Machine Learning-Based Prediction of Hemoglobinopathies Using Complete Blood Count Data.

BACKGROUND: Hemoglobinopathies, the most common inherited blood disorder, are frequently underdiagnosed. Early identification of carriers is important for genetic counseling of couples at risk. The aim of this study was to develop and validate a novel machine learning model on a multicenter data set, covering a wide spectrum of hemoglobinopathies based on routine complete blood count (CBC) testing. METHODS: Hemoglobinopathy test results from 10 322 adults were extracted retrospectively from 8 Dutch laboratories. eXtreme Gradient Boosting (XGB) and logistic regression models were developed to differentiate negative from positive hemoglobinopathy cases, using 7 routine CBC parameters. External validation was conducted on a data set from an independent Dutch laboratory, with an additional external validation on a Spanish data set (n = 2629) specifically for differentiating thalassemia from iron deficiency anemia (IDA). RESULTS: The XGB and logistic regression models achieved an area under the receiver operating characteristic (AUROC) of 0.88 and 0.84, respectively, in distinguishing negative from positive hemoglobinopathy cases in the independent external validation set. Subclass analysis showed that the XGB model reached an AUROC of 0.97 for ß-thalassemia, 0.98 for α0-thalassemia, 0.95 for homozygous α+-thalassemia, 0.78 for heterozygous α+-thalassemia, and 0.94 for the structural hemoglobin variants Hemoglobin C, Hemoglobin D, Hemoglobin E. Both models attained AUROCs of 0.95 in differentiating IDA from thalassemia. CONCLUSIONS: Both the XGB and logistic regression model demonstrate high accuracy in predicting a broad range of hemoglobinopathies and are effective in differentiating hemoglobinopathies from IDA. Integration of these models into the laboratory information system facilitates automated hemoglobinopathy detection using routine CBC parameters.

Clinical value of the red blood cell distribution width to albumin ratio in the assessment of prognosis in critically ill patients with sepsis: a retrospective analysis.

Background: Red blood cell (RBC) distribution width (RDW) to albumin ratio is a novel biomarker and its prognostic effect on critically ill patients with sepsis has not been extensively investigated. The objective of this study was to identify the prognostic value of the RDW to albumin ratio in these patients. Methods: Data were extracted from the Medical Information Mart for Intensive Care III (MIMIC-III) database. A Cox proportional hazards model and restricted cubic spline model were used to determine the association of RDW to albumin ratio with mortality. Receiver operating characteristic (ROC) curves and Kaplan-Meier survival curves were applied, and the area under the curve (AUC) was used to compare the predictive value. Results: A total of 3,969 eligible patients were enrolled. The median RDW to albumin ratio was significantly higher in non-survivors than in survivors at 30 and 90 days. Patients were divided into groups according to the RDW to albumin ratio, and the risk of 30- and 90-day mortality markedly increased in the group with a higher ratio. The relationship between the RDW to albumin ratio as a continuous variable and 30-day mortality also showed an upward trend in the restricted cubic spline. The AUC of the RDW to albumin ratio was 0.633 in discriminating 30-day mortality which was similar to that of the lactate to albumin ratio (AUC =0.617; P=0.133) and higher than that of the neutrophil percentage to albumin ratio (AUC =0.559; P<0.001). Conclusions: The RDW to albumin ratio is a promising biomarker for assessing the prognosis of critically ill patients with sepsis. Its predictive value in determining mortality was found to be similar to that of the lactate to albumin ratio and superior to that of the neutrophil percentage to albumin ratio.

Usefulness of extended inflammatory parameters related to neutrophil activation reported by Sysmex XN-1000 hematology analyzer for predicting complicated acute appendicitis. Comparison with canonical inflammatory laboratory tests.

