RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records

Ran Xu, Wenqi Shi, Yue Yu, Yuchen Zhuang, Bowen Jin +3 more
2/25/2024
cs.CLcs.AIcs.IR

Official code: ritaranx/RAM-EHR (42 stars, MIT, last commit 2024-09-19).

Abstract

We present RAM-EHR, a Retrieval AugMentation pipeline to improve clinical predictions on Electronic Health Records (EHRs). RAM-EHR first collects multiple knowledge sources, converts them into text format, and uses dense retrieval to obtain information related to medical concepts. This strategy addresses the difficulties associated with complex names for the concepts. RAM-EHR then augments the local EHR predictive model co-trained with consistency regularization to capture complementary information from patient visits and summarized knowledge. Experiments on two EHR datasets show the efficacy of RAM-EHR over previous knowledge-enhanced baselines (3.4% gain in AUROC and 7.2% gain in AUPR), emphasizing the effectiveness of the summarized knowledge from RAM-EHR for clinical prediction tasks. The code will be published at \url{https://github.com/ritaranx/RAM-EHR}.

View on arXivView PDF

Code Implementations(1)

ritaranx/RAM-EHROfficial100%
MIT

[ACL 2024] This is the code for our paper ”RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records“.

424Shell, PythonFeb 23, 20242 years agoMIT
clinicalelectronic-health-recordhealthcarellmmedical+2 more

Similar Papers

DR.EHR: Dense Retrieval for Electronic Health Record with Knowledge Injection and Synthetic Data

83% match2025

EMERGE: Enhancing Multimodal Electronic Health Records Predictive Modeling with Retrieval-Augmented Generation

82% match2 repos162024

Evaluating Retrieval-Augmented Generation vs. Long-Context Input for Clinical Reasoning over EHRs

81% match2025

Large Language Models are Powerful Electronic Health Record Encoders

81% match1 repo22025

Health-LLM: Personalized Retrieval-Augmented Disease Prediction System

81% match2024

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

80% match2024

Cite this paper

@article{xu2024ramehr,
  title  = {RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records},
  author = {Ran Xu and Wenqi Shi and Yue Yu and Yuchen Zhuang and Bowen Jin and May D. Wang and Joyce C. Ho and Carl Yang},
  year   = {2024},
  eprint = {2403.00815},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2403.00815v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2403.00815.svg)](https://codeofpaper.com/paper/2403.00815)

Discussion