Identification of IV fluid contamination in complete blood counts and subsequent unnecessary red blood cell transfusions using artificial intelligence

TL;DR

This paper shows how artificial intelligence can detect IV fluid contamination in blood tests, which helps prevent unnecessary blood transfusions.

Contribution

The study introduces machine learning models to retrospectively identify IV fluid contamination in CBCs, enabling large-scale detection and evaluation of transfusion appropriateness.

Findings

Machine learning models achieved high accuracy (AUC 0.972 and 0.957) in identifying IV fluid contamination in CBC results.

Approximately 2% of inpatient CBC trios were predicted as contaminated, and 6–9% of transfusions were potentially unnecessary.

The models demonstrated real-world applicability across two institutions with strong discrimination performance.

Abstract

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.

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.

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.

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.

Figures