AIM: Accurate diagnosis of complicated appendicitis is of importance to ensure that patients receive early and effective treatment, minimizing the risk of postoperative complications to promote successful recovery. Biochemical markers are a promising tool to identify complicated appendicitis. We aimed to evaluate the potential role of novel parameters related with neutrophil activation, known as "Extended Inflammation Parameters" (EIP), included in blood cell count reported by Sysmex XN-Series analyzers, compared to other canonical biomarkers in identifying complicated appendicitis. METHOD: Prospective observational study including patients with confirmed diagnosis of acute appendicitis. C-reactive protein (CRP), procalcitonin, cell blood count, including white blood cell (WBC), absolute neutrophil (ANC) and immature granulocyte (IG) count and EIP (neutrophil reactivity [NEUT-RI] and granularity intensity [NEUT-GI]) were analyzed before surgery. Their accuracy to diagnose complicated appendicitis was tested in an ROC curve analysis. RESULTS: Our population study included 119 patients, and appendicitis was complicated in 58 (48.7%). NLR, CRP and procalcitonin levels, ANC and IG count and NEUT-RI and NEUT-GI were higher in patients with complicated appendicitis. Regarding accuracy for complicated appendicitis, CRP was the biomarker with the highest performance (ROC AUC: 0.829), with an optimal cutoff of 73.1 mg/L (sensitivity: 63.8%, specificity: 88.5%). NEUT-RI and NEUT-GI achieved both significant but poor accuracy, with ROC AUC of 0.606 and 0.637, respectively. CONCLUSIONS: Novel laboratory tests reported by Sysmex XN-Series analyzers have poor accuracy for identifying complicated appendicitis. In this study, CRP was the biomarker with the highest performance and may be useful as predictor of the severity of acute appendicitis.

ICSH guidance for internal quality control policy for blood cell counters.

This paper is a description of the ICSH guidance for internal quality control (IQC) policy for blood cell counters. It follows from and links to a separate ICSH review for such policies and practices. The ICSH has gathered information regarding the current state of practice through review of published guidance from regulatory bodies, a questionnaire to six major cell counter manufacturers and a survey issued to 191 diagnostic laboratories in four countries (China, the Republic of Ireland, Spain, and the United Kingdom) on their IQC practice and approach to the use of commercial IQC materials. This has revealed diversity both in guidance and in practice around the world. There is diversity in guidance from regulatory organizations in regard to IQC methods each recommends, clinical levels to use and frequency to run commercial controls, and finally recommended sources of commercial control materials. The diversity in practice among clinical laboratories spans the areas of IQC methods used, derivation of target values, and action limits used with commercial control materials, and frequency of running commercial controls materials. These findings and their implications for IQC Practice are addressed in this guidance document, which proposes a harmonized approach to address the issues faced by diagnostic laboratories.

ICSH review of internal quality control policy for blood cell counters.

INTRODUCTION: This paper is a report of an ICSH review of policies and practices for internal quality control (IQC) policy for haematology cell counters among regulatory bodies, cell counter manufacturers and diagnostic laboratories. It includes a discussion of the study findings and links to separate ICSH guidance for such policies and practices. The application of internal quality control (IQC) methods is an essential pre-requisite for all clinical laboratory testing including the blood count (Full Blood Count, FBC, or Complete Blood Count, CBC). METHODS: The ICSH has gathered information regarding the current state of practice through review of published guidance from regulatory bodies, a questionnaire to six major cell counter manufacturers (Abbott Diagnostics, Beckman Coulter, Horiba Medical Diagnostic Instruments & Systems, Mindray Medical International, Siemens Healthcare Diagnostics and Sysmex Corporation) and a survey issued to 191 diagnostic laboratories in four countries (China, Republic of Ireland, Spain and the United Kingdom) on their IQC practice and approach to use of commercial IQC materials. RESULTS: This has revealed diversity both in guidance and in practice around the world. There is diversity in guidance from regulatory organizations in regard to IQC methods each recommends, clinical levels to use and frequency to run commercial controls, and finally recommended sources of commercial controls. The diversity in practice among clinical laboratories spans the areas of IQC methods used, derivation of target values and action limits used with control materials, and frequency of running commercial controls materials. CONCLUSIONS: These findings and their implications for IQC Practice are discussed in this paper. They are used to inform a separate guidance document, which proposes a harmonized approach to address the issues faced by diagnostic laboratories.

Report of the International Council for Standardization in Haematology working group for standardization of reticulocyte parameters.

INTRODUCTION: The International Council for Standardization in Haematology convened a working group to assess and propose improvements upon the state of standardization and harmonization of reticulocyte parameters among commercial hematology analyzers. METHODS: An international group of laboratory hematologists prospectively collected and analyzed clinical samples using locally available IVD commercial hematology analyzers. Eight hundred and fifty-five total samples were collected at 6 sites using 9 distinct analyzer types. Samples were assessed for reticulocyte percent (RET%), immature reticulocyte fraction (IRF), and reticulocyte hemoglobin content (RHC). Method comparison and regression statistics were calculated. These analyses were used to determine whether statistical recalibration offered a potential avenue for increasing comparability between these methods. RESULTS: While methods producing reticulocyte percent were the most comparable in this study, the state of harmonization for the IRF and RHC was reduced with pearson correlation coefficients ranging from 0.955 to 0.77 and 0.927 and 0.680, respectively. Nevertheless, use of parameters from the Passing Bablok regression substantially improved the comparability of the results. In addition, precision data was derived which also demonstrated substantial differences between analyzer systems. CONCLUSION: While reticulocyte counting is correlated between the automated methods evaluated in this study, the current state of harmonization of other reticulocyte parameters is not as strong. A major challenge in moving this field forward is the need for commutable materials to facilitate comparisons between analyzers not co-located. A potential alternate approach to improve the current state would be instrument re-calibration. However, this is challenging both technically and due to national regulatory frameworks.

