Early prediction of COVID-19 outcome using artificial intelligence techniques and only five laboratory indices.

We aimed to develop a prediction model for intensive care unit (ICU) hospitalization of Coronavirus disease-19 (COVID-19) patients using artificial neural networks (ANN). We assessed 25 laboratory parameters at first from 248 consecutive adult COVID-19 patients for database creation, training, and development of ANN models. We developed a new alpha-index to assess association of each parameter with outcome. We used 166 records for training of computational simulations (training), 41 for documentation of computational simulations (validation), and 41 for reliability check of computational simulations (testing). The first five laboratory indices ranked by importance were Neutrophil-to-lymphocyte ratio, Lactate Dehydrogenase, Fibrinogen, Albumin, and D-Dimers. The best ANN based on these indices achieved accuracy 95.97%, precision 90.63%, sensitivity 93.55%. and F1-score 92.06%, verified in the validation cohort. Our preliminary findings reveal for the first time an ANN to predict ICU hospitalization accurately and early, using only 5 easily accessible laboratory indices.

Thromboelastometry Variables in Neonates with Perinatal Hypoxia.

Perinatal hypoxia is associated with an increased risk of coagulation disorders by enhancing the consumption of platelets and some clotting factors due to the associated severe hypoxemia, acidemia, and compromised oxygen and blood supply to the neonatal liver and bone marrow. Thromboelastometry (TEM), which estimates the dynamics of blood coagulation, may represent an attractive tool for studying the coagulation status of these neonates. We aimed at assessing the hemostatic profile of neonates with perinatal hypoxia using the standard extrinsically activated TEM (ex-TEM) assay. In total, 164 hospitalized neonates with perinatal asphyxia and/or fetal distress comprised the study subjects, and 273 healthy neonates served as controls. Ex-TEM assay was performed, SNAPPE (Score for Neonatal Acute Physiology Perinatal Extension) was calculated, and clinical findings and laboratory results were recorded in all study subjects. Hypoxic neonates expressed a prolonged clotting time (CT) and clot formation time (CFT) and reduced amplitude at 10 minutes (A10), α-angle, and maximum clot firmness compared with healthy neonates. Furthermore, asphyxiated neonates had a significantly prolonged CT and CFT and reduced A10 and α-angle compared with neonates with fetal distress. Hypoxic neonates demonstrate a hypocoagulable ex-TEM profile relative to healthy neonates, indicating a potential role of TEM in the early detection of coagulation derangement in perinatal hypoxia.

Red Blood Cell Alloantibody Titration - Does the Titration Method Matter?

BACKGROUND: Red blood cell (RBC) alloantibody titration is a quasi-quantitative method to assess antibody concentration and is considered a useful means of estimating maternal alloimmunization during pregnancy. Traditionally, titration is performed using conventional tube test (CTT). The gel microcolumn agglutination-based method (GMA) has been proven reliable for many immunohematology tests. Our study compared CTT with GMA of two different, commercially available GMA systems for RBC alloantibody titration. METHODS: Serum samples with significant RBC-alloantibodies were evaluated in our study. Each sample was titrated concurrently with CTT, with ID-DiaMed-GmbH, Cressier, Switzerland (GMA1), and with DG Gel Coombs Diagnostic Grifols, Passeig Fluvial, Spain (GMA2). RESULTS: One hundred thirty-seven titration tests including 50 anti-D, 25 anti-Kell, 10 anti-E, 9 anti-Jka, 8 anti-c, 5 anti-Cw, 5 anti-Fya, 7 anti-M, 6 anti-Kpa, 3 anti-Lua, 1 anti-e, 3 anti-G, and 2 anti-Cha were performed and evaluated. Samples tested by CTT versus GMA1 and GMA2 generated mostly equal or higher titers by GMAs. The results of both comparisons were in good agreement (W = 0.91, p < 0.0001, and W = 0.92, p < 0.0001, respectively). For all antibody specificities, the mean absolute difference in titers ranged from 1 - 3 for both GMA1 and GMA2 versus CTT. Samples tested by GMA1 vs. GMA2 were in almost perfect agreement (W = 0.95, p < 0.0001). CONCLUSIONS: Although both GMAs were found slightly more sensitive than CTT for alloantibody titration, the differences were not significant and the agreement between all methods was very good, possibly indicating GMA as a suitable alternative to CTT in RBC antibody titration.

Clinical Application of Thromboelastography/Thromboelastometry (TEG/TEM) in the Neonatal Population: A Narrative Review.

Hemostasis is a dynamic age-related process, which gradually evolves from fetal life throughout childhood until adulthood. Although at birth there is a hemostatic deficit of most coagulation factors, studies have shown that this "hemostatic immaturity" is functionally counterbalanced in healthy term or preterm newborns. This delicate hemostatic balance is, however, deranged in sick neonates, resulting in an enhanced risk of hemorrhage and/or thrombosis. In critically ill neonates, conventional coagulation tests do not seem to provide reliable information or indications regarding the functional status of platelets or fibrinolysis. In contrast, viscoelastic tests, namely thromboelastography/thromboelastometry (TEG/TEM) hold promise for rapid assessment of the whole hemostatic potential, allowing immediate intervention should this be required. However, neonatal data are limited due to lack of reference values, especially in premature neonates. In this narrative review, we provide some insights around current knowledge regarding TEG/TEM applications in healthy and sick newborns. Overall, the use of viscoelastic tests in diagnosis and management of coagulation disorders in neonates is definitely worth further exploration. Consideration should be made to include these tests in the routine laboratory investigation of neonates and specific transfusion algorithms should also be developed in order to avoid treatment pitfalls.

