Multicentric study underlining the interest of adding CD5, CD7 and CD56 expression assessment to the flow cytometric Ogata score in myelodysplastic syndromes and myelodysplastic/myeloproliferative neoplasms.

Although numerous recent publications have demonstrated interest in multiparameter flow cytometry in the investigation of myelodysplastic disorders, it is perceived by many laboratory hematologists as difficult and expensive, requiring a high level of expertise. We report a multicentric open real-life study aimed at evaluating the added value of the technically simple flow cytometry score described by the Ogata group for the diagnosis of myelodysplastic syndromes. A total of 652 patients were recruited prospectively in four different centers: 346 myelodysplastic syndromes, 53 myelodysplastic/myeloproliferative neoplasms, and 253 controls. The Ogata score was assessed using CD45 and CD34 staining, with the addition of CD10 and CD19. Moreover, labeling of CD5, CD7 and CD56 for the evaluation of myeloid progenitors and monocytes was tested on a subset of 294 patients. On the whole series, the specificity of Ogata score reached 89%. Respective sensitivities were 54% for low-risk myelodysplastic syndromes, 68% and 84% for type 1 and type 2 refractory anemia with excess of blasts, and 72% for myelodysplastic/myeloproliferative neoplasms. CD5 expression was poorly informative. When adding CD56 or CD7 labeling to the Ogata score, sensitivity rose to 66% for low-risk myelodysplastic syndromes, to 89% for myelodysplastic/myeloproliferative neoplasms and to 97% for refractory anemia with excess of blasts. This large multicenter study confirms the feasibility of Ogata scoring in routine flow cytometry diagnosis but highlights its poor sensitivity in low-risk myelodysplastic syndromes. The addition of CD7 and CD56 in flow cytometry panels improves the sensitivity but more sophisticated panels would be more informative.

Evaluation of a machine-learning model based on laboratory parameters for the prediction of acute leukaemia subtypes: a multicentre model development and validation study in France.

BACKGROUND: Acute leukaemias are life-threatening haematological cancers characterised by the infiltration of transformed immature haematopoietic cells in the blood and bone marrow. Prompt and accurate diagnosis of the three main acute leukaemia subtypes (ie acute lymphocytic leukaemia [ALL], acute myeloid leukaemia [AML], and acute promyelocytic leukaemia [APL]) is of utmost importance to guide initial treatment and prevent early mortality but requires cytological expertise that is not always available. We aimed to benchmark different machine-learning strategies using a custom variable selection algorithm to propose an extreme gradient boosting model to predict leukaemia subtypes on the basis of routine laboratory parameters. METHODS: This multicentre model development and validation study was conducted with data from six independent French university hospital databases. Patients aged 18 years or older diagnosed with AML, APL, or ALL in any one of these six hospital databases between March 1, 2012, and Dec 31, 2021, were recruited. 22 routine parameters were collected at the time of initial disease evaluation; variables with more than 25% of missing values in two datasets were not used for model training, leading to the final inclusion of 19 parameters. The performances of the final model were evaluated on internal testing and external validation sets with area under the receiver operating characteristic curves (AUCs), and clinically relevant cutoffs were chosen to guide clinical decision making. The final tool, Artificial Intelligence Prediction of Acute Leukemia (AI-PAL), was developed from this model. FINDINGS: 1410 patients diagnosed with AML, APL, or ALL were included. Data quality control showed few missing values for each cohort, with the exception of uric acid and lactate dehydrogenase for the cohort from Hôpital Cochin. 679 patients from Hôpital Lyon Sud and Centre Hospitalier Universitaire de Clermont-Ferrand were split into the training (n=477) and internal testing (n=202) sets. 731 patients from the four other cohorts were used for external validation. Overall AUCs across all validation cohorts were 0·97 (95% CI 0·95-0·99) for APL, 0·90 (0·83-0·97) for ALL, and 0·89 (0·82-0·95) for AML. Cutoffs were then established on the overall cohort of 1410 patients to guide clinical decisions. Confident cutoffs showed two (0·14%) wrong predictions for ALL, four (0·28%) wrong predictions for APL, and three (0·21%) wrong predictions for AML. Use of the overall cutoff greatly reduced the number of missing predictions; diagnosis was proposed for 1375 (97·5%) of 1410 patients for each category, with only a slight increase in wrong predictions. The final model evaluation across both the internal testing and external validation sets showed accuracy of 99·5% for ALL diagnosis, 98·8% for AML diagnosis, and 99·7% for APL diagnosis in the confident model and accuracy of 87·9% for ALL diagnosis, 86·3% for AML diagnosis, and 96·1% for APL diagnosis in the overall model. INTERPRETATION: AI-PAL allowed for accurate diagnosis of the three main acute leukaemia subtypes. Based on ten simple laboratory parameters, its broad availability could help guide initial therapies in a context where cytological expertise is lacking, such as in low-income countries. FUNDING: None.

