Acute Myeloid Leukemia: Diagnosis and Evaluation by Flow Cytometry

Area of Science:

• Hematology
• Oncology
• Computational Biology

Background:

• Modern acute myeloid leukemia (AML) classification requires integrating diverse data: immunophenotypic, cytogenetic, molecular, and clinical findings.
• Recent updates include the WHO Classification (WHO-HAEM5), International Consensus Classification (ICC), and European LeukemiaNet (ELN) 2022 recommendations.
• Flow cytometry is crucial for rapid, sensitive immunophenotyping in AML diagnosis, target identification, and MRD monitoring.

Purpose of the Study:

• To highlight the integration of flow cytometry and genetic data in AML classification and management.
• To discuss the role of machine learning in analyzing flow cytometry data for AML diagnosis and genetic prediction.

Main Methods:

• Utilizing multiparametric flow cytometry for immunophenotyping.
• Correlating immunophenotypic features with recurrent genetic abnormalities.
• Applying machine learning models to flow cytometric data for automated analysis.

Main Results:

• Established associations between immunophenotypic markers and genetic abnormalities in AML.
• Demonstrated the potential of machine learning for automated AML diagnosis.
• Showcased machine learning's capability in predicting genetic alterations from flow cytometry data.

Conclusions:

• Accurate AML diagnosis and prognostication necessitate integrating flow cytometry, genetic, and clinical data.
• Flow cytometry is indispensable for AML classification, therapeutic targeting, and MRD assessment.
• Machine learning shows promise in enhancing flow cytometry data analysis for AML management.