Prospective and External Validation of an Ensemble Learning Approach to Sensitively Detect Intravenous Fluid Contamination in Basic Metabolic Panels
An accurate, generalizable, and explainable ensemble-based machine learning pipeline was developed and validated for sensitively detecting IV fluid contamination. Implementing this pipeline would help identify errors that are poorly detected by current clinical workflows and a previously described unsupervised machine learning-based method.
Authors
- Leah Militello (ORCID: https://orcid.org/0000-0002-8528-3366)
- Joe M El-Khoury (ORCID: https://orcid.org/0000-0002-9444-9540)
- Christopher W Farnsworth (ORCID: https://orcid.org/0000-0001-7169-3850)
- Thomas J S Durant (ORCID: https://orcid.org/0000-0003-1107-8148)
- Nicholas C. Spies (ORCID: https://orcid.org/0000-0002-5873-351X)
- Mark A. Zaydman (ORCID: https://orcid.org/0000-0002-4236-1459)
Institutions
- Washington University in St. Louis (US)
- University of Utah (US)
- Yale University (US)
- ARUP Laboratories (United States) (US)
Publication Details
- Journal
- Clinical Chemistry
- Published
- 2024-11-15
- DOI
- https://doi.org/10.1093/clinchem/hvae168
- Citations
- 5
- Primary Topic
- Clinical Laboratory Practices and Quality Control
- Type
- article
- Field-Weighted Citation Impact
- 1.63