Machine learning-based improvement of MDS-CBC score brings platelets into the limelight to optimize smear review in the hematology laboratory.

BACKGROUND: Myelodysplastic syndromes (MDS) are clonal hematopoietic diseases of the elderly characterized by chronic cytopenias, ineffective and dysplastic haematopoiesis, recurrent genetic abnormalities and increased risk of progression to acute myeloid leukemia. A challenge of routine laboratory Complete Blood Counts (CBC) is to correctly identify MDS patients while simultaneously avoiding excess smear reviews. To optimize smear review, the latest generations of hematology analyzers provide new cell population data (CPD) parameters with an increased ability to screen MDS, among which the previously described MDS-CBC Score, based on Absolute Neutrophil Count (ANC), structural neutrophil dispersion (Ne-WX) and mean corpuscular volume (MCV). Ne-WX is increased in the presence of hypogranulated/degranulated neutrophils, a hallmark of dysplasia in the context of MDS or chronic myelomonocytic leukemia. Ne-WX and MCV are CPD derived from leukocytes and red blood cells, therefore the MDS-CBC score does not include any platelet-derived CPD. We asked whether this score could be improved by adding the immature platelet fraction (IPF), a CPD used as a surrogate marker of dysplastic thrombopoiesis. METHODS: Here, we studied a cohort of more than 500 individuals with cytopenias, including 168 MDS patients. In a first step, we used Breiman's random forests algorithm, a machine-learning approach, to identify the most relevant parameters for MDS prediction. We then designed Classification And Regression Trees (CART) to evaluate, using resampling, the effect of model tuning parameters on performance and choose the "optimal" model across these parameters. RESULTS: Using random forests algorithm, we identified Ne-WX and IPF as the strongest discriminatory predictors, explaining 37 and 33% of diagnoses respectively. To obtain "simplified" trees, which could be easily implemented into laboratory middlewares, we designed CART combining MDS-CBC score and IPF. Optimal results were obtained using a MDS-CBC score threshold equal to 0.23, and an IPF threshold equal to 3%. CONCLUSIONS: We propose an extended MDS-CBC score, including CPD from the three myeloid lineages, to improve MDS diagnosis on routine laboratory CBCs and optimize smear reviews.

Optimization of CSF biological investigations for CNS lymphoma diagnosis.

Diagnosis of lymphoma leptomeningeal dissemination is challenging and relies on a wide array of methods. So far, no consensus biological guidelines are available. This increases the chance of intra- and interpractice variations, despite the shared concern to perform the minimum amount of tests while preserving clinically relevant results.We evaluated a training cohort of 371 cerebrospinal fluid (CSF) samples from patients with putative lymphomatous central nervous system (CNS) localization using conventional cytology (CC), flow cytometry (FCM), molecular clonality assesment by PCR and cytokine quantification (CQ). This led us to propose a biological algorithm, which was then verified on a validation cohort of 197 samples. The samples were classified according to the clinical context and the results of each technique were compared. Using all four techniques was not useful for exclusion diagnosis of CNS lymphoma (CNSL), but they proved complementary for cases with suspected CNSL. This was particularly true for CQ in primary CNSL. Overall, diagnosis can be obtained with a two-step approach. The first step comprises CC and FCM, as results are available quickly and FCM is a sensitive method. Both PCR and CQ can be postponed and performed in a second step, depending on the results from the first step and the clinical context.The proposed algorithm missed none of the CNSL samples of the validation cohort. Moreover, applying this algorithm would have spared 30% of PCR tests and 20% of CQ over a one-year period, without compromising clinical management.

A new approach for diagnosing chronic myelomonocytic leukemia using structural parameters of Sysmex XNTM analyzers in routine laboratory practice.

According to WHO recommendations, diagnosis of chronic myelomonocytic leukemia (CMML) beforehand requires microscopic examination of peripheral blood to identify dysplasia and/or blasts when monocytes are greater or equal to 1.0 × 109/L and 10% of leucocytes. We analyzed parameters derived from SysmexTM XN analyzers to improve the management of microscopic examination for monocytosis. We analyzed results of the complete blood count and the positioning and dispersion parameters of polymorphonuclear neutrophils and monocytes in 61 patients presenting with CMML and 635 control patients presenting with a reactive monocytosis. We used logistic regression and multivariate analysis to define a score for smear review. Three parameters were selected: neutrophil/monocyte ratio, structural neutrophil dispersion (Ne-WX) and monocyte absolute value. We established an equation in which the threshold of 0.160 guided microscopic examination in the search for CMML abnormalities with a sensitivity of 0.967 and a specificity of 0.978 in the learning cohort (696 samples) and 0.923 and 0.936 in the validation cohort (1809 samples) respectively. We created a score for microscopic smear examination of patients presenting with a monocytosis greater or equal to 1.0 × 109/L and 10% of leucocytes, improving efficiency in laboratory routine practice.

Usefulness of thresholds for smear review of neutropenic samples analyzed with a Sysmex XN-10 analyzer.

