Evaluation of the Hematological Patterns from Up to 985 Days of Long COVID: A Cross-Sectional Study.

Long COVID affects many individuals following acute coronavirus disease 2019 (COVID-19), and hematological changes can persist after the acute COVID-19 phase. This study aimed to evaluate these hematological laboratory markers, linking them to clinical findings and long-term outcomes in patients with long COVID. This cross-sectional study selected participants from a 'long COVID' clinical care program in the Amazon region. Clinical data and baseline demographics were obtained, and blood samples were collected to quantify erythrogram-, leukogram-, and plateletgram-related markers. Long COVID was reported for up to 985 days. Patients hospitalized in the acute phase had higher mean red/white blood cell, platelet, and plateletcrit levels and red blood cell distribution width. Furthermore, hematimetric parameters were higher in shorter periods of long COVID than in longer periods. Patients with more than six concomitant long COVID symptoms had a higher white blood cell count, a shorter prothrombin time (PT), and increased PT activity. Our results indicate there may be a compensatory mechanism for erythrogram-related markers within 985 days of long COVID. Increased levels of leukogram-related markers and coagulation activity were observed in the worst long COVID groups, indicating an exacerbated response after the acute disturbance, which is uncertain and requires further investigation.

Multiparameter mobile blood analysis for complete blood count using contrast-enhanced defocusing imaging and machine vision.

Blood analysis through complete blood count is the most basic medical test for disease diagnosis. Conventional blood analysis requires bulky and expensive laboratory facilities and skilled technicians, limiting the universal medical use of blood analysis outside well-equipped laboratory environments. Here, we propose a multiparameter mobile blood analyzer combined with label-free contrast-enhanced defocusing imaging (CEDI) and machine vision for instant and on-site diagnostic applications. We designed a low-cost and high-resolution miniature microscope (size: 105 mm × 77 mm × 64 mm, weight: 314 g) that comprises a pair of miniature aspheric lenses and a 415 nm LED for blood image acquisition. The analyzer, adopting CEDI, can obtain both the refractive index distributions of the white blood cell (WBC) and hemoglobin spectrophotometric information, enabling the analyzer to supply rich blood parameters, including the five-part WBC differential count, red blood cell (RBC) count, and mean corpuscular hemoglobin (MCH) quantification with machine vision algorithms and the Lambert-Beer law. We have shown that our assay can analyze a blood sample within 10 minutes without complex staining, and measurements (30 samples) from the analyzer have a strong linear correlation with clinical reference values (significance level of 0.0001). This study provides a miniature, light weight, low-cost, and easy-to-use blood analysis technique that overcomes the challenge of simultaneously realizing FWD count, RBC count, and MCH analysis using a mobile device and has great potential for integrated surveillance of various epidemic diseases, including coronavirus infection, invermination, and anemia, especially in low- and middle-income countries.

Can We Predict a Higher Risk of Urothelial Bladder Cancer With a Simple Blood Test?

BACKGROUND/AIM: The COVID-19 pandemic highlighted the need to develop tools prioritizing high risk patients for urgent evaluation. Our objective was to determine whether Glasgow Prognostic Score (GPS), an inflammation-based score, can predict higher grade and stage urothelial bladder cancer in patients with gross hematuria who need urgent evaluation. PATIENTS AND METHODS: We analyzed a database of 129 consecutive patients presenting with gross hematuria. GPS was calculated using pretreatment C-reactive protein (CRP) and albumin levels. Patients with bacteriuria or other known malignancies were excluded. The relationship between GPS and final diagnosis was analyzed with multivariate logistic regression. RESULTS: A total of 101 patients were included in the study and 24 patients were identified without any pathology and 77 with a bladder tumor. Pathology demonstrated 21 with muscle invasive, 18 with high grade non-muscle invasive, and 38 with low grade superficial bladder cancer. Twenty-six of 39 (67%) patients with high grade tumors had a GPS of 1 or 2 compared to only 8 out of 62 (13%) patients with either low grade or negative findings (p<0.0001). Ten of 21 (48%) patients with muscle invasive disease had a GPS of 2 compared to 1 out of 18 (6%) with high grade non muscle invasive tumors (p=0.04). On multivariate analysis, GPS was a strong independent predictor of high grade and stage bladder cancer. CONCLUSION: GPS may serve as a highly accessible predictor of high grade, high stage, and large urothelial bladder tumors at the time of initial evaluation and can help identify patients who need urgent evaluation.