Analytical evaluation and quality assessment of the ARKRAY ADAMS A1c Lite HA-8380V for HbA1c.

INTRODUCTION: ARKRAY ADAMS A1c Lite HA-8380V is a fully automated high- performance liquid chromatography system for the measurement of HbA1c. We aimed to evaluate its analytical performance using the Variant Mode. METHODS: Carry-over, linearity, imprecision, trueness, interferences and comparison against ARKRAY ADAMS A1c HA-8180V and HA-8180T analyzers were studied. RESULTS: Total CVs 0.93% (IFCC units), 0.63% (NGSP units) at low concentration and 1.01% (IFCC) 0.74% (NGSP), at high concentration. Mean difference with the target values was -0.44 mmol/mol (IFCC) -0.04% (NGSP). Carry-over, linearity and method comparison were excellent.The results were not affected in the range of total Hb 39-199 g/L, labile fraction 5.7%, carbamylated Hb 9.1% nor acetylated Hb 7.8%, effect of common variants was negligible. CONCLUSIONS: the analyzer demonstrated very good analytical performances, according to the consensus criteria established for HbA1c; it is adequate for laboratories with medium-low workloads.

Analytical evaluation and quality assessment of the ARKRAY ADAMS A1c HA-8190V for Hb A1c.

ARKRAY ADAMS A1c HA-8190V is a fully automated high-pressure liquid chromatography (HPLC) system for the measurement of HbA1c. The runtime is 58 s per sample in the Variant mode and 24 s per sample in the Fast mode. We evaluated the analytical performance of this analyzer in the Variant mode, to verify the quality of analysis, according to the consensus criteria established for this measurand. Reproducibility, trueness, carry-over, linearity, interferences and comparison with ARKRAY ADAMS A1c HA-8180V and HA-8180T analyzers were evaluated. Total CVs were 0.76% (IFCC units) 0.55 (NGSP units) at low HbA1c concentration and 0.85% (IFCC units) 0.68 (NGSP units) at high HbA1c concentration. Mean difference with the target values was -1.25 mmol/mol (-0.119%) and total error at medium level was 2.83% (IFCC units), 2.46% (NGSP units) Carry-over was 0%. Linearity was shown in the range 27-122 mmol/mol (4.6-13.3%). The results were not affected in the range of total Hb 59-199 g/L, labile fraction up to 5.5%, carbamylated up to Hb 6.3% nor acetylated Hb up to 5.3%. Method comparison demonstrated good concordance between the methods. The analyzer demonstrated a high analytical performance adequate for routine clinical use in laboratories with high workloads.

Recent advances in laboratory hematology reflected by a decade of CCLM publications.

On the occasion of the 60th anniversary of Clinical Chemistry and Laboratory Medicine (CCLM) we present a review of recent developments in the discipline of laboratory hematology as these are reflected by papers published in CCLM in the period 2012-2022. Since data on CCLM publications from 1963 to 2012 are also available, we were able to make a comparison between the two periods. This interestingly revealed that the share of laboratory hematology papers has steadily increased and reached now 16% of all papers published in CCLM. It also became evident that blood coagulation and fibrinolysis, erythrocytes, platelets and instrument and method evaluation constituted the 'hottest' topics with regard to number of publications. Some traditional, characteristic CCLM categories like reference intervals, standardization and harmonization, were more stable and probably will remain so in the future. With the advent of important newer topics, like new coagulation assays and drugs and cell population data generated by hematology analyzers, laboratory hematology is anticipated to remain a significant discipline in CCLM publications.

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.

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.

Beyond the In-Practice CBC: The Research CBC Parameters-Driven Machine Learning Predictive Modeling for Early Differentiation among Leukemias.

