Clinical validation of a real‐time machine learning‐based system for the detection of acute myeloid leukemia by flow cytometry
Cytometry Part B: Clinical Cytometry · 2025-09 · 108 (5) · 392-403
DOI: 10.1002/cyto.b.22229 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift Cytometry Part B: Clinical Cytometry, online erschienen am 27.02.2025. Verfasst von Lauren M Zuromski und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Applied Artificial Intelligence and Bioinformatics, Institute for Research and Innovation, ARUP Laboratories, Salt Lake City, Utah, USA. Hauptthemen laut MEDLINE: Leukemia, Myeloid, Acute, Machine Learning, Flow Cytometry. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Machine‐learning (ML) models in flow cytometry have the potential to reduce error rates, increase reproducibility, and boost the efficiency of clinical labs. While numerous ML models for flow cytometry data have been proposed, few studies have described the clinical deployment of such models. Realizing the potential gains of ML models in clinical labs requires not only an accurate model but also infrastructure for automated inference, error detection, analytics and monitoring, and structured data extraction. Here, we describe an ML model for the detection of Acute Myeloid Leukemia (AML), along with the infrastructure supporting clinical implementation. Our infrastructure leverages the resilience and scalability of the cloud for model inference, a Kubernetes‐based workflow system that provides model reproducibility and resource management, and a system for extracting structured diagnoses from full‐text reports. We also describe our model monitoring and visualization platform, an essential element for ensuring continued model accuracy. Finally, we present a post‐deployment analysis of impacts on turn‐around time and compare production accuracy to the original validation statistics.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Applied Artificial Intelligence and Bioinformatics, Institute for Research and Innovation, ARUP Laboratories, Salt Lake City, Utah, USA.
- Hematologic Flow Cytometry, ARUP Laboratories, Salt Lake City, Utah, USA.
- Institute for Clinical and Experimental Pathology, ARUP Laboratories, Salt Lake City, Utah, USA.
- Department of Pathology, University of Utah, Salt Lake City, Utah, USA.
ORCID-Profile: David P Ng
Zitieren
APA
Zuromski, L. M., Durtschi, J., Aziz, A., Chumley, J., Dewey, M., English, P., Morrison, M., Simmon, K., Whipple, B., O'Fallon, B., & Ng, D. P. (2025). Clinical validation of a real‐time machine learning‐based system for the detection of acute myeloid leukemia by flow cytometry. Cytometry Part B: Clinical Cytometry, 108(5), 392-403. https://doi.org/10.1002/cyto.b.22229
Vancouver
Zuromski LM, Durtschi J, Aziz A, Chumley J, Dewey M, English P, et al. Clinical validation of a real‐time machine learning‐based system for the detection of acute myeloid leukemia by flow cytometry. Cytometry Part B: Clinical Cytometry. 2025;108(5):392-403. doi:10.1002/cyto.b.22229
BibTeX
@article{Zuromski2025,
author = {Zuromski, Lauren M and Durtschi, Jacob and Aziz, Aimal and Chumley, Jeffrey and Dewey, Mark and English, Paul and Morrison, Muir and Simmon, Keith and Whipple, Blaine and O'Fallon, Brendan and Ng, David P},
title = {Clinical validation of a real‐time machine learning‐based system for the detection of acute myeloid leukemia by flow cytometry},
journal = {Cytometry Part B: Clinical Cytometry},
year = {2025},
volume = {108},
number = {5},
pages = {392--403},
doi = {10.1002/cyto.b.22229}
}
EUVIMED