Interest of the cellular population data analysis as an aid in the early diagnosis of SARS-CoV-2 infection

Detection of decreased granules in neutrophils by automated hematology analyzers XR-1000 and UniCel DxH 800

OBJECTIVE

This study aimed to investigate the utility of neutrophil-related cell population data obtained by automated hematology analyzers in assessing myelodysplastic syndrome cases with decreased granules in neutrophils.

METHODS

A total of 108 subjects were classified into normal granule (n = 35), hypogranulation (n = 37), or hypergranulation (n = 36) groups. Neutrophil cell area and granule area were measured by ImageJ. All samples were analyzed on the XR-1000 and UniCel DxH 800, and neutrophil-related parameters were compared among the 3 groups.

RESULTS

Neutrophil cell area and the ratio of the granular area showed significant differences among the 3 groups; they were the highest in the hypergranulation group and lowest in the hypogranulation group. XR-1000 data showed significant differences in NE-SFL and NE-FSC among the 3 groups (P < .0001). NE-SFL and NE-FSC discriminated most accurately hypogranulation group against other groups. UniCel DxH 800 data showed significant differences in MN-V-NE, MN-MALS-N, MN-UMALS-NE, SD-UMALS-NE (P <.01), MN-LMALS-NE, and SD-LMALS-NE (P <.05) among the 3 groups. The combination of SD-V-NE and SD-LMALS-NE discriminated most accurately the hypogranulation group against the other groups.

CONCLUSION

NE-SFL and NE-FSC and the combination of SD-V-NE and SD-LMALS-NE are useful in detecting cases with decreased granules in neutrophils.

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.

Can Haematological Parameters Discriminate COVID-19 from Influenza?

Symptoms of COVID-19 are similar to the influenza virus, but because treatments and prognoses are different, it is important to accurately and rapidly differentiate these diseases. The aim of this study was to evaluate whether the analysis of complete blood count (CBC), including cellular population (CPD) data of leukocytes and automated flow cytometry analysis, could discriminate these pathologies. In total, 350 patients with COVID-19 and 102 patients with influenza were included between September 2021 and April 2022 in the tertiary hospital of Suresnes (France). Platelets were lower in patients with influenza than in patients with COVID-19, whereas the CD16pos monocyte count and the ratio of the CD16pos monocytes/total monocyte count were higher. Significant differences were observed for 9/56 CPD of COVID-19 and flu patients. A logistic regression model with 17 parameters, including among them 11 CPD, the haemoglobin level, the haematocrit, the red cell distribution width, and B-lymphocyte and CD16pos monocyte levels, discriminates COVID-19 patients from flu patients. The sensitivity and efficiency of the model were 96.2 and 86.6%, respectively, with an area under the curve of 0.862. Classical parameters of CBC are very similar among the three infections, but CPD, CD16pos monocytes, and B-lymphocyte levels can discriminate patients with COVID-19.

It's in the blood: a review of the hematological system in SARS-CoV-2-associated COVID-19

The emergence of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has led to an unprecedented global healthcare crisis. While SARS-CoV-2-associated COVID-19 affects primarily the respiratory system, patients with COVID-19 frequently develop extrapulmonary manifestations. Notably, changes in the hematological system, including lymphocytopenia, neutrophilia and significant abnormalities of hemostatic markers, were observed early in the pandemic. Hematological manifestations have since been recognized as important parameters in the pathophysiology of SARS-CoV-2 and in the management of patients with COVID-19. In this narrative review, we summarize the state-of-the-art regarding the hematological and hemostatic abnormalities observed in patients with SARS-CoV-2-associated COVID-19, as well as the current understanding of the hematological system in the pathophysiology of acute and chronic SARS-CoV-2-associated COVID-19.

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.

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.

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.

Hematology and Machine Learning

BACKGROUND

Substantial improvements in computational power and machine learning (ML) algorithm development have vastly increased the limits of what autonomous machines are capable of. Since its beginnings in the 19th century, laboratory hematology has absorbed waves of progress yielding improvements in both of accuracy and efficiency. The next wave of change in laboratory hematology will be the result of the ML revolution that has already touched many corners of healthcare and society at large.

CONTENT

This review will describe the manifestations of ML and artificial intelligence (AI) already utilized in the clinical hematology laboratory. This will be followed by a topical summary of the innovative and investigational applications of this technology in each of the major subdomains within laboratory hematology.

SUMMARY

Application of this technology to laboratory hematology will increase standardization and efficiency by reducing laboratory staff involvement in automatable activities. This will unleash time and resources for focus on more meaningful activities such as the complexities of patient care, research and development, and process improvement.

Prognostic value of cellular population data in patients with COVID-19

Background and aims

Beckman Coulter hematology analysers identify leukocytes by their volume (V), conductivity (C) and scatter (S) of a laser beam at different angles. Each leukocyte sub-population [neutrophils (NE), lymphocytes (LY), monocytes (MO)] is characterized by the mean (MN) and the standard deviation (SD) of 7 measurements called "cellular population data" (@CPD), corresponding to morphological analysis of the leukocytes. As severe forms of infections to SARS-CoV-2 are characterized by a functional activation of mononuclear cells, leading to a cytokine storm, we evaluated whether CPD variations are correlated to the inflammation state, oxygen requirement and lung damage and whether CPD analysis could be useful for a triage of patients with COVID-19 in the Emergency Department (ED) and could help to identify patients with a high risk of worsening.

