A Multi-Phase Analysis of Blood Culture Stewardship: Machine Learning Prediction, Expert Recommendation Assessment, and LLM Automation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Amrollahi, Fatemeh, Marshall, Nicholas, Haredasht, Fateme Nateghi, Black, Kameron C, Zahedivash, Aydin, Maddali, Manoj V, Ma, Stephen P., Chang, Amy, Deresinski, MD Phar Stanley C, Goldstein, Mary Kane, Asch, Steven M., Banaei, Niaz, Chen, Jonathan H
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915235710894080
author Amrollahi, Fatemeh
Marshall, Nicholas
Haredasht, Fateme Nateghi
Black, Kameron C
Zahedivash, Aydin
Maddali, Manoj V
Ma, Stephen P.
Chang, Amy
Deresinski, MD Phar Stanley C
Goldstein, Mary Kane
Asch, Steven M.
Banaei, Niaz
Chen, Jonathan H
author_facet Amrollahi, Fatemeh
Marshall, Nicholas
Haredasht, Fateme Nateghi
Black, Kameron C
Zahedivash, Aydin
Maddali, Manoj V
Ma, Stephen P.
Chang, Amy
Deresinski, MD Phar Stanley C
Goldstein, Mary Kane
Asch, Steven M.
Banaei, Niaz
Chen, Jonathan H
contents Blood cultures are often over ordered without clear justification, straining healthcare resources and contributing to inappropriate antibiotic use pressures worsened by the global shortage. In study of 135483 emergency department (ED) blood culture orders, we developed machine learning (ML) models to predict the risk of bacteremia using structured electronic health record (EHR) data and provider notes via a large language model (LLM). The structured models AUC improved from 0.76 to 0.79 with note embeddings and reached 0.81 with added diagnosis codes. Compared to an expert recommendation framework applied by human reviewers and an LLM-based pipeline, our ML approach offered higher specificity without compromising sensitivity. The recommendation framework achieved sensitivity 86%, specificity 57%, while the LLM maintained high sensitivity (96%) but over classified negatives, reducing specificity (16%). These findings demonstrate that ML models integrating structured and unstructured data can outperform consensus recommendations, enhancing diagnostic stewardship beyond existing standards of care.
format Preprint
id arxiv_https___arxiv_org_abs_2504_07278
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Multi-Phase Analysis of Blood Culture Stewardship: Machine Learning Prediction, Expert Recommendation Assessment, and LLM Automation
Amrollahi, Fatemeh
Marshall, Nicholas
Haredasht, Fateme Nateghi
Black, Kameron C
Zahedivash, Aydin
Maddali, Manoj V
Ma, Stephen P.
Chang, Amy
Deresinski, MD Phar Stanley C
Goldstein, Mary Kane
Asch, Steven M.
Banaei, Niaz
Chen, Jonathan H
Machine Learning
Artificial Intelligence
Blood cultures are often over ordered without clear justification, straining healthcare resources and contributing to inappropriate antibiotic use pressures worsened by the global shortage. In study of 135483 emergency department (ED) blood culture orders, we developed machine learning (ML) models to predict the risk of bacteremia using structured electronic health record (EHR) data and provider notes via a large language model (LLM). The structured models AUC improved from 0.76 to 0.79 with note embeddings and reached 0.81 with added diagnosis codes. Compared to an expert recommendation framework applied by human reviewers and an LLM-based pipeline, our ML approach offered higher specificity without compromising sensitivity. The recommendation framework achieved sensitivity 86%, specificity 57%, while the LLM maintained high sensitivity (96%) but over classified negatives, reducing specificity (16%). These findings demonstrate that ML models integrating structured and unstructured data can outperform consensus recommendations, enhancing diagnostic stewardship beyond existing standards of care.
title A Multi-Phase Analysis of Blood Culture Stewardship: Machine Learning Prediction, Expert Recommendation Assessment, and LLM Automation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2504.07278