Construction of the prediction model for multiple myeloma based on machine learning.

INTRODUCTION: The global burden of multiple myeloma (MM) is increasing every year. Here, we have developed machine learning models to provide a reference for the early detection of MM. METHODS: A total of 465 patients and 150 healthy controls were enrolled in this retrospective study. Based on the variable screening strategy of least absolute shrinkage and selection operator (LASSO), three prediction models, logistic regression (LR), support vector machine (SVM), and random forest (RF), were established combining complete blood count (CBC) and cell population data (CPD) parameters in the training set (210 cases), and were verified in the validation set (90 cases) and test set (165 cases). The performance of each model was analyzed using receiver operating characteristic (ROC) curve, calibration curves, and decision curve analysis (DCA). Accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under the ROC curve (AUC) were applied to evaluate the models. Delong test was used to compare the AUC of the models. RESULTS: Six parameters including RBC (1012/L), RDW-CV (%), IG (%), NE-WZ, LY-WX, and LY-WZ were screened out by LASSO to construct the model. Among the three models, the AUC of RF model in the training set, validation set, and test set were 0.956, 0.892, and 0.875, which were higher than those of LR model (0.901, 0.849, and 0.858) and SVM model (0.929, 0.868, and 0.846). Delong test showed that there were significant differences among the models in the training set, no significant differences in the validation set, and significant differences only between SVM and RF models in the test set. The calibration curve and DCA showed that the three models had good validity and feasibility, and the RF model performed best. CONCLUSION: The proposed RF model may be a useful auxiliary tool for rapid screening of MM patients.

Time-dependent changes in cell population data obtained using Sysmex XN-series hematology analyzer in bacterial infections.

BACKGROUND: Time-dependent changes in cell populations during acute bacterial infections remain unclear. We assessed time-dependent changes in fluorescent light intensity of the neutrophil area (NE-SFL) and fluorescent light distribution width index of the neutrophil area (NE-WY) and their association with sepsis and bacteremia. METHODS: Patients with acute bacterial infections were enrolled in this prospective, observational cohort study. Blood samples were collected from all patients at the onset of bacterial infections (day 0) and on days 1 and 3. Microbiological evaluation included the examination of blood bacterial load using PCR. Cell population data were assessed using an automated hematology analyzer (Sysmex series XN-2000). RESULTS: Forty-three participants with acute bacterial infections were enrolled in the study. Twenty-five participants developed definite sepsis. All the participants improved after the onset of infection. NE-WY levels showed significant time-dependent changes in participants with sepsis, peaking on day 0 and significantly decreasing until day 3, whereas these changes were not statistically significant for NE-SFL. A significant correlation with the Sequential Organ Failure Assessment score was observed with NE-WY and NE-SFL in the entire cohort on days 0 and 1. However, only NE-WY showed a significant correlation with blood bacterial load on days 0 and 1. CONCLUSION: This study demonstrated that NE-WY elevation in sepsis peaked earlier than NE-SFL, which may partly reflect the early bacterial invasion into circulation. These findings advocate caution in interpreting cell population data values as sepsis biomarkers and propose the potential of NE-WY as a therapeutic indicator.

Reference intervals of cell population data parameters in Sysmex XN-Series and its patterns of changes from early adulthood to geriatric ages in South Korea.

INTRODUCTION: Cell population data (CPD) parameters may be putative biomarkers for the screening of various diseases including some infections and myelodysplastic syndrome. This study aimed to establish the age- and sex-specific reference intervals (RIs) for the CPD parameters in the Korean population. METHODS: The reference population for the RIs of CPD parameters comprised 124 856 subjects aged 20-99 years. CPD parameters were obtained from Sysmex XN-2000 (Kobe, Japan) datasets from 17 health promotion centers in 13 South Korean cities. We determined significant partitions for age and sex, and calculated RIs according to Clinical and Laboratory Standards Institute C28-A3 guidelines. RESULTS: The side scattered light intensity in the neutrophil area and the lymphocyte area did not require sex-related partitioning except in those over the age of 50, among whom the lower limit (LL) and upper limit (UL) were lower in females. However, the side scattered light distribution width in the lymphocyte area required age- and sex-related partitioning, in which LL and UL were higher in females. The LL and UL of the fluorescent light distribution width were higher in males in the neutrophil area and higher in females in the lymphocyte area, but age-related partitioning was not required. The forward scattered light intensity in the neutrophil area, lymphocyte area, and monocyte area did not require age-related partitioning in males. CONCLUSION: This study has determined comprehensive age- and sex-specific RIs for CPD parameters, which could help to prove the clinical significance of these parameters in the Sysmex XN-2000.