Use of an algorithm based on routine blood laboratory tests to exclude COVID-19 in a screening-setting of healthcare workers.

BACKGROUND: COVID-19 is an ongoing pandemic leading to exhaustion of the hospital care system. Our health care system has to deal with a high level of sick leave of health care workers (HCWs) with COVID-19 related complaints, in whom an infection with SARS-CoV-2 has to be ruled out before they can return back to work. The aim of the present study is to investigate if the recently described CoLab-algorithm can be used to exclude COVID-19 in a screening setting of HCWs. METHODS: In the period from January 2021 till March 2021, HCWs with COVID-19-related complaints were prospectively collected and included in this study. Next to the routinely performed SARS-CoV-2 RT-PCR, using a set of naso- and oropharyngeal swab samples, two blood tubes (one EDTA- and one heparin-tube) were drawn for analysing the 10 laboratory parameters required for running the CoLab-algorithm. RESULTS: In total, 726 HCWs with a complete CoLab-laboratory panel were included in this study. In this group, 684 HCWs were tested SARS-CoV-2 RT-PCR negative and 42 cases RT-PCR positive. ROC curve analysis showed an area under the curve (AUC) of 0.853 (95% CI: 0.801-0.904). At a safe cut-off value for excluding COVID-19 of -6.525, the sensitivity was 100% with a specificity of 34% (95% CI: 21 to 49%). No SARS-CoV-2 RT-PCR cases were missed with this cut-off and COVID-19 could be safely ruled out in more than one third of HCWs. CONCLUSION: The CoLab-score is an easy and reliable algorithm that can be used for screening HCWs with COVID-19 related complaints. A major advantage of this approach is that the results of the score are available within 1 hour after collecting the samples. This results in a faster return to labour process of a large part of the COVID-19 negative HCWs (34%), next to a reduction in RT-PCR tests (reagents and labour costs) that can be saved.

Clinical applications of machine learning in the survival prediction and classification of sepsis: coagulation and heparin usage matter.

BACKGROUND: Sepsis is a life-threatening syndrome eliciting highly heterogeneous host responses. Current prognostic evaluation methods used in clinical practice are characterized by an inadequate effectiveness in predicting sepsis mortality. Rapid identification of patients with high mortality risk is urgently needed. The phenotyping of patients will assistant invaluably in tailoring treatments. METHODS: Machine learning and deep learning technology are used to characterize the patients' phenotype and determine the sepsis severity. The database used in this study is MIMIC-III and MIMIC-IV ('Medical information Mart for intensive care') which is a large, public, and freely available database. The K-means clustering is used to classify the sepsis phenotype. Convolutional neural network (CNN) was used to predict the 28-day survival rate based on 35 blood test variables of the sepsis patients, whereas a double coefficient quadratic multivariate fitting function (DCQMFF) is utilized to predict the 28-day survival rate with only 11 features of sepsis patients. RESULTS: The patients were grouped into four clusters with a clear survival nomogram. The first cluster (C_1) was characterized by low white blood cell count, low neutrophil, and the highest lymphocyte proportion. C_2 obtained the lowest Sequential Organ Failure Assessment (SOFA) score and the highest survival rate. C_3 was characterized by significantly prolonged PTT, high SIC, and a higher proportion of patients using heparin than the patients in other clusters. The early mortality rate of patients in C_3 was high but with a better long-term survival rate than that in C_4. C_4 contained septic coagulation patients with the worst prognosis, characterized by slightly prolonged partial thromboplastin time (PTT), significantly prolonged prothrombin time (PT), and high septic coagulation disease score (SIC). The survival rate prediction accuracy of CNN and DCQMFF models reached 92% and 82%, respectively. The models were tested on an external dataset (MIMIC-IV) and achieved good performance. A DCQMFF-based application platform was established for fast prediction of the 28-day survival rate. CONCLUSION: CNN and DCQMFF accurately predicted the sepsis patients' survival, while K-means successfully identified the phenotype groups. The distinct phenotypes associated with survival, and significant features correlated with mortality were identified. The findings suggest that sepsis patients with abnormal coagulation had poor outcomes, abnormal coagulation increase mortality during sepsis. The anticoagulation effects of appropriate heparin sodium treatment may improve extensive micro thrombosis-caused organ failure.