Neutropenia is one of the main criteria for a blood smear review. The objective of this study was to compare the thresholds proposed by the international consensus group for hematology review (1.0 109/L) and the French speaking Group for Cellular Haematology (1.5 109/L) in terms of the number of useless smears. We collected 112,097 analyzed samples from four laboratories equipped with XN instruments (Sysmex, Kobe, Japan) during early 2016. The only exclusion criterion was a leucocyte count below 0.5 109/L. In the absence of abnormal cells and/or morphology suggesting haematological disease, samples were classified as 'negative for morphology' and the differential from the XN-10 was reported. These smear procedures were considered as uninformative. Some 2202 samples met the criterion for neutropenia (<1.5 109/L) for slide review representing 1.96% of the total. These included 1031 with neutropenia alone and 1171 neutropenia plus other abnormalities. Of the 1031 with neutropenia alone, 886 had a neutrophil count between 1.0 109/L and 1.5 109/L. The smear was uninformative for all of these samples. In conclusion, microscopic examination of a blood smear provided very limited information in cases of neutropenia without other abnormalities.

White blood cells scattergram as a valuable tool for COVID-19 screening: A multicentric study.

INTRODUCTION: New tools have been developed to distinguish the COVID-19 diagnosis from other viral infections presenting similar symptomatology and mitigate the lack of sensitivity of molecular testing. We previously identified a specific "sandglass" aspect on the white blood cells (WBC) scattergram of COVID-19 patients, as a highly reliable COVID-19 screening test (sensitivity: 85.9%, specificity: 83.5% and positive predictive value: 94.3%). We then decided to validate our previous data in a multicentric study. METHODS: This retrospective study involved 817 patients with flu-like illness, among 20 centers, using the same CBC instrument (XN analyzer, SYSMEX, Japan). After training, one specialist per center independently evaluated, under the same conditions, the presence of the "sandglass" aspect of the WDF scattergram, likely representing plasmacytoid lymphocytes. RESULTS: Overall, this approach showed sensitivity: 59.0%, specificity: 72.9% and positive predictive value: 77.7%. Sensitivity improved with subgroup analysis, including in patients with lymphopenia (65.2%), patients presenting symptoms for more than 5 days (72.3%) and in patients with ARDS (70.1%). COVID-19 patients with larger plasmacytoid lymphocyte cluster (>15 cells) more often have severe outcomes (70% vs. 15% in the control group). CONCLUSION: Our findings confirm that the WBC scattergram analysis could be added to a diagnostic algorithm for screening and quickly categorizing symptomatic patients as either COVID-19 probable or improbable, especially during COVID-19 resurgence and overlapping with future influenza epidemics. The observed large size of the plasmacytoid lymphocytes cluster appears to be a hallmark of COVID-19 patients and was indicative of a severe outcome. Furthers studies are ongoing to evaluate the value of the new hematological parameters in combination with WDF analysis.

Can the 72-hour rule based on "Blast/Abn Lymph" flag on Sysmex XN-10 optimize the workflow in hematology laboratory?

Despite the continuing improvement of automated blood cell counters, confirmation by blood smear examination remains the gold standard in case of anomalies. With a constant goal of standardisation, different experts committees (e.g. the French-speaking cellular hematology group (Groupe francophone d'hématologie cellulaire, GFHC and the ISLH International society for laboratory hematology) recently published criteria for microscopic analysis of blood smears. Cornet et al. evaluated the application of those criteria and propose to suppress any review for 72 hours when a "Blast/Abn lymph" flag is triggered for a sample with no abnormal cell on the microscopic review. The aims of our study were to retrospectively evaluate whether this 72-hour rule adequately operates and whether it is possible to extend the arbitrary 72-hour timeframe to 96h and 144h. To achieve this goal, 40,688 blood samples were collected from three French-speaking hospitals. 1,548 samples presented an isolated "Blast/Abn lymph" flag. Only 221 samples presented the application of the 72-hour rule at least once for our study period. We were able to extend this rule to 144 hours for 10 samples of them. All blood smears for which the rule was applied were verified and there was no abnormal cell on smears at 72 and 144 hours. In conclusion, the 72-hour rule derived from the GFHC's criteria is secure and reduces the slide review rate and thus the production costs and the turnaround time of hemogram results. Further investigations could confirm that its extension to 144 hours is also adequate.

A hierarchical approach in the diagnostic workflow of chronic myelomonocytic leukemia: Pivotal role of the "Mono-dysplasia-score" combined with flow cytometric quantification of monocyte subsets.

INTRODUCTION: Monocytosis is a frequent trigger for blood smear review in a routine hematology laboratory whereas chronic myelomonocytic leukemia (CMML) is infrequent and arises mostly in elderly patients. In order to define the best workflow for monocytosis, we studied three diagnostic approaches: the classical morphology approach (blood smear review), the flow cytometry assay (quantification of monocyte subsets as described by Selimoglu-Buet et al in 2015), and the "mono-dysplasia-score" also referred to as "Monoscore (as described by our team in 2018 using the structural parameters of the Sysmex XN™ analyzers). METHODS: Studying a multicentric cohort of 196 nonclonal monocytoses and CMML patients aged over 50 years, we compared the diagnostic performance of the three approaches alone and in combination to propose a diagnostic decision tree. RESULTS: In patients presenting with additional criteria for slide review to monocytosis (37% of our cohort), we propose to sequentially combine morphology, Monoscore, and flow cytometry. On the contrary, for patients with isolated monocytosis (63%), slide review is not mandatory and we suggest performing flow cytometry depending on the Monoscore value. Using the proposed algorithm, 98% of CMML patients would have been correctly identified, slide review rate drastically reduced, and flow cytometry would have been carried out in 44% of patients. CONCLUSION: We have shown that implementation of Monoscore is a useful input filter to significantly reduce slide reviews without losing sensitivity and that flow cytometry is a performant technique in the second step of the diagnostic workup of CMML.