Detection of blasts using flags and cell population data rules on Beckman Coulter DxH 900 hematology analyzer in patients with hematologic diseases.

OBJECTIVES: White blood cell (WBC)-related flags are essential for detecting abnormal cells including blasts in automated hematology analyzers (AHAs). Cell population data (CPD) may characterize each WBC population, and customized CPD rules can be also useful for detecting blasts. We evaluated the performance of WBC-related flags, customized CPD rules, and their combination for detecting blasts on the Beckman Coulter DxH 900 AHA (DxH 900, Beckman Coulter, Miami, Florida, USA). METHODS: In a total of 239 samples from patients with hematologic diseases, complete blood count on DxH 900 and manual slide review (MSR) were conducted. The sensitivity, specificity, and efficiency of the five WBC-related flags, nine customized CPD rules, and their combination were evaluated for detecting blasts, in comparison with MSR. RESULTS: Blasts were detected by MSR in 40 out of 239 (16.7 %) samples. The combination of flags and CPD rules showed the highest sensitivity compared with each of flags and CPD rules for detecting blasts (97.5 vs. 72.5 % vs. 92.5 %). Compared with any flag, the combination of flags and CPD rules significantly reduced false-negative samples from 11 to one for detecting blasts (27.5 vs. 2.5 %, p=0.002). CONCLUSIONS: This is the first study that evaluated the performance of both flags and CPD rules on DxH 900. The customized CPD rules as well as the combination of flags and CPD rules outperformed WBC-related flags for detecting blasts on DxH 900. The customized CPD rules can play a complementary role for improving the capability of blast detection on DxH 900.

A machine learning tool for the diagnosis of SARS-CoV-2 infection from hemogram parameters.

Monocytes and neutrophils play key roles in the cytokine storm triggered by SARS-CoV-2 infection, which changes their conformation and function. These changes are detectable at the cellular and molecular level and may be different to what is observed in other respiratory infections. Here, we applied machine learning (ML) to develop and validate an algorithm to diagnose COVID-19 using blood parameters. In this retrospective single-center study, 49 hemogram parameters from 12,321 patients with clinical suspicion of COVID-19 and tested by RT-PCR (4239 positive and 8082 negative) were analysed. The dataset was randomly divided into training and validation sets. Blood cell parameters and patient age were used to construct the predictive model with the support vector machine (SVM) tool. The model constructed from the training set (5936 patients) achieved an accuracy for diagnosis of SARS-CoV-2 infection of 0.952 (95% CI: 0.875-0.892). Test sensitivity and specificity was 0.868 and 0.899, respectively, with a positive (PPV) and negative (NPV) predictive value of 0.896 and 0.872, respectively (prevalence 0.50). The validation set model (4964 patients) achieved an accuracy of 0.894 (95% CI: 0.883-0.903). Test sensitivity and specificity was 0.8922 and 0.8951, respectively, with a positive (PPV) and negative (NPV) predictive value of 0.817 and 0.94, respectively (prevalence 0.34). The area under the receiver operating characteristic curve was 0.952 for the algorithm performance. This algorithm may allow to rule out COVID-19 diagnosis with 94% of probability. This represents a great advance for early diagnostic orientation and guiding clinical decisions.

Leukocyte cell population data as potential markers of COVID-19 disease characterization.