Association of Covid-19 with blood type A in relation to blood sugar, urea, and blood test (D-dimer and ferritin) in patients from Al-Najaf.

COVID-19 is an emerging infectious disease caused by the novel enveloped single-stranded RNA virus quickly declared a pandemic. This study aimed to investigate the severity of COVID-19 infection in patients with blood group type A. A cross-sectional study was conducted at Al-Amal specialized hospital, Al-Najaf (March 8 to March 20/2021). The study included 123 hospitalized patients (63 females and 60 males), aged between 15-95 years, diagnosed with COVID-19, tested for blood group, blood sugar, blood urea, D-dimer, and serum ferritin. Results indicated significant differences in blood sugar and D-dimer in patients with type A blood group at P>0.05. At the same time, no significant difference was found in blood urea and ferritin at P>0.05. The majority of patients showed elevated levels of blood sugar, blood urea, serum D-dimer and ferritin. COVID-19 can infect people of all ages and causes severe infection in all blood groups.

Domain Shifts in Machine Learning Based Covid-19 Diagnosis From Blood Tests.

Many previous studies claim to have developed machine learning models that diagnose COVID-19 from blood tests. However, we hypothesize that changes in the underlying distribution of the data, so called domain shifts, affect the predictive performance and reliability and are a reason for the failure of such machine learning models in clinical application. Domain shifts can be caused, e.g., by changes in the disease prevalence (spreading or tested population), by refined RT-PCR testing procedures (way of taking samples, laboratory procedures), or by virus mutations. Therefore, machine learning models for diagnosing COVID-19 or other diseases may not be reliable and degrade in performance over time. We investigate whether domain shifts are present in COVID-19 datasets and how they affect machine learning methods. We further set out to estimate the mortality risk based on routinely acquired blood tests in a hospital setting throughout pandemics and under domain shifts. We reveal domain shifts by evaluating the models on a large-scale dataset with different assessment strategies, such as temporal validation. We present the novel finding that domain shifts strongly affect machine learning models for COVID-19 diagnosis and deteriorate their predictive performance and credibility. Therefore, frequent re-training and re-assessment are indispensable for robust models enabling clinical utility.

An Ensemble Learning Model for COVID-19 Detection from Blood Test Samples.

