# Lessons Learned on Information Retrieval in Electronic Health Records: A Comparison of Embedding Models and Pooling Strategies

arXiv: https://arxiv.org/abs/2409.15163 · HTML: https://mlsanity.com/paper/2409.15163/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 23 Sep 2024.

## Builds on (most cited first, 11 of 11)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [MTEB: Massive Text Embedding Benchmark](https://mlsanity.com/paper/2210.07316/) (2022)
- [LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders](https://mlsanity.com/paper/2404.05961/) (2024)
- [NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark](https://mlsanity.com/paper/2310.18018/) (2023)
- [Benchmarking Retrieval-Augmented Generation for Medicine](https://mlsanity.com/paper/2402.13178/) (2024)
- [Improving Text Embeddings with Large Language Models](https://mlsanity.com/paper/2401.00368/) (2023)
- [GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records](https://mlsanity.com/paper/2203.03540/) (2022)

## Built on by (most cited first, 5 of 5)

- [Evaluating Retrieval-Augmented Generation vs. Long-Context Input for Clinical Reasoning over EHRs](https://mlsanity.com/paper/2508.14817/) (2025)
- [CliniQ: A Multi-faceted Benchmark for Electronic Health Record Retrieval with Semantic Match Assessment](https://mlsanity.com/paper/2502.06252/) (2025)
- [Towards Efficient LLM-aware Heterogeneous Graph Learning](https://mlsanity.com/paper/2511.17923/) (2025)
- [DR.EHR: Dense Retrieval for Electronic Health Record with Knowledge Injection and Synthetic Data](https://mlsanity.com/paper/2507.18583/) (2025)
- [Investigating LLM Capabilities on Long Context Comprehension for Medical Question Answering](https://mlsanity.com/paper/2510.18691/) (2025)

## Abstract (arXiv)

Objective: Applying large language models (LLMs) to the clinical domain is challenging due to the context-heavy nature of processing medical records. Retrieval-augmented generation (RAG) offers a solution by facilitating reasoning over large text sources. However, there are many parameters to optimize in just the retrieval system alone. This paper presents an ablation study exploring how different embedding models and pooling methods affect information retrieval for the clinical domain. Methods: Evaluating on three retrieval tasks on two electronic health record (EHR) data sources, we compared seven models, including medical- and general-domain models, specialized encoder embedding models, and off-the-shelf decoder LLMs. We also examine the choice of embedding pooling strategy for each model, independently on the query and the text to retrieve. Results: We found that the choice of embedding model significantly impacts retrieval performance, with BGE, a comparatively small general-domain model, consistently outperforming all others, including medical-specific models. However, our findings also revealed substantial variability across datasets and query text phrasings. We also determined the best pooling methods for each of these models to guide future design of retrieval systems. Discussion: The choice of embedding model, pooling strategy, and query formulation can significantly impact retrieval performance and the performance of these models on other public benchmarks does not necessarily transfer to new domains. Further studies such as this one are vital for guiding empirically-grounded development of retrieval frameworks, such as in the context of RAG, for the clinical domain.