Background: The usefulness of leukocyte cell population data (CPD) is currently being investigated. In COVID-19 pandemic several reports showed the clinical importance of hematological parameters. Our study aimed to assess CPDs in Sars CoV-2 patients as new disease markers. Methods: From February to April 2020 (1st wave) 540 and from September to December 2020 (2nd wave) 2821 patients respectively were enrolled. SARS CoV-2 infection diagnosis was carried out by Multiplex rRT-PCR from nasopharyngeal swabs. CPDs were detected by XN 2000 hematology analyzer (Sysmex Corporation). A comparison between two disease waves was performed. Additionally, C-reactive protein (CRP) and lactate dehydrogenase (LDH) were assayed. Results: CPDs were classified into: cell complextity, DNA/RNA content and abnormal sized cells. We detected parameters increased from the reference population for all cell types for both 1st and 2nd wave (p<0.05). However, in the 2nd vs 1st wave 5 CPDs vs 9 CPDs were found. In addition we observed higher CPD values of the 1st compared to 2nd wave: (NE-SFL) (p<0.001), (LY-Y) (p<0.0001), (LY-Z) (p<0.0001), (MO-X) (p<0.0001), (MO-Y) (p<0.0001). These findings were confirmed by the higher concentrations of CRP and LDH in the 1st vs 2nd wave: 17.3 mg/L (8.5-59.3) vs 6.3 mg/L (2.3-17.6) (p<0.001) and 241.5 IU/L (201-345) vs 195 IU/L (174-228) (p< 0.001) (median, interquartile range) respectively. Conclusions: CPDs showed increased cell activation in 1st wave patients confirmed by clinical and biochemical data, associated with worse clinical conditions. Results highlighted the CPDs as disease characterization markers or useful for a risk model.

Exploring Extended White Blood Cell Parameters for the Evaluation of Sepsis among Patients Admitted to Intensive Care Units.

Sepsis is a major cause of mortality and morbidity in intensive care units. This case-control study aimed to investigate the haematology cell population data and extended inflammatory parameters for sepsis management. The study included three groups of patients: sepsis, non-sepsis, and healthy controls. Patients suspected of having sepsis underwent a Sequential Organ Failure Assessment (SOFA) evaluation and had blood drawn for blood cultures, complete peripheral blood counts (CBC), and measurements of various markers such as C-reactive protein (CRP), procalcitonin (PCT), and interleukin-6 (IL-6). We observed significant changes in numerous CBC parameters and extended inflammation parameters (EIPs), in addition to significant biochemical analysis markers CRP and IL-6 in sepsis cohorts. Multiple logistic regression analyses showed that combining different CBC parameters and EIPs were effective to profile these patients. Two different models have been developed using white blood cell counts and their extended parameters. Our findings indicate that the absolute counts of white blood cells, and the EIPs which reflect their activation states, are important for the prediction and assessment of sepsis, as the body responds to an insult that triggers an immune response. In an emergency situation, having timely updates on patient conditions becomes crucial for guiding the management process. Identifying trends in these specific patient groups will aid early diagnosis, complementing clinical signs and symptoms, especially as CBC is the most commonly ordered test in a diagnostic workup.

Leucocyte volume, conductivity, and scatter at presentation in COVID-19 patients.

Background: In COVID-19 patients, besides changes in leucocyte count, morphological abnormalities of circulating blood cells have been reported. Aim: This study aims to investigate the relationship between the morphological and functional properties of leucocytes and the severity of the disease in COVID-19 patients. Materials and Methods: Blood samples were collected from COVID-19 patients (n = 130) at the time of admission. The patients were stratified according to the comorbidity, age, LDH, lymhocyte count score as mild, moderate, and severe. Complete blood count and the cell population data were analyzed by the Volume, conductivity, scatter (VCS) technology on Beckman Coulter LH-780 hematology analyzer. Kruskal-Wal'lis test was used to assess the differences between the groups with subsequent Bonferroni correction. Results: Neutrophil count was increased, and lymphocyte count was decreased in severe patients compared to mild patients. The increase in the percent of neutrophils and the neutrophil/lymphocyte ratio in the severe patient group was significant in comparison to both the moderate and the mild group. The dispersion of the neutrophil volume and conductivity showed significant changes depending on the severity of the disease. The lymphocyte volume, lymphocyte-volume-SD and lymphocyte-conductivity as well as the monocyte-volume and monocyte-volume-SD were significantly increased in severe patients in comparison to mild patients. The increase of lymphocyte and monocyte volume in severe patients was also significant in comparison to moderate patients. Conclusions: COVID-19 infection leads to important changes in cell population data of leucocytes. The volumetric changes in lymphocytes and monocytes are related to the severity of the disease.

Predictive value of cell population data with Sysmex XN-series hematology analyzer for culture-proven bacteremia.