Current research endeavors in the application of artificial intelligence (AI) methods in the diagnosis of the COVID-19 disease has proven indispensable with very promising results. Despite these promising results, there are still limitations in real-time detection of COVID-19 using reverse transcription polymerase chain reaction (RT-PCR) test data, such as limited datasets, imbalance classes, a high misclassification rate of models, and the need for specialized research in identifying the best features and thus improving prediction rates. This study aims to investigate and apply the ensemble learning approach to develop prediction models for effective detection of COVID-19 using routine laboratory blood test results. Hence, an ensemble machine learning-based COVID-19 detection system is presented, aiming to aid clinicians to diagnose this virus effectively. The experiment was conducted using custom convolutional neural network (CNN) models as a first-stage classifier and 15 supervised machine learning algorithms as a second-stage classifier: K-Nearest Neighbors, Support Vector Machine (Linear and RBF), Naive Bayes, Decision Tree, Random Forest, MultiLayer Perceptron, AdaBoost, ExtraTrees, Logistic Regression, Linear and Quadratic Discriminant Analysis (LDA/QDA), Passive, Ridge, and Stochastic Gradient Descent Classifier. Our findings show that an ensemble learning model based on DNN and ExtraTrees achieved a mean accuracy of 99.28% and area under curve (AUC) of 99.4%, while AdaBoost gave a mean accuracy of 99.28% and AUC of 98.8% on the San Raffaele Hospital dataset, respectively. The comparison of the proposed COVID-19 detection approach with other state-of-the-art approaches using the same dataset shows that the proposed method outperforms several other COVID-19 diagnostics methods.

Hemolysis and blood gas analysis: it's time for a change!

Modern blood gas analyzers are not able to identify hemolysis, lipemia and icterus; therefore, the aim of this study was to assess the influence of hemolysis on blood gas samples. Blood gas analysis represents an essential part in the diagnosis and treatment of critically ill patients, including those affected by the pandemic coronavirus disease 2019 (COVID-19). Hemolysis, lipemia, and icterus, are causes of clinical misinterpretation of laboratory tests. A total of 1244 blood gas specimens were collected over a one-week period from different clinical wards, including the Emergency Department, and were assessed for serum indices on Cobas C6000 CE (Roche Diagnostics, Mannheim, Germany). The prevalence of hemolysis, lipemia, and icterus were 5%, 12%, and 14%, respectively. Sample storage at room temperature, delivery to central laboratory using pneumatic tube system, as well as small sample size, strongly affected blood gas parameters (p < .01). Hemolysis led to an increase in analytical bias for pH, pO2, and potassium, and a significant decrease for pCO2, HCO3-, sodium, and Ca2+ (p <.01). Currently, hemolysis detection systems are not yet widespread, and a rapid centrifugation of samples after blood gas analysis along with the assessment of serum indices represent the only prompt approach to identify unsuitable results, avoiding pitfalls in clinical decision-making, although it cannot be applied to the Emergency Department routine. Blood gas analyzers manufacturers and suppliers should implement automated built-in serum indices detection systems.

Feature selection reveal peripheral blood parameter's changes between COVID-19 infections patients from Brazil and Ecuador.

The investigation of conventional complete blood-count (CBC) data for classifying the SARS-CoV-2 infection status became a topic of interest, particularly as a complementary laboratory tool in developing and third-world countries that financially struggled to test their population. Although hematological parameters in COVID-19-affected individuals from Asian and USA populations are available, there are no descriptions of comparative analyses of CBC findings between COVID-19 positive and negative cases from Latin American countries. In this sense, machine learning techniques have been employed to examine CBC data and aid in screening patients suspected of SARS-CoV-2 infection. In this work, we used machine learning to compare CBC data between two highly genetically distinguished Latin American countries: Brazil and Ecuador. We notice a clear distribution pattern of positive and negative cases between the two countries. Interestingly, almost all red blood cell count parameters were divergent. For males, neutrophils and lymphocytes are distinct between Brazil and Ecuador, while eosinophils are distinguished for females. Finally, neutrophils, lymphocytes, and monocytes displayed a particular distribution for both genders. Therefore, our findings demonstrate that the same set of CBC features relevant to one population is unlikely to apply to another. This is the first study to compare CBC data from two genetically distinct Latin American countries.

Estimation of erythrocyte parameters of general blood analysis in patients with SARS-CoV-2 -associated pneumonia.

