Related Experiment Video
Updated: Jan 13, 2026
Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence
Published on: January 27, 2023
Identification of IV fluid contamination in complete blood counts and subsequent unnecessary red blood cell
Carly Maucione1, Nathan McLamb1, Mark A Zaydman1
1Department of Pathology and Immunology, Washington University School of Medicine, St. Louis, Missouri, USA.
Insights
Machine learning models can now identify intravenous fluid contamination in complete blood counts (CBCs), improving laboratory accuracy. This helps prevent unnecessary transfusions and enhances patient safety.
Area of Science:
- Clinical Pathology
- Medical Informatics
- Machine Learning Applications
Background:
- Intravenous (IV) fluid contamination in blood samples causes significant complete blood count (CBC) measurement errors.
- Current methods lack a gold standard for retrospectively identifying IV contamination, hindering quality improvement.
Purpose of the Study:
- To develop and validate machine learning (ML) models for large-scale, retrospective identification of IV fluid contamination in CBC results.
- To assess the real-world applicability of these ML models across multiple institutions.
Main Methods:
- ML models were trained on simulated IV fluid contamination using hemoglobin, platelet, and white blood cell counts from CBCs.
- Models were validated against expert-reviewed datasets and tested on one year of real-world CBC data from two institutions.
Main Results:
- The ML models demonstrated high accuracy in distinguishing contaminated from non-contaminated CBC results (AUCs 0.972 and 0.957).
- ~2% of inpatient CBCs were predicted as contaminated, and 6%-9% of transfusions were potentially unnecessary.
- The models proved effective in identifying IV fluid contamination at scale.
Conclusions:
- Machine learning offers an efficient and effective method for identifying IV fluid contamination in CBCs.
- Further research, including prospective studies and real-time detection, is needed to fully realize benefits for patient safety and laboratory operations.
Background:
Specimens contaminated with intravenous (IV) fluids can lead to considerable measurement errors in complete blood counts (CBCs), posing challenges for laboratory operations and clinical decision-making. There is no gold-standard method for retrospectively identifying these events, making it difficult to target quality improvement initiatives or optimize laboratory detection protocols.
Study Design And Methods:
This study aimed to develop and validate machine learning (ML) models to retrospectively identify IV fluid contamination in CBC results at scale across two institutions. The models were trained on simulated contamination in CBCs using prior, current, and post hemoglobin concentrations, platelet counts, and white blood cell counts, then validated against expert-reviewed datasets. Real-world applicability was assessed using 1 year's worth of CBC results from each institution.
Results:
The models effectively discriminated contaminated from non-contaminated results on real-world datasets, with areas under the receiver operating characteristic curve of 0.972 and 0.957, and areas under the precision-recall curve of 0.723 and 0.619. In 1 year of CBC data, ~2% of inpatient CBC trios were predicted as contaminated across both institutions. 6%-9% of inpatient transfusions for which a CBC trio was available were deemed potentially unnecessary using a rule set validated by expert chart review.
Discussion:
The findings support the feasibility of using ML to identify IV fluid contamination in CBC results efficiently and effectively. Further work, including prospective real-world evaluations, targeted quality improvement initiatives, and development of real-time detection models, is necessary before realizing the potential benefits to patient safety, laboratory operations, and patient blood management.
Related Concept Videos
01:15Blood Transfusion
Blood Transfusion Overview
A blood transfusion is a medical procedure used to replace blood lost due to injury, surgery, or to treat conditions such as anemia or cancer. During a transfusion, donor blood is...
02:45Blood Transfusion and Agglutination
History
The history of blood transfusion dates back to the 17th century, when early attempts were made in animals. In 1818 James Blundell, a British doctor, performed the first successful human blood transfusion. Later in 1900, Karl...