Background: Cell population data (CPD) parameters related to neutrophils, such as fluorescent light intensity (NE-SFL) and fluorescent light distribution width index (NE-WY), have emerged as potential biomarkers for sepsis. However, the diagnostic implication in acute bacterial infection remains unclear. This study assessed the diagnostic value of NE-WY and NE-SFL for bacteremia in patients with acute bacterial infections, and those associations with other sepsis biomarkers. Methods: Patients with acute bacterial infections were enrolled in this prospective observational cohort study. For all patients, a blood sample, with at least two sets of blood cultures, were collected at the onset of infection. Microbiological evaluation included examination of the blood bacterial load using PCR. CPD was assessed using Automated Hematology analyzer Sysmex series XN-2000. Serum levels of procalcitonin (PCT), interleukin-6 (IL-6), presepsin, and CRP were also assessed. Results: Of 93 patients with acute bacterial infection, 24 developed culture-proven bacteremia and 69 did not. NE-SFL and NE-WY were significantly higher in patients with bacteremia than in those without bacteremia (p < 0.005, respectively), and were significantly correlated with the bacterial load determined by PCR (r = 0.384 and r = 0.374, p < 0.005, respectively). To assess the diagnostic value for bacteremia, receiver operating characteristic curve analysis was used. NE-SFL and NE-WY showed an area under the curve of 0.685 and 0.708, respectively, while those of PCT, IL-6, presepsin, and CRP were 0.744, 0.778, 0.685, and 0.528, respectively. Correlation analysis showed that the levels of NE-WY and NE-SFL were strongly correlated with PCT and IL-6 levels. Conclusion: This study demonstrated that NE-WY and NE-SFL could predict bacteremia in a manner that may be different from that of other indicators. These findings suggest there are potential benefits of NE-WY/NE-SFL in predicting severe bacterial infections.

Machine learning of cell population data, complete blood count, and differential count parameters for early prediction of bacteremia among adult patients with suspected bacterial infections and blood culture sampling in emergency departments.

BACKGROUND: Bacteremia is a life-threatening complication of infectious diseases. Bacteremia can be predicted using machine learning (ML) models, but these models have not utilized cell population data (CPD). METHODS: The derivation cohort from emergency department (ED) of China Medical University Hospital (CMUH) was used to develop the model and was prospectively validated in the same hospital. External validation was performed using cohorts from ED of Wei-Gong Memorial Hospital (WMH) and Tainan Municipal An-Nan Hospital (ANH). Adult patients who underwent complete blood count (CBC), differential count (DC), and blood culture tests were enrolled in the present study. The ML model was developed using CBC, DC, and CPD to predict bacteremia from positive blood cultures obtained within 4 h before or after the acquisition of CBC/DC blood samples. RESULTS: This study included 20,636 patients from CMUH, 664 from WMH, and 1622 patients from ANH. Another 3143 patients were included in the prospective validation cohort of CMUH. The CatBoost model achieved an area under the receiver operating characteristic curve of 0.844 in the derivation cross-validation, 0.812 in the prospective validation, 0.844 in the WMH external validation, and 0.847 in the ANH external validation. The most valuable predictors of bacteremia in the CatBoost model were the mean conductivity of lymphocytes, nucleated red blood cell count, mean conductivity of monocytes, and neutrophil-to-lymphocyte ratio. CONCLUSIONS: ML model that incorporated CBC, DC, and CPD showed excellent performance in predicting bacteremia among adult patients with suspected bacterial infections and blood culture sampling in emergency departments.

Combination of NeuX and NeuZ can predict neutrophil dysplasia features of myelodysplastic neoplasms in peripheral blood.

INTRODUCTION: The assessment of neutrophil dysplasia features in peripheral blood is very helpful for the early screening and diagnosis of myelodysplastic neoplasms (MDS). Cell population data (CPD) parameters generated by automated hematology analyzers can reflect morphological characteristics of blood cells. This study aimed to investigate the clinical significance of CPD parameters neutrophil (Neu) X, NeuY and NeuZ in assessing neutrophil dysplasia. METHODS: 218 MDS patients were divided into two subgroups according to neutrophil morphology. The differences of neutrophil research parameters between the two MDS subgroups and the control group, consisting of 210 healthy individuals, were compared, the correlation among neutrophil research parameters and the relationship between these parameters and cell morphology in MDS patients were analyzed, and receiver operating characteristic analysis were performed. RESULTS: The median values of neutrophil research parameters NeuX and NeuZ in MDS with granulocyte dysplasia group were significantly lower than those in MDS without granulocyte dysplasia group and control group (p < 0.001), and they were positively correlated (r = 0.878, p < 0.001). The area under the receiver operating characteristic curve of NeuX and NeuZ was 0.720 (95% CI: 0.643-0.796, p < 0.001) and 0.738 (95% CI: 0.665-0.811, p < 0.001), respectively. In addition, with the decrease of NeuX value, neutrophils gradually show decreased nuclear segment and/or cytoplasmic granules. CONCLUSIONS: Combining NeuX and NeuZ can predict neutrophil dysplasia features of MDS in peripheral blood, and this can be an easier method to screen for the neutrophil dysplasia cases, as compared with the microscopic examination of peripheral blood and/or bone marrow smears.

