Cédric De Almeida Braga, Maxence Bauvais, Pierre Sujobert, Maël Heiblig, Maxime Jullien, Baptiste Le Calvez, Camille Richard, Valentin Le Roc'h, Emmanuelle Rault, Olivier Hérault, Pierre Peterlin, Alice Garnier, Patrice Chevallier, Simon Bouzy, Yannick Le Bris, Antoine Néel, Julie Graveleau, Olivier Kosmider, Perrine Paul‐Gilloteaux, Nicolas Normand, Marion Eveillard
{"title":"Deep Learning‐Based Blood Abnormalities Detection as a Tool for VEXAS Syndrome Screening","authors":"Cédric De Almeida Braga, Maxence Bauvais, Pierre Sujobert, Maël Heiblig, Maxime Jullien, Baptiste Le Calvez, Camille Richard, Valentin Le Roc'h, Emmanuelle Rault, Olivier Hérault, Pierre Peterlin, Alice Garnier, Patrice Chevallier, Simon Bouzy, Yannick Le Bris, Antoine Néel, Julie Graveleau, Olivier Kosmider, Perrine Paul‐Gilloteaux, Nicolas Normand, Marion Eveillard","doi":"10.1111/ijlh.14368","DOIUrl":"https://doi.org/10.1111/ijlh.14368","url":null,"abstract":"IntroductionVEXAS is a syndrome described in 2020, caused by mutations of the <jats:italic>UBA1</jats:italic> gene, and displaying a large pleomorphic array of clinical and hematological features. Nevertheless, these criteria lack significance to discriminate VEXAS from other inflammatory conditions at the screening step. This work hence first focused on singling out dysplastic features indicative of the syndrome among peripheral blood (PB) polymorphonuclears (PMN). A deep learning algorithm is then proposed for automatic detection of these features.MethodsA multicentric dataset, comprising 9514 annotated PMN images was gathered, including <jats:italic>UBA1</jats:italic> mutated VEXAS (<jats:italic>n</jats:italic> = 25), <jats:italic>UBA1</jats:italic> wildtype myelodysplastic (<jats:italic>n</jats:italic> = 14), and <jats:italic>UBA1</jats:italic> wildtype cytopenic patients (<jats:italic>n</jats:italic> = 25). Statistical analysis on a subset of patients was performed to screen for significant abnormalities. Detection of these features on PB was then automated with a convolutional neural network (CNN) for multilabel classification.ResultsSignificant differences were observed in the proportions of PMNs with pseudo‐Pelger, nuclear spikes, vacuoles, and hypogranularity between patients with VEXAS and both cytopenic and myelodysplastic controls.Automatic detection of these abnormalities yielded AUCs in the range [0.85–0.97] and a F1‐score of 0.70 on the test set. A VEXAS screening score was proposed, leveraging the model outputs and predicting the <jats:italic>UBA1</jats:italic> mutational status with 0.82 sensitivity and 0.71 specificity on the test patients.ConclusionThis study suggests that computer‐assisted analysis of PB smears, focusing on suspected VEXAS cases, can provide valuable insights for determining which patients should undergo molecular testing. The presented deep learning approach can help hematologists direct their suspicions before initiating further analyses.","PeriodicalId":14120,"journal":{"name":"International Journal of Laboratory Hematology","volume":"25 1","pages":""},"PeriodicalIF":3.0,"publicationDate":"2024-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142260777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Suwen Yang, Qianwen Hu, Xiaofen Wang, Sai Qiao, Chao Qi, Hong Jin, Yuhong Zhong
{"title":"Interferon Regulatory Factor 4: An Alternative Marker for Plasma Cells in Daratumumab‐Treated Patients With Multiple Myeloma","authors":"Suwen Yang, Qianwen Hu, Xiaofen Wang, Sai Qiao, Chao Qi, Hong Jin, Yuhong Zhong","doi":"10.1111/ijlh.14366","DOIUrl":"https://doi.org/10.1111/ijlh.14366","url":null,"abstract":"IntroductionAnti‐CD38 therapeutic modalities (e.g., daratumumab) can impede classical CD38 and CD138 gating use for plasma cell (PC) detection in multiple myeloma (MM) patients with minimal residual disease (MRD). We assessed the applicability of CD229, CD269, and interferon regulatory factor (IRF‐4) for PC detection in MM MRD patients.MethodsBone marrow samples were collected from patients with MM. Through multiparameter flow cytometry, we evaluated the suitability of CD229, CD269, and IRF‐4 for distinguishing PCs from other hematopoietic cells and compared their expression pattern on normal PCs (nPCs) and aberrant PCs (aPCs). We also assessed IRF‐4 expression stability