The study of the features and dynamics of the erythrocyte parameters of general blood analysis in patients with cardiovascular diseases who underwent SARS-CoV-2 associated pneumonia is of great practical importance. That was a prospective study. The study included 106 patients with SARS-CoV-2-associated pneumonia. All patients were divided into 2 groups. The first group included 51 patients without CVD, the second group included 55 patients with CVD .Patients in both groups underwent laboratory examination of blood samples at the time of hospitalization and 3 months after discharge from the hospital. Parameters of the erythroid series of the general blood test were assessed. Among inflammatory biomarkers, we examined the concentration of C-reactive protein (CRP), high-sensitivity CRP (hs-CRP) and homocysteine. Initially all patients underwent computed tomography of the chest organs. Revealed what indicators of the erythroid series in the groups of patients with and without CVD had significant differences in a number of parameters: ESR; RDW-SD and RDW-CV with significant excess of parameters in group 2. Three months after discharge from the hospital, patients in both groups had a significant increase in HCT, MCV, MCH. There was detected decrease in both groups in MCHC, RDW-CV (p<0.001 for all parameters), ESR level in group 2.At baseline, CRP exceeded reference values in both groups of patients, reaching maximum values in group 2. After 3 months CRP decreased significantly only in group 1. Increased CRP was associated with elevated hs-CRP in 3 months after discharge and elevated homocysteine levels in both groups, indicating the persistence of prolonged inflammatory vascular reaction in patients after SARS-CoV-2 associated pneumonia, more pronounced in group 2 patients. RDW-CV over 13.6 and lymphocytes / CRP less than 0.6 increase the likelihood of having lung tissue damage over 50% by 9.3 and 5.9 times, respectively. Thus, the data obtained confirm that RDW-CV, the coefficient of variation of erythrocyte distribution width, associated with the parameters of inflammatory response and the lymphocytes / CRP is lung volume marker and of COVID-19 severity. Careful consideration of already known laboratory parameters allows us to expand the number of indicators influencing the risk of COVID-19 complications and enable an earlier response to a difficult situation.

Changes in peripheral blood cellular morphology as diagnostic markers for COVID-19 infection.

INTRODUCTION: Real-time reverse-transcriptase polymerase chain reaction (RT-PCR) assays were established to detect severe acute respiratory syndrome-coronavirus 2 (SARS-CoV-2). However, due to the high rate of false negative results, additional tests as computed tomography (CT) scans of the chest and blood chemistry are required to properly diagnose COVID-19 infection. Abnormal morphological changes of peripheral blood cells as granulocytic dysmorphism and abnormal reactive lymphocytes have been described in some cases. The aim of the present study was to investigate the morphological changes affecting all peripheral blood cells of COVID-19 patients, in order to find any specific abnormalities that could help in the early diagnosis and/or prognosis. METHODS: Peripheral blood smears of 113 COVID-19 patients and 50 non-COVID-19 controls were examined for morphological changes in the period between October 2020 and January 2021 (second wave). We set a score value in which every morphological abnormality was given one point in each examined blood smear. Score, neurophil/lymphocyte (N/L) ratio, and blood chemistry were compared to the severity and outcome of the disease. RESULTS: Significant morphological changes were found when compared to control blood smears. Various abnormalities as pyknotic cells, broken cells, pseudo Pelger-Huët, abnormal lymphocytes, abnormal monocytes, and leukoerythroblastic reaction were found. Cases with higher scores had unfavorable outcomes (p = .005). High interleukin-6 (IL-6) levels were correlated to pyknotic cells (p = .003). CONCLUSION: The blood picture of COVID-19 patients revealed various morphological changes that are not detected with the same frequency and variability in other viral infections. The prominent morphological changes can be predictive of an undesirable outcome of the disease.

Using different machine learning models to classify patients into mild and severe cases of COVID-19 based on multivariate blood testing.