Evaluation of the Diagnostic Value of Cell Population Data in Sepsis in Comparison to Localized Infection, Chronic Inflammation, and Noninfectious Inflammation Cases.

INTRODUCTION: Sepsis, defined as an increase of 2 points or more in the sequential organ failure assessment score, is a life-threatening organ dysfunction caused by the dysregulated host response to infection. Volume-conductivity-scatter (VCS) parameters of cell counters which are known as cell population data (CPD) have been suggested to be beneficial in diagnosing sepsis. We aimed to evaluate the diagnostic value of CPD parameters in sepsis in comparison to nonsystemic infection cases (NSI) and non-infectious acute and chronic inflammatory conditions. MATERIALS AND METHODS: We prospectively included four groups of patients" data: sepsis (n = 66), localized infection (pneumonia, n = 59), chronic inflammation (rheumatoid arthritis, n = 92) and noninfectious inflammation (coronary artery bypass graft operation, n = 56) groups, according to their clinical status and laboratory results. Samples for cell counting and serum markers were collected on the same day of culture collection. VCS parameters were measured by Unicel DxH800 Coulter Cellular Analyzer (Beckman Coulter, USA). RESULTS: Mean neutrophil volume (MN-V-NE), was highest in the sepsis group [155(149-168)] compared to the localized infection [148(140-158)], chronic inflammation [144.5(142-149)] and noninfectious inflammation [149(145.2-153.7)] (P = 0.001, P < 0.001, P < 0.001, respectively). Neutrophil volume SD (SD-V-NE) was higher in the sepsis [21(18.8-23.7)], significantly differentiating sepsis from other groups. The area under curves of procalcitonin and hs-C-reactive protein were 0.846 and 0.837, respectively, in the receiver-operating characteristic curves (ROC) . CPD combinations, (SD-V NE + SD-V LY + SD-V MO), (SD-V NE + SD-V MO), and (MN-V NE + SD-V NE + SD-C LY + SD-V MO) had greater AUC values than procalcitonin's. CONCLUSION: VCS parameters might be promising for differentiating sepsis and non-sepsis cases. Additionally, obtaining these data routinely makes their prospects promising without any additional cost and time.

Diagnostic performance of machine learning models using cell population data for the detection of sepsis: a comparative study.

OBJECTIVES: To compare the artificial intelligence algorithms as powerful machine learning methods for evaluating patients with suspected sepsis using data from routinely available blood tests performed on arrival at the hospital. Results were compared with those obtained from the classical logistic regression method. METHODS: The study group consisted of consecutive patients with fever and suspected infection admitted to the Emergency Department. The complete blood counts (CBC) were acquired using the Mindray BC-6800 Plus analyser (Mindray Diagnostics, Shenzhen, China). Cell Population Data (CPD) were also recorded. The ML and artificial intelligence (AI) models were developed; their performance was evaluated using several indicators, such as the area under the receiver operating curve (AUC), calibration plots and decision curve analysis (DCA). RESULTS: Overall, all the tested approaches obtained an AUC>0.90. The logistic regression (LR) performed well compared to the ML/AI models. The naïve Bayes and the K-nearest neighbour (KNN) methods did not show good calibration properties. The multi-layer perceptron (MLP) model was the best in terms of discrimination, calibration and clinical usefulness. CONCLUSIONS: The best performance in the early detection of sepsis was achieved using the ML and AI models. However, external validation studies are needed to strengthen model derivation and procedure updating.

Research use only and cell population data items obtained from the Beckman Coulter DxH800 automated hematology analyzer are useful in discriminating MDS patients from those with cytopenia without MDS.