Automated Detection of Dysplasia: Data Mining from Our Hematology Analyzers.

Myelodysplastic syndromes (MDSs) are clonal hematopoietic diseases of the elderly, characterized by chronic cytopenia, ineffective and dysplastic hematopoiesis, recurrent genetic abnormalities and increased risk of progression to acute myeloid leukemia. Diagnosis on a complete blood count (CBC) can be challenging due to numerous other non-neoplastic causes of cytopenias. New generations of hematology analyzers provide cell population data (CPD) that can be exploited to reliably detect MDSs from a routine CBC. In this review, we first describe the different technologies used to obtain CPD. We then give an overview of the currently available data regarding the performance of CPD for each lineage in the diagnostic workup of MDSs. Adequate exploitation of CPD can yield very strong diagnostic performances allowing for faster diagnosis and reduction of time-consuming slide reviews in the hematology laboratory.

Machine learning identifies the independent role of dysplasia in the prediction of response to chemotherapy in AML.

The independent prognostic impact of specific dysplastic features in acute myeloid leukemia (AML) remains controversial and may vary between genomic subtypes. We apply a machine learning framework to dissect the relative contribution of centrally reviewed dysplastic features and oncogenetics in 190 patients with de novo AML treated in ALFA clinical trials. One hundred and thirty-five (71%) patients achieved complete response after the first induction course (CR). Dysgranulopoiesis, dyserythropoiesis and dysmegakaryopoiesis were assessable in 84%, 83% and 63% patients, respectively. Multi-lineage dysplasia was present in 27% of assessable patients. Micromegakaryocytes (q = 0.01), hypolobulated megakaryocytes (q = 0.08) and hyposegmented granulocytes (q = 0.08) were associated with higher ELN-2017 risk. Using a supervised learning algorithm, the relative importance of morphological variables (34%) for the prediction of CR was higher than demographic (5%), clinical (2%), cytogenetic (25%), molecular (29%), and treatment (5%) variables. Though dysplasias had limited predictive impact on survival, a multivariate logistic regression identified the presence of hypolobulated megakaryocytes (p = 0.014) and micromegakaryocytes (p = 0.035) as predicting lower CR rates, independently of monosomy 7 (p = 0.013), TP53 (p = 0.004), and NPM1 mutations (p = 0.025). Assessment of these specific dysmegakarypoiesis traits, for which we identify a transcriptomic signature, may thus guide treatment allocation in AML.

Reference Values for WBC Differential by Hematoflow Analysis.

Objectives: WBC differentials performed using flow cytometry with monoclonal antibodies have been developed in the last decade and are nowadays integrated into the routine workflow of some laboratories. Definition of reference values for each population is required in order to achieve an automatic validation of the results by laboratory software. Methods: We analyzed 584 samples from three hospitals using the Hematoflow solution to define the reference values. Results: Reference values are presented for five groups according to age (0-5, 6-11, 12-19, 20-69, and >69 years). Conclusions: These normal values will be helpful in the definition of relevant threshold for the automatic validation of samples analyzed by flow cytometry and the flagging of pathologic samples.

High sensitivity of the Hematoflow™ solution for chronic myelomonocytic leukemia screening.

BACKGROUND: Accumulation of classical monocytes CD14++ CD16- (also called MO1) ≥ 94% can accurately distinguish chronic myelomonocytic leukemia (CMML) from reactive monocytosis. The HematoFlow™ solution, able to quantify CD16 negative monocytes, could be a useful tool to manage monocytosis which remains a common issue in routine laboratories. METHODS: Classical monocytes were quantified from 153 whole blood samples collected on EDTA using both flow cytometry methods, either MO1 percentage determination by the multiparameter assay previously published and regarded here as the reference method, or CD16 negative monocyte percentage determination by the means of HematoFlow™. RESULTS: Both methods of classical monocyte percentage determination were highly and significantly correlated (r = 0.87, P < 0.0001). The HematoFlow™ solution leant toward an overestimation of the genuine classical monocyte percentages obtained by the reference method. Percentages of CD16 negative monocytes provided by HematoFlow were higher than 94% for all the 73 patients displaying classical monocytes MO1 found ≥94% by the reference method, indicating a sensitivity of 100%. Furthermore, the calculation of CD16 negative monocyte percentage can be easily computerized and integrated to the middleware. CONCLUSIONS: We propose a new application of the Hematoflow™ solution that can be used as a flag system for monocytosis management and CMML detection. © 2017 International Clinical Cytometry Society.