Machine learning for the identification of mild to moderate EDTA contamination of serum samples.

Authors

Christopher-John Lancaster Farrell, Julie Sherfan, Tony Badrick

Published in

Annals of clinical biochemistry. Pages 45632261488751. Sep 02, 2026. Epub Sep 02, 2026.

Abstract

Background K2EDTA contamination of serum samples is a preanalytical error that poses a risk to patient safety. Contamination is most frequently mild to moderate, which standard detection procedures often miss. We examined whether machine learning models could improve the detection of K2EDTA contamination. Methods Artificial neural network, decision tree (both simple and complex), extreme gradient boosting, k-nearest neighbours, logistic regression, naïve Bayes, random forest, and support vector machine models were developed. Models were trained using extracted patient results for electrolytes, urea, creatinine, albumin-adjusted calcium, magnesium, and phosphate, with K2EDTA contamination errors simulated in silico. Model performance was evaluated on 300 real-world samples, half of which were intentionally contaminated with mild to moderate amounts of K2EDTA. Model performance was compared with that of limit checks, multi-analyte rules and two novel parameters, the potassium/calcium ratio and the potassium/magnesium ratio. Results All nine machine learning models identified K2EDTA contamination more accurately than standard approaches (p-values <0.05). Seven models performed similarly, with accuracies of 91.3-93.3%, sensitivities of 88.0-90.0%, specificities of 94.7-96.7%, and area under the receiver operating characteristic curve (AUROC) of 0.9727-0.9787. The simple decision tree and naïve Bayes models performed slightly worse. The potassium/calcium ratio was the most effective of the standard approaches, with accuracy of 79.7%, sensitivity of 68.7%, specificity of 90.7%, and AUROC of 0.9233. Conclusions Using machine learning models would enable better detection of mild to moderate K2EDTA serum contamination and improve patient safety. For laboratories unable to implement machine learning models, the best alternative is the potassium/calcium ratio.

PMID:
42686407
Bibliographic data and abstract were imported from PubMed on 03 Sep 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.