Evidence map›Paper›PMID 41726397›Full record

ArticleAMIA ... Annual Symposium proceedings. AMIA Symposium2024

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

Fatemeh Amrollahi, Nicholas Marshall, Fateme Nateghi Haredasht, Kameron C Black, Aydin Zahedivash, Manoj V Maddali, Stephen P Ma, Amy Chang, Stanley C Deresinski, Mary Kane Goldstein and 3 more

Abstract read
PubMed Full text at PMC
In one paragraph

Article in AMIA ... Annual Symposium proceedings. AMIA Symposium, 2024. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 3 papers.

0numbers the graph read from it
0cells of the map it votes in
3citing papers in PubMed
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

3 citing papers in PubMed.

  1. Cultryx: Precision Diagnostic Stewardship for Blood Cultures Using Machine Learning.medRxiv : the preprint server for health sciences · 2026
    Article
  2. Article
  3. Article
4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

13 authors.

Fatemeh AmrollahiStanford Center for Biomedical Informatics Research, Stanford University, Stanford, CA, USA.
Nicholas MarshallDepartment of Medicine, Stanford University School of Medicine, Stanford, CA, USA.
Fateme Nateghi HaredashtStanford Center for Biomedical Informatics Research, Stanford University, Stanford, CA, USA.
Kameron C BlackDepartment of Medicine, Stanford University School of Medicine, Stanford, CA, USA.
Aydin ZahedivashDepartment of Medicine, Stanford University School of Medicine, Stanford, CA, USA.
Manoj V MaddaliStanford Center for Biomedical Informatics Research, Stanford University, Stanford, CA, USA.
Stephen P MaDepartment of Medicine, Stanford University School of Medicine, Stanford, CA, USA.
Amy ChangDepartment of Medicine, Stanford University School of Medicine, Stanford, CA, USA.
Stanley C DeresinskiDepartment of Medicine, Stanford University School of Medicine, Stanford, CA, USA.
Mary Kane GoldsteinDepartment of Health Policy, Stanford University School of Medicine, Stanford, CA, USA.
Steven M AschDepartment of Medicine, Stanford University School of Medicine, Stanford, CA, USA.
Niaz BanaeiDepartment of Medicine, Stanford University School of Medicine, Stanford, CA, USA.
Jonathan H ChenStanford Center for Biomedical Informatics Research, Stanford University, Stanford, CA, USA.

Funding

Measuring and Predicting Appropriate Antibiotic Use to Combat Resistant BacteriaR01AI178121 · NIAID · STANFORD UNIVERSITY · PI JONATHAN H. CHEN · 2023 to 2026
$3.1M
NIAID NIH HHS R01 AI178121
6 · The paper itself

Abstract

Blood cultures are often overordered without clear justification, straining healthcare resources and contributing to inappropriate antibiotic use-pressures worsened by the global shortage. In the study of 135,483 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 model's 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 offers higher specificity without compromising sensitivity. The recommendation framework achieved sensitivity 86%, specificity 57%, while the LLM maintained high sensitivity (96%) but overclassified 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.

Indexed as

Antimicrobial StewardshipBacteremiaBlood CultureLarge Language ModelsMachine LearningElectronic Health RecordsEmergency Service, HospitalHumansPredictive Learning ModelsSensitivity and Specificity

Identifiers

PMID41726397
PMCPMC12919529

What OpenQuestion holds

Textmetadata
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.