Materials and method

The CPD of 825 consecutive patients with proven COVID-19 presenting to the ED were recorded and compared to classical biochemical parameters, the need for hospitalization in the ward or ICU, the need for oxygen, or lung injury on CT-scan.

Results

40 of the 42 CPD were significantly modified in COVID-19 patients in comparison to 245 controls. @MN-V-MO and @SD-V-MO were highly correlated with C-reactive protein, procalcitonin, ferritin and D-dimers. SD-UMALS-LY > 21.45 and > 23.92 identified, respectively, patients with critical lung injuries (>75%) and requiring tracheal intubation. @SD-V-MO > 25.03 and @SD-V-NE > 19.4 identified patients required immediate ICU admission, whereas a @MN-V-MO < 183 suggested that the patient could be immediately discharged. Using logistic regression, the combination of 8 CPD with platelet and basophil counts and the existence of diabetes or obesity could identify patients requiring ICU after a first stay in conventional wards (area under the curve = 0.843).

Conclusion

CPD analysis constitutes an easy and inexpensive tool for triage and prognosis of COVID-19 patients in the ED.

Coronavirus disease 2019 (COVID-19): Focus on peripheral blood cell morphology

Numerous studies have shown peculiar morphological anomalies in COVID-19 patients' smears. We searched all the peer-reviewed scientific publications that explicitly reference the cytomorphological alterations on peripheral blood smears of patients with COVID-19. We extracted data from sixty-five publications (case reports, patient group studies, reviews, and erythrocyte morphology studies). The results show that frequent alterations concern the morphology of lymphocytes (large lymphocytes with weakly basophilic cytoplasm, plasmacytoid lymphocytes, large granular lymphocytes). Neutrophils display abnormal nuclei and cytoplasm in a distinctive cytomorphological picture. Besides a left shift in maturation, granulations can be increased (toxic type) or decreased with areas of basophilia. Nuclei are often hyposegmented (pseudo-Pelger-Huёt anomaly). Apoptotic or pycnotic cells are not uncommon. Monocytes typically have a large cytoplasm loaded with heterogeneous and coalescing vacuoles. Platelets show large and giant shapes. The presence of erythrocyte fragments and schistocytes is especially evident in the forms of COVID-19 that are associated with thrombotic microangiopathies. Such atypia of blood cells reflects the generalized activation in severe COVID-19, which has been demonstrated with immunophenotypic, molecular, genetic, and functional methods. Neutrophils, in particular, are involved in the pathophysiology of hyperinflammation with cytokine storm, which characterizes the most unfavorable evolution.

Diagnostic and Prognostic Value of Monocyte Distribution Width in Sepsis

Monocyte distribution width (MDW) is a blood monocyte morphological parameter that can be easily detected by an automated hemocyte analyzer and can provide clinicians with important information about cell volume variability in peripheral blood monocyte populations. The United States' Food and Drug Administration and Conformite Europeenne have both been cleared for their clinical application in the detection of sepsis and developing sepsis in adult patients in the emergency department (ED). Recently, MDW has been found to have an early diagnosis and predictive value for sepsis in neonates and COVID-19 patients. Here, we summarize the findings of the studies investigating the clinical application of MDW in sepsis. Under different stimuli, especially in infectious diseases, the activation of innate immunity is the host's first defense mechanism, and the change in monocyte volume is considered an early indicator reflecting the state of activation of innate immunity. Pivotal study data from a large multicenter patient cohort showed that abnormal MDW at presentation increases the odds of sepsis, considering the combination of MDW and White Blood Cell Count (WBC) as part of a standard sepsis assessment protocol for ED, which may increase the sensitivity and specificity of sepsis diagnosis. Meanwhile, MDW shares a diagnostic performance comparable to that of conventional biomarkers (C-reactive protein and procalcitonin) in sepsis. In addition, some evidence suggests that increased MDW, both in adults and neonates, may be associated with unfavorable short- and long-term outcomes, which indicates its prognostic value in sepsis. Taken together, MDW is a parameter of increased morphological variability of monocytes in response to infection, and numerous studies have shown that MDW could be used as a valuable diagnostic and prognostic index in patients with sepsis or suspected sepsis.

Artificial Intelligence Applications for COVID-19 in Intensive Care and Emergency Settings: A Systematic Review

Background: Little is known about the role of artificial intelligence (AI) as a decisive technology in the clinical management of COVID-19 patients. We aimed to systematically review and critically appraise the current evidence on AI applications for COVID-19 in intensive care and emergency settings. Methods: We systematically searched PubMed, Embase, Scopus, CINAHL, IEEE Xplore, and ACM Digital Library databases from inception to 1 October 2020, without language restrictions. We included peer-reviewed original studies that applied AI for COVID-19 patients, healthcare workers, or health systems in intensive care, emergency, or prehospital settings. We assessed predictive modelling studies and critically appraised the methodology and key findings of all other studies. Results: Of fourteen eligible studies, eleven developed prognostic or diagnostic AI predictive models, all of which were assessed to be at high risk of bias. Common pitfalls included inadequate sample sizes, poor handling of missing data, failure to account for censored participants, and weak validation of models. Conclusions: Current AI applications for COVID-19 are not ready for deployment in acute care settings, given their limited scope and poor quality. Our findings underscore the need for improvements to facilitate safe and effective clinical adoption of AI applications, for and beyond the COVID-19 pandemic.