Diagnostic Stewardship of Blood Cultures in the Pediatric ICU Using Machine Learning
We trained and validated an ML model that accurately predicted >25% of subsequently negative blood cultures. If implemented prospectively, such models could help reduce unnecessary blood cultures among low-risk children.
Authors
- Christopher H. Greer
- Sarah J. Parker (ORCID: https://orcid.org/0000-0001-6007-5803)
- Sara J. Deakyne Davies (ORCID: https://orcid.org/0000-0002-8602-1624)
- Seth Russell (ORCID: https://orcid.org/0000-0002-2436-1367)
- Marisa Payan
- Peter E. DeWitt (ORCID: https://orcid.org/0000-0002-6391-0795)
- Blake Martin (ORCID: https://orcid.org/0000-0001-5683-8310)
- Charlotte Gray
- David J. Albers (ORCID: https://orcid.org/0000-0002-5369-526X)
- Halden F. Scott (ORCID: https://orcid.org/0000-0002-1412-6128)
- Tellen D. Bennett (ORCID: https://orcid.org/0000-0003-1483-4236)
- Charlotte Woods-Hill (ORCID: https://orcid.org/0000-0003-4886-0547)
Institutions
- Children's Hospital of Philadelphia (US)
- Children's Hospital Colorado (US)
- University of Colorado Denver (US)
Publication Details
- Journal
- Hospital Pediatrics
- Published
- 2025-05-22
- DOI
- https://doi.org/10.1542/hpeds.2024-008235
- Primary Topic
- Bacterial Identification and Susceptibility Testing
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Heart, Lung, and Blood Institute