after sample storage under different conditions. A 10‐color MRD antibody panel was used to determine whether IRF‐4 is an alternative primary PC‐gating marker for MM MRD assessment.ResultsIRF‐4 was expressed specifically on all PCs; its mean fluorescence intensity (MFI) was highest on PCs among all hematopoietic cells. This MFI did not decrease even after sample storage at 4°C or 25°C for 72 h. In all 42 MRD assessment samples, except for samples (<jats:italic>n</jats:italic> = 10) with no PCs, the use of IRF‐4 enabled accurate nPC (<jats:italic>n</jats:italic> = 12), aPC (<jats:italic>n</jats:italic> = 13), and nPC + aPC (<jats:italic>n</jats:italic> = 7) identification. Even samples from daratumumab‐treated patients had high IRF‐4 MFI, with no difference between pre‐treatment and post‐treatment (<jats:italic>n</jats:italic> = 7; <jats:italic>p</jats:italic> = 0.610).ConclusionsIRF‐4 demonstrates high MFI on PCs, and it is not expressed on other leukocytes. In MM patients with MRD, daratumumab treatment does not affect IRF‐4 expression. IRF‐4 is a promising marker for PC identification in MRD assessment of MM patients undergoing anti‐CD38 therapy.","PeriodicalId":14120,"journal":{"name":"International Journal of Laboratory Hematology","volume":"35 1","pages":""},"PeriodicalIF":3.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142260781","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A novel TNFRSF13B frameshift variant in one family with lymphoid neoplasms","authors":"Jing Li, Huici Gu, Shu Zhang, Xiaobo Mao, Junyan Zou, Xiaopeng Zhang, Guangxin Peng","doi":"10.1111/ijlh.14359","DOIUrl":"https://doi.org/10.1111/ijlh.14359","url":null,"abstract":"","PeriodicalId":14120,"journal":{"name":"International Journal of Laboratory Hematology","volume":"102 1","pages":""},"PeriodicalIF":3.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142260778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Matthew Kitchen, Michelle Bryant, Paula Brown, Anita Woolley, Steve Kitchen
{"title":"Frozen/Thawed Samples Can Replace Fresh Samples for Assignment of ISI to Secondary Thromboplastin Standards for Multiple Reagent/Instrument Combinations: Data to Support Possible Revision of WHO Guidelines","authors":"Matthew Kitchen, Michelle Bryant, Paula Brown, Anita Woolley, Steve Kitchen","doi":"10.1111/ijlh.14369","DOIUrl":"https://doi.org/10.1111/ijlh.14369","url":null,"abstract":"BackgroundCalibration of thromboplastins is required for accurate calculation of the international normalised ratio (INR). Accurate INR results are required for optimal dosing of vitamin K antagonists. Decreases in vitamin K antagonist usage have made the recruitment of sample sets for international sensitivity index (ISI) calibrations more difficult. A possible solution to this would be to allow the use of frozen–thawed samples in place of fresh plasmas in the calibration of secondary standards.ObjectivesWe investigated the effect of freezing and thawing samples before usage in ISI calibrations of secondary standards.MethodsMultiple reagent/instruments were tested to identify the degree of difference between a fresh sample ISI calibration and one performed on frozen–thawed samples. Where possible, the two ISI calibrations were performed on the same sample set. Alternatively, a separate set of samples from different patients was used.ResultsThe difference in ISI values was <3% for those datasets where the same samples were used, and <6% for those datasets where two sample sets were used. Additionally, other parameters required for a valid ISI calibration showed only minor differences—some calibrations showed fewer outliers in the frozen–thawed datasets. Mean normal prothrombin time for the international reference thromboplastins was <3.5% different across four different calibrations (two for rabbit thromboplastin and two for recombinant human thromboplastin).ConclusionsThis modification to the WHO guidelines would facilitate the recruitment of test plasmas in advance of calibration solving the problem of requiring availability of fresh patient samples with a range of INRs in a 5‐h window.Trial Registration: Not a part of any clinical trial.","PeriodicalId":14120,"journal":{"name":"International Journal of Laboratory Hematology","volume":"207 1","pages":""},"PeriodicalIF":3.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142260779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Alessio Lusci Gemignani, Robel Papotti, Riccardo Bomben, Valter Gattei, Samantha Pozzi, Valentina Donati, Stefania Bettelli, Elisa Forti, Giovanna Mansueto, Arianna Di Napoli, Maria Christina Cox, Leonardo Flenghi, Pietro Rossi, Guido Volpe, Dimitri Dardanis, Clara Bono, Francesca Guerrini, Riccardo Morganti, Stefano Sacchi, Sara Galimberti
{"title":"A new digital droplet PCR method for looking at epigenetics in diffuse large B‐cell lymphomas: The role of BMI1, EZH2, and USP22 genes","authors":"Alessio Lusci Gemignani, Robel Papotti, Riccardo Bomben, Valter Gattei, Samantha Pozzi, Valentina Donati, Stefania Bettelli, Elisa Forti, Giovanna Mansueto, Arianna Di Napoli, Maria Christina Cox, Leonardo Flenghi, Pietro Rossi, Guido Volpe, Dimitri Dardanis, Clara Bono, Francesca Guerrini, Riccardo Morganti, Stefano Sacchi, Sara Galimberti","doi":"10.1111/ijlh.14363","DOIUrl":"https://doi.org/10.1111/ijlh.14363","url":null,"abstract":"IntroductionEpigenetics has been shown to be relevant in oncology: <jats:italic>BMI1</jats:italic> overexpression has been reported in leukemias, <jats:italic>EZH2</jats:italic> mutations have been found in follicular lymphoma, and <jats:italic>USP22</jats:italic> seems to stabilize BMI1 protein. In this study, we measured the expression of <jats:italic>BMI1, EZH2</jats:italic>, and <jats:italic>USP22</jats:italic> in lymph nodes from 56 diffuse large B‐cell lymphoma (DLBCL) patients.MethodsA new multiplex digital droplet PCR (ddPCR) has been set up to measure the expression of 4 genes (<jats:italic>BMI1, EZH2, USP22</jats:italic>, and <jats:italic>GAPDH</jats:italic>) in the same reaction on RNA extracted from paraffin‐embedded tissues.ResultsThe specificity of ddPCR was confirmed by a 100% alignment on the BLAST platform and its repeatability demonstrated by duplicates. A strict correlation between expression of <jats:italic>BMI1</jats:italic> and <jats:italic>EZH2</jats:italic> and <jats:italic>BMI1</jats:italic> and <jats:italic>USP22</jats:italic> has been found, and high expression of these genes was correlated with extra‐nodal lymphomas. Progression‐free survival (PFS) and overall survival (OS) were conditioned by IPI, bone marrow infiltration, and the complete response achievement. High levels of <jats:italic>BMI1</jats:italic> and <jats:italic>USP22</jats:italic> did not condition the response to therapy, but impaired the PFS, especially for patients defined at “high risk” based on the cell of origin (no germinal center [GCB]), high BCL2 expression, and IPI 3‐5. In this subgroup, the probability of relapse/progression was twice higher than that of patients carrying low <jats:italic>BMI1</jats:italic> and <jats:italic>USP22</jats:italic> levels.ConclusionHigh expression of <jats:italic>BMI1</jats:italic> and of <jats:italic>USP22</jats:italic> might be a poor prognostic factor in DLBCL, and might represent the target for novel inhibitors.","PeriodicalId":14120,"journal":{"name":"International Journal of Laboratory Hematology","volume":"4 1","pages":""},"PeriodicalIF":3.0,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142218227","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Delphine De Smet, Dimitri Hemelsoet, Veerle De Herdt, Pieter M. De Kesel, Katrien M. J. Devreese
{"title":"Brief communication: Heparin-calibrated chromogenic anti-Xa assay for the detection of threshold-levels of direct oral anticoagulants","authors":"Delphine De Smet, Dimitri Hemelsoet, Veerle De Herdt, Pieter M. De Kesel, Katrien M. J. Devreese","doi":"10.1111/ijlh.14357","DOIUrl":"10.1111/ijlh.14357","url":null,"abstract":"","PeriodicalId":14120,"journal":{"name":"International Journal of Laboratory Hematology","volume":"46 6","pages":"1136-1139"},"PeriodicalIF":2.2,"publicationDate":"2024-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142038090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An automated method for thrombocyte counting in capillary microsamples","authors":"Caroline Vasard Boesen, Vibeke Staun Christensen, Klaus Rosenkilde Jensen, Anja Reinert Hansen, Claus Vinter Bødker Hviid","doi":"10.1111/ijlh.14354","DOIUrl":"10.1111/ijlh.14354","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Introduction</h3>\u0000 \u0000 <p>We aimed to develop an automated, low-volume method for thrombocyte counting in capillary blood using the Sysmex predilution (PD) mode.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>Microsamples were prepared by resuspension of 50 μL blood in 300 μL DCL CellPack. Thrombocyte counting was done in the impedance (PLT-I) and fluorescence (PLT-F) channels. The imprecision and bias was evaluated in >394 microsamples from adult blood. Preanalytical factors (skin-piercing, storage, and transportation in our pneumatic tube system) was assessed, and studies on pediatric microsamples were made for comparison. The improvement in analytical quality and turnaround time was examined.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>For PLT-F, the imprecision was 1.1%–3.7%, and the bias was 10.1% (95% CI: 8.8–11.3). After skin-piercing, the bias was 8.1% (95% CI: 5.6–10.6) and the imprecision 1.9% (95% CI: 1.3–2.5). Thrombocyte counts kept stable after 4 h at room temperature (94.8% [95% CI: 93.2–96.4]) and after pneumatic tube transportation [6.7% (95% CI: 4.8–8.6)]. The bias of the PD mode for pediatric microsamples was 13.0% (95% CI: −8.4–34.4) in the PLT-F channel. The automated method had a considerably lower imprecision than the existing manual thrombocyte counting method and reduced turnaround times.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusion</h3>\u0000 \u0000 <p>The automated microsample method offers a low-volume alternative for measurement of thrombocytes. The method appears useful also in pediatric samples.</p>\u0000 </section>\u0000 </div>","PeriodicalId":14120,"journal":{"name":"International Journal of Laboratory Hematology","volume":"46 6","pages":"1044-1051"},"PeriodicalIF":2.2,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/ijlh.14354","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141977464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Establishing reflex test rules for platelet fluorescent counting method using machine learning models on Sysmex XN-series hematology analyzer","authors":"Zhengyu Zhou, Mengqiao Guo, Kang Wu, Zhanyi Yue","doi":"10.1111/ijlh.14353","DOIUrl":"10.1111/ijlh.14353","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Introduction</h3>\u0000 \u0000 <p>The platelet fluorescent counting (PLT-F) method is utilized as a reflex test method following the initial test of the platelet impedance counting (PLT-I) method in clinical practice on the Sysmex XN-series automated hematology analyzer. Our aim is to establish reflex test rules for the PLT-F method by combining multiple parameters provided by the “CBC + DIFF” mode of the Sysmex XN-series automated hematology analyzer.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>We tested 120 samples to evaluate the baseline bias between the PLT-F and PLT-I methods. Then, we selected 1256 samples to establish and test reflex test rules using seven machine learning models (decision Tree, random forest, neural network, logistic regression, k-nearest neighbor, support vector machine, and Naive Bayes). The training set and test set were divided at a ratio of 7:3. We evaluated the performance of machine learning models on the test set using various metrics to select the most valuable model.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>The PLT-F method exhibited a high degree of correlation with the PLT-I method (r = 0.998). The random forest model emerged as the most valuable, boasting an accuracy of 0.893, an area under the curve of 0.954, an F1 score of 0.771, a recall of 0.719, a precision of 0.831, and a specificity of 0.950. The most important variable in the random forest model was mean cell volume, weighted at 15.09%.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusion</h3>\u0000 \u0000 <p>The random forest model, which demonstrated high efficiency in our study, can be used to establish PLT reflex test rules based on the PLT-F method for the Sysmex XN-series automated hematology analyzer.</p>\u0000 </section>\u0000 </div>","PeriodicalId":14120,"journal":{"name":"International Journal of Laboratory Hematology","volume":"46 6","pages":"1036-1043"},"PeriodicalIF":2.2,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141891345","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}