We investigated the performance of research use only/cell population data (RUO/CPD) items obtained from the Beckman Coulter DxH800 automated hematologic analyzer in discriminating MDS patients from cytopenic patients without MDS.Total of 14 routine CBC, 18 research use only (RUO) items, and 70 CPD items were obtained retrospectively at diagnosis. The results were then compared between 94 MDS patients and 100 cytopenic patients without MDS. In items with statistically significant differences, receiver operating characteristic (ROC) analysis was performed and the results were compared.Four CBC/RUO items [red cell distribution width-standard deviation (RDW-SD), immature reticulocyte fraction (IRF), mean sphered cell volume (MSCV), high light scatter reticulocytes (HLR)], and two CPD items [mean volume of neutrophils (NE-V-Mean) and mean volume of early granulated cells (EGC-V-Mean)] showed area-under the curve (AUC) scores > 0.750. Notably, four RUO/CPD items (MSCV > 81.4/HLR > 0.15%/NE-V-Mean > 145/EGC-V-Mean > 156) showed high sensitivity (91.9%/93.6%/88.1%/90.2%, respectively) in discriminating MDS patients from cytopenic patients without MDS. With these six items, scores ≥ 4 (defined as ≥ 4 items exceeding cutoff values out of six items) showed AUC scores/sensitivity/specificity/accuracy (0.891/87.3%/79.0%/83.0%, respectively).Six CBC/RUO/CPD items showed satisfactory AUC scores of > 0.750, and four RUO/CPD items showed high sensitivity in discriminating MDS patients from cytopenic patients without MDS. Scoring system with six items showed high sensitivity, specificity, and accuracy with decision criteria of ≥ 4 scores. Therefore, DxH800 RUO/CPD items would be useful in discriminating MDS patients from cytopenic patients without MDS.

The Clinical Performance of Cell Population Data for Diagnosis of Bloodstream Infection in Cancer Patients.

Background Bloodstream infection (BSI) induces a change in the number and morphology of blood cells. In this study, we compared cell population data (CPD) parameters between cancer patients with or without BSI to determine whether these parameters could serve as biomarkers of BSI. Methods Between April and June 2021, 43 BSI-negative and 22 BSI-positive cancer patients were enrolled in this study. We compared 18 CPD parameters and biomarkers between cancer patients with BSI-positive and BSI-negative. Results There were significant differences in the levels of several CPD parameters, including MO-WZ (p=0.040), MO-X (p<0.01), MO-Y (p=0.012), NE-SFL (p<0.01), and NE-WX (p=0.037), but not C-reactive protein (p=0.347) and procalcitonin (p=0.237) between BSI-positive and BSI-negative patients. The areas under the receiver-operating characteristic curves (AUCs) were above 0.7 for MO-X (0.762; 95% confidence intervals (CI): 0.624-0.901), NE-SFL (0.766; 95% CI: 0.625-0.880). And LY-WY (p=0.024) showed a significant difference between gram-negative and gram-positive BSI patients with high AUC (0.883; 95% CI: 0.703-1). Conclusion CPD parameters (MO-X and NE-SFL) provide additional information for discriminating between BSI-negative and BSI-positive BSI. And LY-WY provides useful information for discriminating between cancer patients with gram-negative BSI and gram-positive BSI.

Baseline complete blood count and cell population data as prognostic markers for in-hospital mortality among COVID-19 patients admitted at the Philippine General Hospital from March 2020 to January 2022