A targeted and timely treatment can be a beneficial tool for patients with hematological emergencies (particularly acute leukemias). The key challenges in the early diagnosis of leukemias and related hematological disorders are their symptom-sharing nature and prolonged turnaround time as well as the expertise needed in reporting confirmatory tests. The present study made use of the potential morphological and immature fraction-related parameters (research items or cell population data) generated during complete blood cell count (CBC), through artificial intelligence (AI)/machine learning (ML) predictive modeling for early (at the pre-microscopic level) differentiation of various types of leukemias: acute from chronic as well as myeloid from lymphoid. The routine CBC parameters along with research CBC items from a hematology analyzer in the diagnosis of 1577 study subjects with hematological neoplasms were collected. The statistical and data visualization tools, including heat-map and principal component analysis (PCA,) helped in the evaluation of the predictive capacity of research CBC items. Next, research CBC parameter-driven artificial neural network (ANN) predictive modeling was developed to use the hidden trend (disease's signature) by increasing the auguring accuracy of these potential morphometric parameters in differentiation of leukemias. The classical statistics for routine and research CBC parameters showed that as a whole, all study items are significantly deviated among various types of leukemias (study groups). The CPD parameter-driven heat-map gave clustering (separation) of myeloid from lymphoid leukemias, followed by the segregation (nodding) of the acute from the chronic class of that particular lineage. Furthermore, acute promyelocytic leukemia (APML) was also well individuated from other types of acute myeloid leukemia (AML). The PCA plot guided by research CBC items at notable variance vindicated the aforementioned findings of the CPD-driven heat-map. Through training of ANN predictive modeling, the CPD parameters successfully differentiate the chronic myeloid leukemia (CML), AML, APML, acute lymphoid leukemia (ALL), chronic lymphoid leukemia (CLL), and other related hematological neoplasms with AUC values of 0.937, 0.905, 0.805, 0.829, 0.870, and 0.789, respectively, at an agreeably significant (10.6%) false prediction rate. Overall practical results of using our ANN model were found quite satisfactory with values of 83.1% and 89.4.7% for training and testing datasets, respectively. We proposed that research CBC parameters could potentially be used for early differentiation of leukemias in the hematology-oncology unit. The CPD-driven ANN modeling is a novel practice that substantially strengthens the predictive potential of CPD items, allowing the clinicians to be confident about the typical trend of the "disease fingerprint" shown by these automated potential morphometric items.

Harmonized D-dimer levels upon admission for prognosis of COVID-19 severity: Results from a Spanish multicenter registry (BIOCOVID-Spain study).

Coagulopathy is a key feature of COVID-19 and D-dimer has been reported as a predictor of severity. However, because D-dimer test results vary considerably among assays, resolving harmonization issues is fundamental to translate findings into clinical practice. In this retrospective multicenter study (BIOCOVID study), we aimed to analyze the value of harmonized D-dimer levels upon admission for the prediction of in-hospital mortality in COVID-19 patients. All-cause in-hospital mortality was defined as endpoint. For harmonization of D-dimer levels, we designed a model based on the transformation of method-specific regression lines to a reference regression line. The ability of D-dimer for prediction of death was explored by receiver operating characteristic curves analysis and the association with the endpoint by Cox regression analysis. Study population included 2663 patients. In-hospital mortality rate was 14.3%. Harmonized D-dimer upon admission yielded an area under the curve of 0.66, with an optimal cut-off value of 0.945 mg/L FEU. Patients with harmonized D-dimer ≥ 0.945 mg/L FEU had a higher mortality rate (22.4% vs. 9.2%; p < 0.001). D-dimer was an independent predictor of in-hospital mortality, with an adjusted hazard ratio of 1.709. This is the first study in which a harmonization approach was performed to assure comparability of D-dimer levels measured by different assays. Elevated D-dimer levels upon admission were associated with a greater risk of in-hospital mortality among COVID-19 patients, but had limited performance as prognostic test.

Mature and Immature/Activated Cells Fractionation: Time for a Paradigm Shift in Differential Leucocyte Count Reporting?