COVID-19 is a serious respiratory disease. The ever-increasing number of cases is causing heavier loads on the health service system. Using 38 blood test indicators on the first day of admission for the 422 patients diagnosed with COVID-19 (from January 2020 to June 2021) to construct different machine learning (ML) models to classify patients into either mild or severe cases of COVID-19. All models show good performance in the classification between COVID-19 patients into mild and severe disease. The area under the curve (AUC) of the random forest model is 0.89, the AUC of the naive Bayes model is 0.90, the AUC of the support vector machine model is 0.86, and the AUC of the KNN model is 0.78, the AUC of the Logistic regression model is 0.84, and the AUC of the artificial neural network model is 0.87, among which the naive Bayes model has the best performance. Different ML models can classify patients into mild and severe cases based on 38 blood test indicators taken on the first day of admission for patients diagnosed with COVID-19.

Hematological changes associated with COVID-19 infection.

BACKGROUND: The unresolved COVID-19 pandemic considerably impacts the health services in Iraq and worldwide. Consecutive waves of mutated virus increased virus spread and further constrained health systems. Although molecular identification of the virus by polymerase chain reaction is the only recommended method in diagnosing COVID-19 infection, radiological, biochemical, and hematological studies are substantially important in risk stratification, patient follow-up, and outcome prediction. AIM: This narrative review summarized the hematological changes including the blood indices, coagulative indicators, and other associated biochemical laboratory markers in different stages of COVID-19 infection, highlighting the diagnostic and prognostic significance. METHODS: Literature search was conducted for multiple combinations of different hematological tests and manifestations with novel COVID-19 using the following key words: "hematological," "complete blood count," "lymphopenia," "blood indices," "markers" "platelet" OR "thrombocytopenia" AND "COVID-19," "coronavirus2019," "2019-nCoV," OR "SARS-CoV-2." Articles written in the English language and conducted on human samples between December 2019 and January 2021 were included. RESULTS: Hematological changes are not reported in asymptomatic or presymptomatic COVID-19 patients. In nonsevere cases, hematological changes are subtle, included mainly lymphocytopenia (80.4%). In severe, critically ill patients and those with cytokine storm, neutrophilia, lymphocytopenia, elevated D-dimer, prolonged PT, and reduced fibrinogen are predictors of disease progression and adverse outcome. CONCLUSION: Monitoring hematological changes in patients with COVID-19 can predict patients needing additional care and stratify the risk for severe course of the disease. More studies are required in Iraq to reflect the hematological changes in COVID-19 as compared to global data.

Clinical Features and Laboratory Examination to Identify Severe Patients with COVID-19: A Systematic Review and Meta-Analysis.

BACKGROUND: With the COVID-19 epidemic breakout in China, up to 25% of diagnosed cases are considered to be severe. To effectively predict the progression of COVID-19 via patients' clinical features at an early stage, the prevalence of these clinical factors and their relationships with severe illness were assessed. METHODS: In this study, electronic databases (PubMed, Embase, Web of Science, and Chinese database) were searched to obtain relevant studies, including information on severe patients. Publication bias analysis, sensitivity analysis, prevalence, sensitivity, specificity, likelihood ratio, diagnosis odds ratio calculation, and visualization graphics were achieved through software Review Manager 5.3, Stata 15, Meta-DiSc 1.4, and R. RESULTS: Data of 3.547 patients from 24 studies were included in this study. The results revealed that patients with chronic respiratory system diseases (pooled positive likelihood 6.07, 95% CI: 3.12-11.82), chronic renal disease (4.79, 2.04-11.25), cardiovascular disease (3.45, 2.19-5.44), and symptoms of the onset of chest tightness (3.8, 1.44-10.05), shortness of breath (3.18, 2.24-4.51), and diarrhea (2.04, 1.38-3.04) exhibited increased probability of progressing to severe illness. C-reactive protein, ratio of neutrophils to lymphocytes, and erythrocyte sedimentation rate increased a lot in severe patients compared to nonsevere. Yet, it was found that clinical features including fever, cough, and headache, as well as some comorbidities, have little warning value. CONCLUSIONS: The clinical features and laboratory examination could be used to estimate the process of infection in COVID-19 patients. The findings contribute to the more efficient prediction of serious illness for patients with COVID-19 to reduce mortality.