Evaluating LLM Abilities to Understand Tabular Electronic Health Records: A Comprehensive Study of Patient Data Extraction and Retrieval
This addresses the challenge of extracting and retrieving patient data from EHRs for healthcare applications, but it is incremental as it builds on existing LLMs with specific optimizations.
This study tackled the problem of using large language models (LLMs) to understand tabular electronic health records for patient data extraction and retrieval, finding that optimal feature selection and serialization methods improved task performance by up to 26.79% and in-context learning setups enhanced data extraction by 5.95%.
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.