Leucocytes, especially neutrophils featuring pro- and anti-cancerous characteristics, are involved in nearly every stage of tumorigenesis. Phenotypic and functional differences among mature and immature neutrophil fractions are well reported, and their correlation with tumor progression and therapy has emerging implications in modern oncology practices. Technological advancements enabled modern hematology analyzers to generate extended information (research parameters) during complete blood cell count (CBC) analysis. We hypothesized that neutrophil and lymphocyte fractions-related extended differential leucocytes count (DLC) parameters hold superior diagnostic utility over routine modalities. The present study was carried out over a four-and-a-half-year period wherein extended neutrophil (immature granulocyte [IG] and mature neutrophil [NEUT#&]), and lymphocyte (activated/high fluorescence lymphocyte count [HFLC] and resting lymphocyte [LYMP#&]) parameters were challenged over routine neutrophil [NEUT#] and lymphocyte [LYMP#] items in a study population of 1067 hematological neoplasm patients. Extending the classical statistical approaches, machine-learning-backed data visualization was used to explore trends in the study parameters. As a whole, extended neutrophil and lymphocyte count outperformed and was diagnostically more relevant than routine neutrophil and lymphocyte parameters by showing the least difference from their respective (gold-standard) manual DLC counts. The mature neutrophil count was compared to IG, and resting lymphocyte count was compared to HFLC by calling the function 'correlation' as a 'clustering function' for heatmap based visualization. The aforementioned study parameters displayed close clustering (rearrangement) for their respective study items by presenting distinct trends of equally valuable weights (deviated values), advocating fractions-based extended DLC reporting. Importantly, using a Bland and Altman analysis analogously to a manual neutrophil count, the mature neutrophil count [NEUT#&] remained unbiased since a routine neutrophil count [NEUT#] was found to be a negatively biased. The extended DLC-parameter-driven fractions-based reporting has superior diagnostic utility over classical routine approaches; this finding can largely minimize labor-intensive manual DLC practices, especially in hematology-oncology departments.

Leukocyte differential and reactive lymphocyte counts from Sysmex XN analyzer in the evaluation of SARS-CoV-2 infection.

BACKGROUND: Leukocyte differential present certain features in COVID 19 patients. RE-LYMP (reactive lymphocytes) is an extended inflammation parameter (EIP) reported by XN analyzer (Sysmex Corporation, Kobe, Japan) reflect the activation of lymphocytes triggered by infections. We aimed to assess the clinical utility of these parameters as biomarkers for the rapid detection of COVID 19. METHODS: The study group included 200 COVID 19 and 167 patients with other infections at admission. Differences of leukocyte differential, neutrophil/lymphocyte ratio (NLR) and EIP among groups were assessed with the Kruskal-Wallis test; parameters statiscally different in the groups were tested with Receiver operating characteristic (ROC) curve analysis to assess their diagnostic performance in distinguishing SARS-CoV-2 infections. The reliability of the selected parameters was evaluated in a validation group of 347 patients (160 COVID 19 and 187 other infections). RESULTS: NLR performed well to discard viral infections, area under curve (AUC) 0.988 (95%CI 0.973 - 0.991) and RE-LYMP was useful to distinguish COVID 19 and bacterial infections AUC 0.920 (95%CI 0.884 - 0.948); the two conditions NLR> 3.3 RE-LYMP> 0.6% was applied to the validation group and 153 out of 160 COVID 19 patients were correctly distinguished (95.6%). CONCLUSIONS: Early diagnosis of SARS-CoV-2 infection is critical for better caring of patients and to reduce the threat of nosocomial infection for professionals. Leukocyte differential and RE-LYMPH could assist in a preliminary differential diagnosis of the disease.

Cardiac troponin and COVID-19 severity: Results from BIOCOVID study.

BACKGROUND: Myocardial injury is a common finding in COVID-19 strongly associated with severity. We analysed the prevalence and prognostic utility of myocardial injury, characterized by elevated cardiac troponin, in a large population of COVID-19 patients, and further evaluated separately the role of troponin T and I. METHODS: This is a multicentre, retrospective observational study enrolling patients with laboratory-confirmed COVID-19 who were hospitalized in 32 Spanish hospitals. Elevated troponin levels were defined as values above the sex-specific 99th percentile upper reference limit, as recommended by international guidelines. Thirty-day mortality was defined as endpoint. RESULTS: A total of 1280 COVID-19 patients were included in this study, of whom 187 (14.6%) died during the hospitalization. Using a nonspecific sex cut-off, elevated troponin levels were found in 344 patients (26.9%), increasing to 384 (30.0%) when a sex-specific cut-off was used. This prevalence was significantly higher (42.9% vs 21.9%; P < .001) in patients in whom troponin T was measured in comparison with troponin I. Sex-specific elevated troponin levels were significantly associated with 30-day mortality, with adjusted odds ratios (ORs) of 3.00 for total population, 3.20 for cardiac troponin T and 3.69 for cardiac troponin I. CONCLUSION: In this multicentre study, myocardial injury was a common finding in COVID-19 patients. Its prevalence increased when a sex-specific cut-off and cardiac troponin T were used. Elevated troponin was an independent predictor of 30-day mortality, irrespective of cardiac troponin assay and cut-offs to detect myocardial injury. Hence, the early measurement of cardiac troponin may be useful for risk stratification in COVID-19.