Computational assessment of measurable residual disease in acute myeloid leukemia using mixture models

Abstract

The proportion of residual leukemic blasts after chemotherapy assessed by multiparameter flow cytometry, is an important prognostic factor for the risk of relapse and overall survival in acute myeloid leukemia (AML). This measurable residual disease (MRD) is used in clinical trials to stratify patients for more or less intensive consolidation therapy. However, an objective and reproducible analysis method to assess MRD status from flow cytometry data is lacking, yet is highly anticipated for broader implementation of MRD testing. We propose a computational pipeline based on Gaussian mixture modeling that allows a fully automated assessment of MRD status while remaining completely interpretable for clinical diagnostic experts. Our pipeline requires limited training data, which makes it easily transferable to other medical centers and cytometry platforms. We identify all healthy and leukemic immature myeloid cells in with high concordance (Spearman’s Rho = 0.974) and classification performance (median F-score = 0.861) compared to manual analysis. Using control samples (n = 18), we calculate a computational MRD percentage with high concordance to expert gating (Spearman’s rho = 0.823) and predict MRD status in a cohort of 35 AML follow-up measurements with high accuracy (97%). We demonstrate that our pipeline provides a powerful tool for fast (~3 s) and objective automated MRD assessment in AML. Cancer cells can be targeted with intensive chemotherapy in patients with acute myeloid leukemia (a type of blood cell cancer). However, disease can return after treatment due to the survival of cancer cells in the bone marrow. Identifying these cells is relevant to decide on future treatment options. However, this analysis is still performed manually by looking at a series of graphs to identify cancer and healthy cells. This process is labor-intensive, and results can differ based on the person performing the analysis. In this study, we demonstrate that this process can be automated using a computer algorithm (calculations), cutting the analysis time down from thirty minutes to three seconds. We anticipate that this can improve the accessibility and accuracy of diagnosing acute myeloid leukemia. Mocking et al. address the need for enhanced detection of measurable residual disease (MRD) in leukemia utilizing flow cytometry and computational methods. Their fully automated assessment of MRD status produces interpretable results for clinical diagnostic experts.