The ALLgorithMM: How to define the hemodilution of bone marrow samples in lymphoproliferative diseases

Abstract

Introduction: Minimal residual disease (MRD) is commonly assessed in bone marrow (BM) aspirate. However, sample quality can impair the MRD measurement, leading to underestimated residual cells and to false negative results. To define a reliable and reproducible method for the assessment of BM hemodilution, several flow cytometry (FC) strategies for hemodilution evaluation have been compared.

Methods: For each BM sample, cells populations with a well-known distribution in BM and peripheral blood - e.g., mast cells (MC), immature (IG) and mature granulocytes (N) - have been studied by FC and quantified alongside the BM differential count.

Results: The frequencies of cells' populations were correlated to the IG/N ratio, highlighting a mild correlation with MCs and erythroblasts (R=0.25 and R=0.38 respectively, with p-value=0.0006 and 0.0000052), whereas no significant correlation was found with B or T-cells. The mild correlation between IG/N, erythroblasts and MCs supported the combined use of these parameters to evaluate BM hemodilution, hence the optimization of the ALLgorithMM. Once validated, the ALLgorithMM was employed to evaluate the dilution status of BM samples in the context of MRD assessment. Overall, we found that 32% of FC and 52% of Next Generation Sequencing (NGS) analyses were MRD negative in samples resulted hemodiluted (HD) or at least mildly hemodiluted (mHD).

Conclusions: The high frequency of MRD-negative results in both HD and mHD samples implies the presence of possible false negative MRD measurements, impairing the correct assessment of patients' response to therapy and highlighs the importance to evaluate BM hemodilution.

Keywords: acute lymphoblastic leukemia; flow cytometry; hemodilution; hemodilution/methods; measurable (minimal) residual disease; minimal residual disease; multiple myeloma.

Figure 1

Gating strategy to define BM population. (A) Difference between a non-hemodiluted sample (left) and a hemodiluted sample (right), as shown by the presence of both immature (purple) and mature granulocytes (blue): the maturation line of granulocytes (including promyelocytes, myelocytes and metamyelocytes) is highlithed in purple and is highly present in nonHD samples (on the left), wherease it is almost absent in HD samples (on the right). (B) Each plot is the result of the different gating strategies used to define different populations, according to FSC/SSC and the specific markers. In details, plot 1 displays immature (SSC++/FSC++; CD45dim/+/CD16low/CD10neg) and mature granulocytes (SSC++/FSC++; CD45dim/+/CD10+/CD16+), plot 2 shows erythroblasts (SSClow/FSClow; CD45neg/CD71+), plot 3 displays mast cells (SSC++/FSC++; CD45dim/CD117hi), plot 4 exhibits hematogones (SSClow; CD45dim/CD10+/CD81hi), plot 5 shows B-cells (SSClow; CD45hi/CD19+/CD56neg) and T-cells (NK-like T-cells/NK; SSClow; CD45hi/CD19neg/CD56hi), and plot 6 displays plasma cells (SSClow/FSC+; CD138hi).

Figure 2

Correlation analysis. (A) Correlation matrix related to all samples included in the study; the relative matrices for MM (B) and ALL patients (C). Positive correlations are displayed in red, while negative correlations are displayed in blue. Color intensity is defined by the correlation coefficient. Overall, the Pearson’s rho (R) for IG/N vs. mast cells and erythroblasts was ~0.3, with p<0.0006.

Figure 3

Correlation analysis with categorized parameters. Positive and negative correlations are presented in red and blue, respectively. Correlation coefficients are related to the color intensity. Once defined the cut-offs for the three parameters (IG/N, mast cells and erythroblasts (nucleated red blood cells, NRBCs), a higher correlation was observed between these categorized variables as compared to the same continuous variables shown in Figure 2 .

Figure 4

The ALLgorithMM sequence. For each BM aspirate, the definition of either hemodiluted or non-hemodiluted sample is the result of at least 2 out of 3 parameters, as analyzed by flow cytometry in the BM sample. Immature granulocytes (IG); mature granulocytes/neutrophils (N); erythroblasts (nucleated red blood cells, NRBCs); hemodiluted (HD); mildly hemodiluted (mHD); non-hemodiluted (nonHD).

Figure 5

Kruskal-Wallis distribution. Hemodiluted (HD, red), mildly hemodiluted (mHD, blue) and non-hemodiluted (non-HD, green) sample distribution related to the IG/N ratio (A), to the erythroblasts (nucleated red blood cells, NRBCs) (B) and to the mast cells presence (C). The distribution between groups has a p-value inferior to 2.4e10-9, indicating a statistically highly significant tendency. (***p < 0.0005 and ****p < 0.00005).

Figure 6

Correlation matrix between ALLgorithMM-defined BM hemodiluted (HD), mildlyHD (mHD) and non-hemodiluted (nonHD) vs. age (old or young), gender (female or male) and therapy used at the time of the sampling. Blue and red stand for negative or positive correlations, respectively. Color intensity is proportional to the correlation coefficients. The figure shows an absence of correlation between the 3 HD groups and others variables, confirming the robustness of the ALLgorithMM.

Figure 7

Correlation between in vitro and in silico-calculated data of ALLgorithMM parameters. The Pearson’s rho (R) accompanied by the relative p-value for (A) IG/N ratio, (B) mast cells, and (C) erythroblasts.