meds_reader: A fast and efficient EHR processing library

Ethan Steinberg, Michael Wornow, Suhana Bedi, Jason Alan Fries, Matthew B. A. McDermott +1 more
9/12/2024
cs.LGcs.DB

Official code: som-shahlab/meds_reader (21 stars, Apache-2.0, last commit 2026-01-26).

Abstract

The growing demand for machine learning in healthcare requires processing increasingly large electronic health record (EHR) datasets, but existing pipelines are not computationally efficient or scalable. In this paper, we introduce meds_reader, an optimized Python package for efficient EHR data processing that is designed to take advantage of many intrinsic properties of EHR data for improved speed. We then demonstrate the benefits of meds_reader by reimplementing key components of two major EHR processing pipelines, achieving 10-100x improvements in memory, speed, and disk usage. The code for meds_reader can be found at https://github.com/som-shahlab/meds_reader.

View on arXivView PDF

Code Implementations(1)

som-shahlab/meds_readerOfficial100%
Apache-2.0

A high-performance database and Python reader interface for MEDS datasets

212C++, ShellJun 21, 20248 months agoApache-2.0
ehrelectronic-health-recordfoundation-modelshealthcaremeds

Similar Papers

MEDS-Tab: Automated tabularization and baseline methods for MEDS datasets

82% match2024

EHRmonize: A Framework for Medical Concept Abstraction from Electronic Health Records using Large Language Models

80% match1 repo72024

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

79% match1 repo422024

CKD-EHR:Clinical Knowledge Distillation for Electronic Health Records

78% match1 repo12025

Rediscovery of CNN's Versatility for Text-based Encoding of Raw Electronic Health Records

78% match1 repo92023

CORE-BEHRT: A Carefully Optimized and Rigorously Evaluated BEHRT

77% match1 repo192024

Cite this paper

@article{steinberg2024medsreader,
  title  = {meds_reader: A fast and efficient EHR processing library},
  author = {Ethan Steinberg and Michael Wornow and Suhana Bedi and Jason Alan Fries and Matthew B. A. McDermott and Nigam H. Shah},
  year   = {2024},
  eprint = {2409.09095},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2409.09095v2}
}

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/2409.09095.svg)](https://codeofpaper.com/paper/2409.09095)

Discussion