming its effectiveness for automated health literacy identification in clinical text.

Technology Category

• Natural Language Processing: Information Extraction
• Humans and AI: Human-in-the-loop Machine Learning
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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).

Problem

• health literacy
• clinical notes
• annotated dataset
• electronic health records
• natural language processing

Innovation

• health literacy
• clinical notes
• annotated dataset
• large language models
• active learning