# Evaluating LLM Abilities to Understand Tabular Electronic Health Records: A Comprehensive Study of Patient Data Extraction and Retrieval

arXiv: https://arxiv.org/abs/2501.09384 · HTML: https://mlsanity.com/paper/2501.09384/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jan 2025.

## Built on by (most cited first, 3 of 3)

- [EHRStruct: A Comprehensive Benchmark Framework for Evaluating Large Language Models on Structured Electronic Health Record Tasks](https://mlsanity.com/paper/2511.08206/) (2025)
- [PatientDx: Merging Large Language Models for Protecting Data-Privacy in Healthcare](https://mlsanity.com/paper/2504.17360/) (2025)
- [ReToP: Learning to Rewrite Electronic Health Records for Clinical Prediction](https://mlsanity.com/paper/2601.19286/) (2026)

## Abstract (arXiv)

Electronic Health Record (EHR) tables pose unique challenges among which is the presence of hidden contextual dependencies between medical features with a high level of data dimensionality and sparsity. This study presents the first investigation into the abilities of LLMs to comprehend EHRs for patient data extraction and retrieval. We conduct extensive experiments using the MIMICSQL dataset to explore the impact of the prompt structure, instruction, context, and demonstration, of two backbone LLMs, Llama2 and Meditron, based on task performance. Through quantitative and qualitative analyses, our findings show that optimal feature selection and serialization methods can enhance task performance by up to 26.79% compared to naive approaches. Similarly, in-context learning setups with relevant example selection improve data extraction performance by 5.95%. Based on our study findings, we propose guidelines that we believe would help the design of LLM-based models to support health search.