EUVIMEDEUVIMED entdecken
Crossref

Automated prediction of acute promyelocytic leukemia from flow cytometry data using a graph neural network pipeline

Andrew M Cox iD, Daehwan Kim, Rolando García, Franklin S Fuda, Olga K Weinberg, Weina Chen iD

American Journal of Clinical Pathology · 01.03.2024 · 161 (3) · 264-272

DOI: 10.1093/ajcp/aqad145 ↗

Kurz gefasst

Fachartikel in der Zeitschrift American Journal of Clinical Pathology, online erschienen am 25.10.2023. Verfasst von Andrew M Cox und 5 weiteren Autor:innen. Beteiligte Einrichtung: Lyda Hill Department of Bioinformatics, UT Southwestern Medical Center, Dallas, TX, US. Hauptthemen laut MEDLINE: Leukemia, Promyelocytic, Acute, Decision Support Systems, Clinical. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 30 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

Our study aimed to develop a machine learning (ML) model to accurately classify acute promyelocytic leukemia (APL) from other types of acute myeloid leukemia (other AML) using multicolor flow cytometry (MFC) data. Multicolor flow cytometry is used to determine immunophenotypes that serve as disease signatures for diagnosis.

Methods

We used a data set of MFC files from 27 patients with APL and 41 patients with other AML, including those with uncommon immunophenotypes. Our ML pipeline involved training a graph neural network (GNN) to output graph-level labels and identifying the most crucial MFC parameters and cells for predictions using an input perturbation method.

Results

The top-performing GNN achieved 100% accuracy on the training/validation and test sets on classifying APL from other AML and used MFC parameters similarly to expert pathologists. Pipeline performance is amenable to use in a clinical decision support system, and our deep learning architecture readily enables prediction explanations.

Conclusions

Our ML pipeline shows robust performance on predicting APL and could be used to screen for APL using MFC data. It also allowed for intuitive interrogation of the model’s predictions by clinicians.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Leukemia, Promyelocytic, AcuteDecision Support Systems, ClinicalHumansFlow CytometryImmunophenotypingNeural Networks, Computer

Stichwörter der Autor:innen

acute myeloid leukemiaacute promyelocytic leukemiaflow cytometrygraph neural networkimmunophenotypemachine learning

Autor:innen und Institutionen

  • Lyda Hill Department of Bioinformatics, UT Southwestern Medical Center, Dallas, TX, US.
  • Department of Pathology, UT Southwestern Medical Center, Dallas, TX, US.

ORCID-Profile: Andrew M Cox, Weina Chen

Zitieren

APA

Cox, A. M., Kim, D., García, R., Fuda, F. S., Weinberg, O. K., & Chen, W. (2024). Automated prediction of acute promyelocytic leukemia from flow cytometry data using a graph neural network pipeline. American Journal of Clinical Pathology, 161(3), 264-272. https://doi.org/10.1093/ajcp/aqad145

Vancouver

Cox AM, Kim D, García R, Fuda FS, Weinberg OK, Chen W. Automated prediction of acute promyelocytic leukemia from flow cytometry data using a graph neural network pipeline. American Journal of Clinical Pathology. 2024;161(3):264-272. doi:10.1093/ajcp/aqad145

BibTeX
@article{Cox2024,
  author = {Cox, Andrew M and Kim, Daehwan and García, Rolando and Fuda, Franklin S and Weinberg, Olga K and Chen, Weina},
  title = {Automated prediction of acute promyelocytic leukemia from flow cytometry data using a graph neural network pipeline},
  journal = {American Journal of Clinical Pathology},
  year = {2024},
  volume = {161},
  number = {3},
  pages = {264--272},
  doi = {10.1093/ajcp/aqad145}
}
Kostenlos starten →