What question did this study set out to answer?

The study aims to assess the effectiveness of large language models for nutrition risk screening using EHR data.

Evaluation of large language models in nutrition risk screening: a comparative analysis across 8 LLMs based on real-world EHR datasets

View Full Paper

Ask AI

Bookmark

Authors

Comparative analysis shows effective risk screening in hospitals using LLMs to ensure health equity.

The study aims to assess the effectiveness of large language models for nutrition risk screening using EHR data.
Compared eight large language models based on real-world EHR datasets.
Developed structured prompts and scoring criteria through expert collaboration.
Evaluated models on accuracy, consistency, and processing efficiency using numerous inpatient records.
Five of the eight models achieved over 90% correct assessment rate in nutritional risk.
The top model reached 99.16% in binary risk classification accuracy.
Performance varied widely in total score accuracy, with domain-specific assessments showing strengths in serum albumin.

Gu et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark