Deep learning model for differentiating acute myeloid and lymphoblastic leukemia in peripheral blood cell images via myeloblast and lymphoblast classification.

Objective: Acute leukemia (AL) is a life-threatening malignant disease that occurs in the bone marrow and blood, and is classified as either acute myeloid leukemia (AML) or acute lymphoblastic leukemia (ALL). Diagnosing AL warrants testing methods, such as flow cytometry, which require trained professionals, time, and money. We aimed to develop a model that can classify peripheral blood images of 12 cell types, including pathological cells associated with AL, using artificial intelligence. Methods: We acquired 42,386 single-cell images of peripheral blood slides from 282 patients (82 with AML, 40 with ALL, and 160 with immature granulocytes). Results: The performance of EfficientNet-V2 (B2) using the original image size exhibited the greatest accuracy (accuracy, 0.8779; precision, 0.7221; recall, 0.7225; and F1 score, 0.7210). The next-best accuracy was achieved by EfficientNet-V1 (B1), with a 256 × 256 pixels image. F1 score was the greatest for EfficientNet-V1 (B1) with the original image size. EfficientNet-V1 (B1) and EfficientNet-V2 (B2) were used to develop an ensemble model, and the accuracy (0.8858) and F1 score (0.7361) were improved. The classification performance of the developed ensemble model for the 12 cell types was good, with an area under the receiver operating characteristic curve above 0.9, and F1 scores for myeloblasts and lymphoblasts of 0.8873 and 0.8006, respectively. Conclusions: The performance of the developed ensemble model for the 12 cell classifications was satisfactory, particularly for myeloblasts and lymphoblasts. We believe that the application of our model will benefit healthcare settings where the rapid and accurate diagnosis of AL is difficult.

Integration of an MC-80 Digital Image Analyzer With an Automated BC-6800Plus Hematology Analyzer Enables Accurate Platelet Counting in Samples With EDTA-Induced Pseudothrombocytopenia.

Background: EDTA-induced pseudothrombocytopenia (PTCP) during whole blood collection requires significant laboratory resources to obtain accurate results. We evaluated platelet-deaggregation function in EDTA-induced PTCP and platelet-clump flagging by the BC-6800Plus hematology analyzer using integrated digital image analysis. Methods: We prospectively collected 132 whole blood samples suspected of platelet clumping (102 in EDTA and 30 in sodium citrate) from 88 individuals. We compared platelet counts determined using the platelet count by impedance (PLT-I) function of the DxH 900 hematology analyzer and the PLT-I or optical platelet count (PLT-O) function of the BC-6800Plus. Platelet clumping was verified through manual inspection and the MC-80 digital image analyzer. Results: Among the 132 whole blood samples, 43 EDTA samples showed platelet clumping. The DxH 900 PLT-I and BC-6800Plus PLT-I results demonstrated a strong correlation (r=0.711) for the EDTA samples but only a moderate correlation with the BC-6800Plus PLT-O results (r=0.506 and 0.545, respectively). The BC-6800Plus PLT-O results were consistent with the sodium citrate platelet counts, with a median dissociation rate of 102.5% (range, 74.9%-123.1%). The DxH 900 and BC-6800Plus analyzers had sensitivity values of 0.79 and 0.72, respectively, for platelet-clump flagging. When integrating the MC-80 digital image analysis results, the sensitivity of BC-6800Plus improved to 0.89 (standard mode) or 1.0 (PLT-Pro mode). Conclusions: BC-6800Plus PLT-O measurement results are close to the actual values obtained by platelet deaggregation with PTCP samples. Integrating the BC-6800Plus with a digital imaging analyzer effectively improved the diagnosis of PTCP and reduced the requirement for additional laboratory procedures.

Development of blood demand prediction model using artificial intelligence based on national public big data.

Objective: Modern healthcare systems face challenges related to the stable and sufficient blood supply of blood due to shortages. This study aimed to predict the monthly blood transfusion requirements in medical institutions using an artificial intelligence model based on national open big data related to transfusion. Methods: Data regarding blood types and components in Korea from January 2010 to December 2021 were obtained from the Health Insurance Review and Assessment Service and Statistics Korea. The data were collected from a single medical institution. Using the obtained information, predictive models were developed, including eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LGBM), and category boosting (CatBoost). An ensemble model was created using these three models. Results: The prediction performance of XGBoost, LGBM, and CatBoost demonstrated a mean absolute error ranging from 14.6657 for AB+ red blood cells (RBCs) to 84.0433 for A+ platelet concentrate (PC) and a root mean squared error ranging from 18.5374 for AB+ RBCs to 118.6245 for B+ PC. The error range was further improved by creating ensemble models, wherein the department requesting blood was the most influential parameter affecting transfusion prediction performance for different blood products and types. Except for the department, the features that affected the prediction performance varied for each product and blood type, including the number of RBC antibody screens, crossmatch, nationwide blood donations, and surgeries. Conclusion: Based on blood-related open big data, the developed blood-demand prediction algorithm can efficiently provide medical facilities with an appropriate volume of blood ahead of time.

Methylation of DNA Repair Genes as a Prognostic Biomarker in AML of a TCGA-LAML Cohort.

BACKGROUND: Dysregulation of DNA damage response and altered DNA methylation in acute myeloid leukemia (AML) have been reported, but the impact of methylation of DNA repair genes has not yet been researched. We aimed to predict the prognosis of non-APL AML patients based on the known CpG site methylation levels of DNA repair genes through The Cancer Genome Atlas AML project (TCGA-LAML). METHODS: We utilized TCGA-LAML cohort (174 non-APL AML) for the methylation data of 22 DNA repair genes. RESULTS: In univariate analysis among 174 non-APL AML patients of the TCGA-LAML cohort, the hypermethylation of MLH1, RAD51, and ATM showed superior overall survival (OS) than non-hypermethylated groups, while hypermethylation of RAD23A, RAD23B, MLH1, MSH2, BRCA1, BRCA2, RAD50, and PARP1 was associated with poor OS. We demonstrated that CpG hypermethylation levels of DNA repair genes differed according to the AML cytogenetic risk groups. In multivariate analysis, hypermethylation of MLH1 and RAD51 showed better OS than non-hypermethylated patients, but hypermethylation of MSH2 and RAD50 showed worse OS than non-hypermethylated patients. CONCLUSION: Methylation of 4 DNA repair genes, such as MLH1, RAD51, MSH2, and RAD50, have the potential to be independent risk factors in non-APL AML patients.

Mortality Risk within 14 Days after Coronavirus Disease 2019 Diagnosis in Dementia Patients: A Nationwide Analysis.

INTRODUCTION: The study evaluated the increased mortality risk within 14 days of coronavirus disease 2019 (COVID-19) diagnosis in dementia patients. METHODS: This retrospective study was conducted from February to April 2020 using the COVID-19 patients' database from the Korea Disease Control and Prevention Agency. The risk factors for early death within 14 days were determined using generalized logistic regression performed in a stepwise manner. Dementia patients diagnosed with COVID-19 were used for the study. The propensity score-matched cohort was included as controls. The differences in mortality within 14 days after COVID-19 diagnosis between the dementia patients and controls were evaluated. RESULTS: We enrolled 5,349 COVID-19 patients from the database; 224 had dementia as comorbidity. The mortality rate within 14 days after COVID-19 diagnosis in dementia patients and the controls was 23.7% versus 1.7%, respectively, before propensity score matching (PSM) (p < 0.001), and 23.7% versus 9.2% after PSM (p < 0.001). The hazard ratio (HR) for mortality within 14 days in COVID-19 patients with dementia was significant even after PSM (HR 5.104, 95% confidence interval 2.889-5.673, p < 0.001). The survival curve of dementia patients was steeply inclined within 14 days after COVID-19 diagnosis, resulting in 70.7% of all deaths in dementia patients. CONCLUSIONS: COVID-19 patients with dementia had a higher risk of early death within 14 days. Thus, prompt intervention is necessary for dementia patients after COVID-19 diagnosis.

Comprehensive DNA repair gene expression analysis and its prognostic significance in acute myeloid leukemia.

BACKGROUND: Deficiency in DNA damage response (DDR) pathway and accumulation of DNA damage increases mutation rates resulting in genomic instability and eventually increases the risk of cancer. The aim of our study was to investigate expressions of DNA repair genes as new prognostic biomarkers in acute myeloid leukemia (AML). METHODS: We utilized The Cancer Genome Atlas AML project (TCGA-LAML cohort, 15 acute promyelocytic leukemia (APL) and 155 non-APL AML) for the expression data of DNA repair genes. For validation, clinical samples (Ewha study group, 9 APL and 72 non-APL AML patients) were analyzed for the expression of 22 DNA repair genes using a custom RT2 Profiler PCR Array. RESULTS: APL patients presented significantly lower expression of DNA repair genes than non-APL AML patients in both study groups. Among non-APL AML patients, high expression levels of PARP1, XRCC1, and RAD51 were associated with poor overall survival (OS) probability in both study groups. Furthermore, Cox regression analysis showed that increased expression levels of PARP1, XRCC1, RAD51, BRCA1 and MRE11A could be independent risk factors for OS in the Ewha study group. Among non-APL patients of the Ewha study group, the OS probability of DDR-overexpressed group with at least one gene or more showing Z score greater than 1.5 was poorer than that of DDR non-overexpressed group. CONCLUSION: In the current study, the DNA repair gene expression profile of APL patients was different from that of non-APL AML patients. Overexpression of DNA repair genes could be a poor prognostic biomarker in non-APL AML.

Variant Prediction by Analyzing RdRp/S Gene Double or Low Amplification Pattern in Allplex SARS-CoV-2 Assay.

The spread of delta variants (B.1.671.2) of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is a severe global threat. Multiplex real-time PCR is a common method for confirming SARS-CoV-2 infection, however, additional tests, such as whole genomic sequencing, are required to reveal the presence or type of viral mutation. Moreover, applying whole genomic sequencing to all SARS-CoV-2 positive samples is challenging due to time and cost constraints. Here, we report that the double or low amplification curve observed during RNA-dependent RNA polymerase (RdRp) gene/S gene amplification in the Allplex SARS-CoV-2 Assay is related to delta/alpha variants. We analyzed the RdRp/S gene amplification curve using 94 samples confirmed as SARS-CoV-2 infection by the Allplex SARS-CoV-2 Assay from January to August, 2021. These positive samples identified variant types using the Novaplex SARS-CoV-2 Variants I and IV Assays. Overall, 17 samples showing a double curve and 11 samples showing a low amplification pattern were associated with alpha-/delta-type strains with variants in the P681 region. The double or low curve shown in the RdRp gene amplification curve had 100% sensitivity and 100% specificity for diagnosing delta/alpha variants. During the SARS-CoV-2 virus diagnostic RT-PCR test using the Allplex SARS-CoV-2 Assay, we could consider the presence of delta/alpha variants in the samples with double or low amplification curve of the RdRp/S gene channel. This PCR amplification curve abnormality enables rapid and cost-effective variant type prediction during SARS-CoV-2 diagnostic testing in clinical laboratories.

Coexistence of Primary Myelofibrosis and Paroxysmal Nocturnal Hemoglobinuria Clone with JAK2 V617F, U2AF1 and SETBP1 Mutations: A Case Report and Brief Review of Literature.

Primary myelofibrosis (PMF) and paroxysmal nocturnal hemoglobinuria (PNH) are very rare diseases, respectively, and it is uncommon to have both diseases together. Mutational profiling using next-generation sequencing in PMF and PNH detected additional mutations associated with myeloid neoplasms, suggesting a step-wise clonal evolution. We present here a very rare case with PMF and PNH with JAK2 V617F, U2AF1 and SETBP1 mutations at the time of diagnosis. The combination of these two diseases and three genetic mutations is difficult to interpret at once. (i.e., the sequence of these two clonal diseases or the time points of acquiring these mutations). Our report suggests that when diagnosing or treating patients with PMF, it is necessary to keep in mind that PNH may be present at the same time or sometimes new. The genetic mutations simultaneously found in this patient require further research to elucidate the clinical significance and their genetic associations fully.

False-positive flag of WBC and change of mean platelet volume (MPV) caused by K3-EDTA on the DxH 900 hematology analyzer.

During the evaluation of the DxH 900 hematology analyzer (Beckman Coulter, Miami, FL), we noted that some patient samples produced a false positive white blood cell (WBC) flag, neutrophil blasts (NE-blast), despite the absence of abnormal cells. We investigated whether storage time or anticoagulants such as K2- or K3-ethylenediaminetetraacetic acid (EDTA) would affect complete blood count (CBC) tests on the DxH 900. Sixty-four whole blood samples were collected in K3-EDTA tubes, and 44 were simultaneously drawn in K2-EDTA tubes. Samples were tested at the following two intervals: within 30 min of collection (0 min) and after an additional 30 min of roller-mixing at room temperature (30 min). WBC differential dataplots in 0-min K3-EDTA tubes showed a mixed cell population between lymphocytes and neutrophils in 22 patients presenting the NE-blast flag. All 22 samples revealed normal WBC differential dataplots after 30 min of roller-mixing. The significantly lower mean neutrophil volume in specimens of 0-min K3-EDTA tubes than those of 0-min K2-EDTA, 30-min K2-EDTA and 30-min K3-EDTA tubes appear to be the cause of the false flag. Unlike blood cell counts, mean platelet volume (MPV) was significantly higher at 30 min using both EDTA tubes than that at 0 min. In conclusion, K3-EDTA can produce a false positive flag, NE-blast, on the DxH 900. MPV increases over time irrespective of EDTA salt type.

Sample size and rejection limits for detecting reagent lot variability: analysis of the applicability of the Clinical and Laboratory Standards Institute (CLSI) EP26-A protocol to real-world clinical chemistry data.

Objectives: To maintain the consistency of laboratory test results, between-reagent lot variation should be verified before using new reagent lots in clinical laboratory. Although the Clinical and Laboratory Standards Institute (CLSI) document EP26-A deals with this issue, evaluation of reagent lot-to-lot difference is challenging in reality. We aim to investigate a practical way for determining between-reagent lot variation using real-world data in clinical chemistry. Methods: The CLSI EP26-A protocol was applied to 83 chemistry tests in three clinical labs. Three criteria were used to define the critical difference (CD) of each test as follows: reference change value and total allowable error, which are based on biological variation, and acceptable limits by external quality assurance agencies. The sample size and rejection limits that could detect CD between-reagent lots were determined. Results: For more than half of chemistry tests, reagent lot-to-lot differences could be evaluated using only one patient sample per decision level. In many cases, the rejection limit that could detect reagent lot-to-lot difference with ≥90% probability was 0.6 times CD. However, the sample size and rejection limits vary depending on how the CD is defined. In some cases, impractical sample size or rejection limits were obtained. In some cases, information on sample size and rejection limit that met intended statistical power was not found in EP26-A. Conclusions: The CLSI EP26-A did not provide all necessary answers. Alternative practical approaches are suggested when CLSI EP26-A does not provide guidance.

Somatic mutation of HLA-DRB1*04:03 in a patient with myelodysplastic syndrome at diagnosis.

Loss or decrease in expression of human HLA caused by somatic mutations of HLA genes has been reported in various malignancies. However, mutations in the HLA-DR gene have been rarely noted in hematologic malignancies. Here, we report a case of myelodysplastic syndrome (MDS) with a novel point mutation in exon 2 of the HLA-DRB1*04:03 gene pertaining to a silent mutation (c.357A > T[p.Thr=]). When compared before and after anticancer drug treatment and to the results from the full HLA-matching sibling donor, mutation of the HLA-DRB1 gene suggests clonal evolution. In conclusion, we report a new DRB1*04:03 mutation in an MDS patient at diagnosis that results in a synonymous substitution with unknown clinical impact.

Estimated Glomerular Filtration Rates Show Minor but Significant Differences Between the Single and Subgroup Creatinine-Based Chronic Kidney Disease Epidemiology Collaboration Equations.

The creatinine-based Chronic Kidney Disease Epidemiology Collaboration (CKD-EPI) equation can be calculated according to race, sex, and creatinine concentration (subgroup equation) or in the form expressed by one equation (single equation). Minor differences in the constants used in the CKD-EPI equations (subgroup vs single equations) could result in a significant difference in the estimated glomerular filtration rate (eGFR). We evaluated the impact of this difference in 79,709 Korean patients. The eGFR was calculated as an integer using the single and subgroup CKD-EPI equations. The differences in eGFR and GFR categories between the equations were analyzed. eGFR was higher in the subgroup equation than the single equation by 1 mL/min/1.73 m² for 12,476 (27.4%) Korean females. The GFR category based on the subgroup equation was reclassified using the single equation for 352 (0.77%) females. Based on the results, the constant of the single equation was optimized. There was no difference in eGFR values between equations using a multiplier of 1.0213 instead of 1.018 for the "white or other" females constant in the single CKD-EPI equation. Clinicians should carefully apply the CKD-EPI equation because eGFR values may differ by 1 mL/min/1.73 m² depending on the manner of calculation. To minimize these differences, the constants of the single equation should be revised.

GATA1 Expression in BCR/ABL1-negative Myeloproliferative Neoplasms.

BACKGROUND: This study aimed to determine GATA1 expression levels to better characterize subgroups in BCR/ABL1-negative myeloproliferative neoplasms (MPNs). METHODS: This study enrolled 49 patients diagnosed as having BCR/ABL1-negative MPN on the basis of the 2016 World Health Organization classification : nine polycythemia vera (PV), 17 essential thrombocythemia (ET), 12 prefibrotic primary myelofibrosis (prePMF), and 11 overt primary myelofibrosis (PMF). Relevant clinical and laboratory data were retrieved from the medical records. The molecular analysis of CALR and MPL mutations and quantification of JAK2 V617F allele burden were performed. GATA1 expression was assessed by an immunohistochemical assay on bone marrow biopsy. GATA1 expression was analyzed serially in 18 patients. RESULTS: GATA1 expression decreased significantly in PMF compared with that in other subtypes, while no statistical difference was identified between ET and prePMF. GATA1 expression did not differ according to the mutation profiles or the allele burden of JAK2 V617F, but it decreased significantly in patients with overt fibrosis or leukemic transformation. CONCLUSIONS: Our results suggest that GATA1 expression is significantly low in PMF and decreases with progressive fibrosis and possibly with leukemic transformation, although our attempt to accurately distinguish between subgroups using GATA1 immunohistochemical approach did not achieve statistical significance. A large patient cohort with long term follow-up is required to evaluate the prognostic value of GATA1 expression.

Is Follow-Up Testing with the FilmArray Gastrointestinal Multiplex PCR Panel Necessary?

The FilmArray gastrointestinal (GI) panel (BioFire Diagnostics, Salt Lake City, UT) is a simple, sample-to-answer, on-demand, multiplex, nucleic acid amplification test for syndromic diagnosis of infectious gastroenteritis. The aim of this study was to measure the yield of follow-up testing with FilmArray GI panel within 4 weeks of an initial test. Consecutive adult and pediatric patients tested at an academic institution between August 2015 and June 2016 were included in this study. Of 145 follow-up tests in 106 unique patients with an initial negative result, 134 (92.4%) tests and 98 (92.5%) patients remained negative upon follow-up testing. Excluding targets that are not reported at this institution (Clostridium difficile, enteroaggregative Escherichia coli, enteropathogenic E. coli, and enterotoxigenic E. coli), 137 (94.5%) follow-up tests and 101 (95.3%) patients remained negative. Weekly conversion rates were not significantly different across the 4-week follow-up interval. No epidemiological or clinical factors were significantly associated with a negative to positive conversion. Of 80 follow-up tests in patients with an initial positive result, 43 (53.8%) remained positive for the same target, 34 (42.5%) were negative, and 3 were positive for a different target (3.8%). Follow-up testing with FilmArray GI panel within 4 weeks of a negative result rarely changed the initial result, and the follow-up test reverted to negative less than half the time after an initial positive result. In the absence of clinical or epidemiological evidence for a new infection, follow-up testing should be limited and FilmArray GI panel should not be used as a test of cure.

Diagnostic Utility of Serum Glycated Albumin for Diabetes Mellitus and Its Correlation With Hyperlipidemia.

BACKGROUND: Glycated albumin (GA) is a better marker of short-term glycemic control than glycated hemoglobin (A1c). Dyslipidemia is the main cause of cardiovascular complications in diabetes mellitus (DM). Studies on the correlation of GA with lipid indices are sparse. We investigated the diagnostic utility of GA for DM and its relationship with serum lipid profiles compared with that of A1c. METHODS: The GA enzymatic method was used to determine the diagnostic utility of GA for DM by using samples from 163 normal subjects (group 1) and 102 patients newly diagnosed with type 2 DM (T2DM; group 2). To analyze the lipid profiles, 263 patients with T2DM receiving treatment (group 3) were recruited. RESULTS: GA correlated with A1c (r=0.934, P<0.0001). Linear regression analysis indicated that GA levels were about 2.48 folds those of A1c. In the ROC analysis for GA to diagnose DM, the areas under the curve (0.988, 95% confidence interval 0.972-1.004) was excellent. HDL levels were significantly lower in groups 2 and 3. In group 1, positive correlations were observed between A1c and triglyceride (TG), total cholesterol (TC), LDL, TG/HDL, TC/HDL, and LDL/HDL levels. A negative correlation was observed between HDL and A1c levels. In group 3, HDL levels (P=0.0124 and P=0.0141, respectively) were significantly higher and LDL levels tended to be lower, not statistically significant, in the well-controlled group categorized using the A1c and GA cut-off values. CONCLUSIONS: GA is a potential diagnostic tool for DM. Compared with A1c, GA seems less relevant to dyslipidemia.

Calreticulin mRNA expression and clinicopathological characteristics in acute myeloid leukemia.

Calreticulin, encoded by CALR, is a multifunctional protein with roles in calcium homeostasis and chaperoning molecular processes. This study aimed to evaluate calreticulin mRNA expression levels in acute myeloid leukemia (AML) compared with other hematologic malignancies, and to investigate the clinicopathological characteristics associated with expression in AML patients. The study group included 43 patients diagnosed with AML, 57 with other hematologic malignancies, and 21 benign hematologic conditions. CALR mRNA quantification using real-time polymerase chain reaction revealed it to be significantly higher in AML compared with other hematologic malignancies (P < 0.0001). There was no difference in CALR mRNA expression between AML subgroups by karyotype (P = 0.3201). No differences were found in age, white blood cell counts, platelet counts, bone marrow blast percentage, calcium, lactate dehydrogenase or CD34 expression rate between the high and low CALR groups (CALR mRNA ≥ 1.2 fold and <1.2 fold, respectively), although hemoglobin and sex differences were observed. Although statistically not significant, there was a trend that Relapse rate was lower (54.5% vs. 84.6%) (P = 0.1063) and disease-free survival was longer (22 months vs. 7 months) (P = 0.0784) in low CALR group, whereas overall survival was similar between the two groups (11 months and 8 months). The clinical relevance of CALR expression in AML remains to be clarified in a larger cohort.

Clinical and microbiological characteristics of six Staphylococcus pettenkoferi isolates from blood samples.

Coagulase-negative staphylococci (CoNS) are reported to be the leading cause of nosocomial bloodstream infections. Staphylococcus pettenkoferi is a novel member of CoNS that was first isolated from the human blood and bursitis wound in 2002. We have reported cases of 6 S. pettenkoferi strains isolated from blood specimens, including one pathogen and 5 contaminants and catheter colonizers. Brucker Biotyper (Brucker Daltonics, Bremen, Germany) and molecular typing with 16S rRNA gene sequencing confirmed the 6 isolates as S. pettenkoferi. The conventional phenotypic identification of these isolates is not reliable owing to their inconsistent biochemical characteristics. Five of the 6 isolates were found to be resistant to oxacillin, and all isolates showed susceptibility to vancomycin and linezolid. For accurate identification of this novel species, advanced methods by using Brucker Biotyper or molecular methods such as 16S rRNA gene sequencing are required.