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.

Outcomes Associated With Neutropenia and Lymphopenia in Epidermal Necrolysis: A Single-Center Retrospective Study of 147 Patients.

This retrospective cohort study examines the association of lymphocyte and neutrophil levels with treatment outcomes in 147 patients with epidermal necrolysis in France.

[Myeloid neoplasms associated with rearrangement of PDGFRB: A rare and tricky disease]. / La néoplasie myéloïde associée à un réarrangement de PDGFRB : une pathologie rare de diagnostic difficile.

In the latest World Health Organization classification (WHO), eosinophilic disorders represent a group of rare pathologic conditions with highly heterogeneous pathophysiology. In this report, we describe a case of myeloid neoplasm associated with eosinophilia and rearrangement of PDGFRB gene in a 67-year-old-male patient hospitalized with cerebellous ataxia. Initial investigations showed a bicytopenia with hypereosinophilia varying from 1.1 to 1.6×109/L. Bone marrow aspiration was rich and showed a heterogeneous distribution of myeloid cells with clusters of promyelocytes and proerythroblasts associated with numerous eosinophils and spindle-shaped mast cells but without excess of blasts, dysplasia nor maturation skewing. These aspects suggested an atypical myeloproliferative neoplasm. Bone marrow biopsy was performed showing also a very high cellularity with area of myeloid and erythroid precursors associated with numerous spindle-shaped mast cells. Diagnoses of unclassified myeloid neoplasm and/or systemic mastocytosis were then proposed. Further chromosome analysis showed a t(5;8) translocation with PDGFRB rearrangement revealed in fluorescent in situ hybridization. Patient was treated with imatinib and intravenous immunoglobulin therapy allowing a significant improvement in neurological symptoms and biological results. Patient condition is currently stable after six lines of treatment. This rare hematopoietic neoplasm displays unusual histological and cytological features and can mimic other myeloproliferative neoplasm. Specific cytogenetics analysis should be considered for such cases with hypereosinophilia to select patients that may benefit from targeted therapy.

Macrophage migration inhibitory factor is overproduced through EGR1 in TET2low resting monocytes.

Somatic mutation in TET2 gene is one of the most common clonal genetic events detected in age-related clonal hematopoiesis as well as in chronic myelomonocytic leukemia (CMML). In addition to being a pre-malignant state, TET2 mutated clones are associated with an increased risk of death from cardiovascular disease, which could involve cytokine/chemokine overproduction by monocytic cells. Here, we show in mice and in human cells that, in the absence of any inflammatory challenge, TET2 downregulation promotes the production of MIF (macrophage migration inhibitory factor), a pivotal mediator of atherosclerotic lesion formation. In healthy monocytes, TET2 is recruited to MIF promoter and interacts with the transcription factor EGR1 and histone deacetylases. Disruption of these interactions as a consequence of TET2-decreased expression favors EGR1-driven transcription of MIF gene and its secretion. MIF favors monocytic differentiation of myeloid progenitors. These results designate MIF as a chronically overproduced chemokine and a potential therapeutic target in patients with clonal TET2 downregulation in myeloid cells.

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.

Cytokine-like protein 1-induced survival of monocytes suggests a combined strategy targeting MCL1 and MAPK in CMML.

Mouse models of chronic myeloid malignancies suggest that targeting mature cells of the malignant clone disrupts feedback loops that promote disease expansion. Here, we show that in chronic myelomonocytic leukemia (CMML), monocytes that accumulate in the peripheral blood show a decreased propensity to die by apoptosis. BH3 profiling demonstrates their addiction to myeloid cell leukemia-1 (MCL1), which can be targeted with the small molecule inhibitor S63845. RNA sequencing and DNA methylation pattern analysis both point to the implication of the mitogen-activated protein kinase (MAPK) pathway in the resistance of CMML monocytes to death and reveal an autocrine pathway in which the secreted cytokine-like protein 1 (CYTL1) promotes extracellular signal-regulated kinase (ERK) activation through C-C chemokine receptor type 2 (CCR2). Combined MAPK and MCL1 inhibition restores apoptosis of monocytes from patients with CMML and reduces the expansion of patient-derived xenografts in mice. These results show that the combined inhibition of MCL1 and MAPK is a promising approach to slow down CMML progression by inducing leukemic monocyte apoptosis.

Exome sequencing for diagnosis of congenital hemolytic anemia.

BACKGROUND: Congenital hemolytic anemia constitutes a heterogeneous group of rare genetic disorders of red blood cells. Diagnosis is based on clinical data, family history and phenotypic testing, genetic analyses being usually performed as a late step. In this study, we explored 40 patients with congenital hemolytic anemia by whole exome sequencing: 20 patients with hereditary spherocytosis and 20 patients with unexplained hemolysis. RESULTS: A probable genetic cause of disease was identified in 82.5% of the patients (33/40): 100% of those with suspected hereditary spherocytosis (20/20) and 65% of those with unexplained hemolysis (13/20). We found that several patients carried genetic variations in more than one gene (3/20 in the hereditary spherocytosis group, 6/13 fully elucidated patients in the unexplained hemolysis group), giving a more accurate picture of the genetic complexity of congenital hemolytic anemia. In addition, whole exome sequencing allowed us to identify genetic variants in non-congenital hemolytic anemia genes that explained part of the phenotype in 3 patients. CONCLUSION: The rapid development of next generation sequencing has rendered the genetic study of these diseases much easier and cheaper. Whole exome sequencing in congenital hemolytic anemia could provide a more precise and quicker diagnosis, improve patients' healthcare and probably has to be democratized notably for complex cases.

Heritability of fetal hemoglobin, white cell count, and other clinical traits from a sickle cell disease family cohort.

Sickle cell disease (SCD) is the most common monogenic disorder in the world. Notably, there is extensive clinical heterogeneity in SCD that cannot be fully accounted for by known factors, and in particular, the extent to which the phenotypic diversity of SCD can be explained by genetic variation has not been reliably quantified. Here, in a family-based cohort of 449 patients with SCD and 755 relatives, we first show that 5 known modifiers affect 11 adverse outcomes in SCD to varying degrees. We then utilize a restricted maximum likelihood procedure to estimate the heritability of 20 hematologic traits, including fetal hemoglobin (HbF) and white blood cell count (WBC), in the clinically relevant context of inheritance from healthy carriers to SCD patients. We report novel estimations of heritability for HbF at 31.6% (±5.4%) and WBC at 41.2% (±6.8%) in our cohort. Finally, we demonstrate shared genetic bases between HbF, WBC, and other hematologic traits, but surprisingly little overlap between HbF and WBC themselves. In total, our analyses show that HbF and WBC have significant heritable components among individuals with SCD and their relatives, demonstrating the value of using family-based studies to better understand modifiers of SCD.

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.