A Machine Learning Model for the Routine Detection of “Wrong Blood in Complete Blood Count Tube” Errors
Clinical Chemistry · 01.09.2023 · 69 (9) · 1031-1037
DOI: 10.1093/clinchem/hvad100 ↗Kurz gefasst
Fachartikel in der Zeitschrift Clinical Chemistry, online erschienen am 20.07.2023. Verfasst von Christopher-John Farrell und 5 weiteren Autor:innen. Beteiligte Einrichtung: Clinical Chemistry Department, NSW Health Pathology-Liverpool Hospital, Sydney, Australia. Hauptthemen laut MEDLINE: Medical Errors, Laboratories, Hospital. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 23 Literaturangaben.
Abstract (Originalsprache)
Background
Current laboratory procedures may fail to detect wrong blood in tube (WBIT) errors. Machine learning models have the potential to improve WBIT error detection, as demonstrated by proof-of-concept studies. The models developed so far, however, are not appropriate for routine use because they are unable to handle missing values and have low positive predictive value (PPV). In this study, a machine learning model suitable for routine use was developed.
Methods
A model was trained and a preliminary evaluation performed on a retrospective data set of 135 128 current and previous patient complete blood count (CBC) results. The model was then applied prospectively to routine samples tested in a public hospital laboratory over a period of 22 weeks. Each week, the 5 samples identified by the model as most likely to be WBIT errors underwent further investigation by testing blood group and red cell phenotype. The study assessed the number of WBIT errors that were missed by current procedures but detected by the model, as well as the PPV of the model.
Results
The model was applied prospectively to 38 187 CBC results that had passed routine laboratory checks. One hundred and ten samples were identified for further testing and 12 WBIT errors were detected. The PPV of the model was 10.9%.
Conclusion
A machine learning model suitable for routine use was able to identify WBIT errors missed by the laboratory’s current procedures. Machine learning models are valuable for the identification of WBIT errors, and their validation and deployment in clinical laboratories would improve patient safety.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Clinical Chemistry Department, NSW Health Pathology-Liverpool Hospital, Sydney, Australia.
- Transfusion Department, NSW Health Pathology-Nepean Hospital, Sydney, Australia.
- Haematology Department, NSW Health Pathology-Nepean Hospital, Sydney, Australia.
ORCID-Profile: Christopher-John Farrell
Zitieren
APA
Farrell, C. J., Makuni, C., Keenan, A., Maeder, E., Davies, G., & Giannoutsos, J. (2023). A Machine Learning Model for the Routine Detection of “Wrong Blood in Complete Blood Count Tube” Errors. Clinical Chemistry, 69(9), 1031-1037. https://doi.org/10.1093/clinchem/hvad100
Vancouver
Farrell CJ, Makuni C, Keenan A, Maeder E, Davies G, Giannoutsos J. A Machine Learning Model for the Routine Detection of “Wrong Blood in Complete Blood Count Tube” Errors. Clinical Chemistry. 2023;69(9):1031-1037. doi:10.1093/clinchem/hvad100
BibTeX
@article{Farrell2023,
author = {Farrell, Christopher-John and Makuni, Charles and Keenan, Aaron and Maeder, Ellena and Davies, Gareth and Giannoutsos, John},
title = {A Machine Learning Model for the Routine Detection of “Wrong Blood in Complete Blood Count Tube” Errors},
journal = {Clinical Chemistry},
year = {2023},
volume = {69},
number = {9},
pages = {1031--1037},
doi = {10.1093/clinchem/hvad100}
}
EUVIMED