Deep Learning Model For Personalized Prediction of Positive MRSA Culture Using Time-Series Electronic Health Records

Authors

Masayuki Nigo
Laila Rasmy
Bingyu Mao
Bijun Sai Kannadath
Ziqian Xie
Degui Zhi

Language

English

Publication Date

3-6-2024

Journal

Nature Communications

DOI

10.1038/s41467-024-46211-0

PMID

38448409

PMCID

PMC10917736

PubMedCentral® Posted Date

March 2024

PubMedCentral® Full Text Version

Post-Print

Abstract

Methicillin-resistant Staphylococcus aureus (MRSA) poses significant morbidity and mortality in hospitals. Rapid, accurate risk stratification of MRSA is crucial for optimizing antibiotic therapy. Our study introduced a deep learning model, PyTorch_EHR, which leverages electronic health record (EHR) time-series data, including wide-variety patient specific data, to predict MRSA culture positivity within two weeks. 8,164 MRSA and 22,393 non-MRSA patient events from Memorial Hermann Hospital System, Houston, Texas are used for model development. PyTorch_EHR outperforms logistic regression (LR) and light gradient boost machine (LGBM) models in accuracy (AUROC

Keywords

Humans, Deep Learning, Electronic Health Records, Methicillin-Resistant Staphylococcus aureus, Critical Care, Hospitals

Published Open-Access

yes

Recommended Citation

Nigo, Masayuki; Rasmy, Laila; Mao, Bingyu; et al., "Deep Learning Model For Personalized Prediction of Positive MRSA Culture Using Time-Series Electronic Health Records" (2024). Faculty, Staff and Student Publications. 333.
https://digitalcommons.library.tmc.edu/uthshis_docs/333