Search

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. [ABSTRACT FROM AUTHOR]

Objectives The practicing pathologist is challenged by the ever-increasing diagnostic complexity of myeloid neoplasms. This guide is intended to provide a general roadmap from initial case detection, often triggered by complete blood count results with subsequent blood smear review, to final diagnosis. Methods The integration of hematologic, morphologic, immunophenotypic, and genetic features into routine practice is standard of care. The requirement for molecular genetic testing has increased along with the complexity of test types, the utility of different testing modalities in identifying key gene mutations, and the sensitivity and turnaround time for various assays. Results Classification systems for myeloid neoplasms have evolved to achieve the goal of providing a pathology diagnosis that enhances patient care, outcome prediction, and treatment options for individual patients and is formulated, endorsed, and adopted by hematologists/oncologists. Conclusions This guide provides diagnostic strategies for all myeloid neoplasm subtypes. Special considerations are provided for each category of testing and neoplasm category, along with classification information, genetic testing requirements, interpretation information, and case reporting recommendations based on the experience of 11 Bone Marrow Pathology Group members. [ABSTRACT FROM AUTHOR]