INTRODUCTION@#Complete blood count (CBC) and cell population data (CPD) are hematologic parameters used in several clinical scenarios including infection and neoplastic processes. In the setting of COVID-19 infection, there is relative paucity of data in their use as possible prognostic markers.@*OBJECTIVE@#We aim to evaluate the utility of the baseline CBC and CPD as prognostic markers for in-hospital mortality among COVID-19 patients admitted in Philippine General Hospital from March 2020 to January 2022.@*METHODOLOGY@#This is a case-control study. Expired patients served as cases, and recovered patients served as controls. Data from eligible patients including age, sex, admitting COVID diagnosis with severity, final disposition, baseline CBC and CPD results were collected from the hospital medical records and hematology section of the Department of Laboratories. Statistical analyses were done to determine the prognostic value of these parameters for in-hospital mortality.@*RESULTS@#Among the different CBC and CPD parameters, the study shows total white blood cell (WBC) count, absolute neutrophil count (ANC), absolute eosinophil count (AEC), and neutrophil-lymphocyte ratio (NLR) were statistically significant predictors for in-hospital mortality. For total WBC count, at a cut off 9.9 x 10 9 /L, the sensitivity and specificity is 70.9% and 66.2%, respectively. For ANC, at a cut off of 7.3 x 10 9 /L, the specificity is 76.4% and the specificity is 68.2%. At a cut off of 7.62, the NLR shows a sensitivity of 76.4% and specificity of 70.1%. For AEC, at a cut off of 0.006 x 10 9 /L, the sensitivity is 53.3% and the specificity is 87.3%. AEC predicts towards the direction of survival rather than to the direction of in-hospital mortality.@*CONCLUSION@#The total WBC count, ANC, and NLR were statistically significant predictors for in-hospital mortality, while AEC predicts towards the direction of survival. The sensitivities and specificities of the cut off for these parameters were less than ideal. Correlation with clinical and other laboratory parameters is still recommended. For future studies, the authors recommend monitoring CBC and CPD parameters at different time points during the patients’ hospital course.

Utility of Differential White Cell Count and Cell Population Data for Ruling Out COVID-19 Infection in Patients With Community-Acquired Pneumonia

Introduction: The main aim of this study was to assess the utility of differential white cell count and cell population data (CPD) for the detection of COVID-19 in patients admitted for community-acquired pneumonia (CAP) of different etiologies. Methods: This was a multicenter, observational, prospective study of adults aged ≥18 years admitted to three teaching hospitals in Spain from November 2019 to November 2021 with a diagnosis of CAP. At baseline, a Sysmex XN-20 analyzer was used to obtain detailed information related to the activation status and functional activity of white cells. Results: The sample was split into derivation and validation cohorts of 1065 and 717 patients, respectively. In the derivation cohort, COVID-19 was confirmed in 791 patients and ruled out in 274 patients, with mean ages of 62.13 (14.37) and 65.42 (16.62) years, respectively (p<0.001). There were significant differences in all CPD parameters except MO-Y. The multivariate prediction model showed that lower NE-X, NE-WY, LY-Z, LY-WY, MO-WX, MO-WY, and MO-Z values and neutrophil-to-lymphocyte ratio were related to COVID-19 etiology with an AUC of 0.819 (0.790, 0.846). No significant differences were found comparing this model to another including biomarkers (p=0.18). Conclusions: Abnormalities in white blood cell morphology based on a few cell population data values as well as NLR were able to accurately identify COVID-19 etiology. Moreover, systemic inflammation biomarkers currently used were unable to improve the predictive ability. We conclude that new peripheral blood biomarkers can help determine the etiology of CAP fast and inexpensively. (AU)

Utility of Differential White Cell Count and Cell Population Data for Ruling Out COVID-19 Infection in Patients With Community-Acquired Pneumonia.

INTRODUCTION: The main aim of this study was to assess the utility of differential white cell count and cell population data (CPD) for the detection of COVID-19 in patients admitted for community-acquired pneumonia (CAP) of different etiologies. METHODS: This was a multicenter, observational, prospective study of adults aged ≥18 years admitted to three teaching hospitals in Spain from November 2019 to November 2021 with a diagnosis of CAP. At baseline, a Sysmex XN-20 analyzer was used to obtain detailed information related to the activation status and functional activity of white cells. RESULTS: The sample was split into derivation and validation cohorts of 1065 and 717 patients, respectively. In the derivation cohort, COVID-19 was confirmed in 791 patients and ruled out in 274 patients, with mean ages of 62.13 (14.37) and 65.42 (16.62) years, respectively (p<0.001). There were significant differences in all CPD parameters except MO-Y. The multivariate prediction model showed that lower NE-X, NE-WY, LY-Z, LY-WY, MO-WX, MO-WY, and MO-Z values and neutrophil-to-lymphocyte ratio were related to COVID-19 etiology with an AUC of 0.819 (0.790, 0.846). No significant differences were found comparing this model to another including biomarkers (p=0.18). CONCLUSIONS: Abnormalities in white blood cell morphology based on a few cell population data values as well as NLR were able to accurately identify COVID-19 etiology. Moreover, systemic inflammation biomarkers currently used were unable to improve the predictive ability. We conclude that new peripheral blood biomarkers can help determine the etiology of CAP fast and inexpensively.

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.