Platelet and coagulation disorders in newly diagnosed patients with pulmonary arterial hypertension.

There is a complex and not fully elucidated association between pulmonary arterial hypertension (PAH) and coagulation disorders. The goal of this study was to evaluate platelet function, coagulation and fibrinolysis in PAH patients at diagnosis, before PAH-specific treatment initiation. We enrolled 20 healthy controls and 30 PAH patients (20 with connective tissue disease (CTD-PAH) and 10 idiopathic (iPAH)). None of the participants was on any antiplatelet or anticoagulation therapy. Blood samples from PAH patients were collected during the initial right heart catheterization. All subjects were assessed with platelet function analyzer-100 (PFA-100), epinephrine (Epi) and ADP-induced light transmission aggregometry (LTA), thromboelastometry (ROTEM) and endogenous thrombin potential (ETP). Our results showed that Epi and ADP-LTA values were significantly lower in newly diagnosed PAH patients compared to controls. Disaggregation was present in 73% of patients, a characteristic not seen in healthy individuals. In ROTEM assay, CT and CFT measurements were significantly higher and a angle lower compared to controls. ETP testing revealed significantly reduced outcomes in AUC, Cmax and Tmax. When CTD-PAH and iPAH patient groups were compared, iPAH ADP-LTA values were significantly decreased compared to CTD-PAH. In conclusion, newly diagnosed PAH patients presented with decreased platelet aggregation, clot propagation and thrombin generation, along with delayed initiation of the coagulation process. These hemostatic deficits could indicate an "exhaustion" of the coagulation process that could be caused by endothelial dysfunction and chronic activation of the procoagulant pathways. Further studies are warranted to confirm these laboratory findings and assess their potential clinical significance.

Clinical Outcomes and Neuroimaging Profiles in Nondisabled Patients With Anticoagulant-Related Intracerebral Hemorrhage.

Background and Purpose- The aim of this study was to prospectively validate our prior findings of smaller hematoma volume and lesser neurological deficit in nonvitamin K oral anticoagulant (NOAC) compared with Vitamin K antagonist (VKA)-related intracerebral hemorrhage (ICH). Methods- Prospective 12-month observational study in 15 tertiary stroke centers in the United States, Europe, and Asia. Consecutive patients with premorbid modified Rankin Scale score of <2 with acute nontraumatic anticoagulant-related ICH divided into 2 groups according to the type of anticoagulant: NOAC versus VKA. We recorded baseline ICH volume, significant hematoma expansion (absolute [12.5 mL] or relative [>33%] increase), neurological severity measured by National Institutes of Health Stroke Scale score, 90-day mortality, and functional status (modified Rankin Scale score). Results- Our cohort comprised 196 patients, 62 NOAC related (mean age, 75.0±11.4 years; 54.8% men) and 134 VKA related (mean age, 72.3±10.5; 73.1% men). There were no differences in vascular comorbidities, antiplatelet, and statin use; NOAC-related ICH patients had lower median baseline hematoma volume (13.8 [2.5-37.6] versus 19.5 [6.6-52.0] mL; P=0.026) and were less likely to have severe neurological deficits (National Institutes of Health Stroke Scale score of >10 points) on admission (37% versus 55.3%, P=0.025). VKA-ICH were more likely to have significant hematoma expansion (37.4% versus 17%, P=0.008). NOAC pretreatment was independently associated with smaller baseline hematoma volume (standardized linear regression coefficient:-0.415 [95% CI, -0.780 to -0.051]) resulting in lower likelihood of severe neurological deficit (odds ratio, 0.44; 95% CI, 0.22-0.85) in multivariable-adjusted models. Conclusions- Patients with NOAC-related ICH have smaller baseline hematoma volumes and lower odds of severe neurological deficit compared with VKA-related ICH. These findings are important for practicing clinicians making anticoagulation choices.

Cancer-Associated Thrombosis: Pathophysiology, Laboratory Assessment, and Current Guidelines.

Dysregulated hemostasis in cancer patients is associated with various clinical conditions, from thromboembolic complications to disseminated intravascular coagulation. Despite the well-established association between cancer and thromboembolic complications, the mechanisms involved are not completely elucidated. There are several predisposing factors in cancer for increased thrombus generation, such as immobilization and chemotherapy. The term cancer-associated thrombosis (CAT) has been introduced to describe the close bidirectional relationship between cancer and thromboembolic events. Conventional coagulation tests (PT/aPTT) are more accurate in detecting a hypocoagulable rather than a hypercoagulable state; thus, their contribution to CAT management is limited. Traditionally, D-dimer levels have been the most common laboratory study for the evaluation of thrombotic risk. However, D-dimer levels only display a snapshot of the coagulation cascade, and they cannot provide a dynamic evaluation of evolving clot formation. Non-conventional assays, such as viscoelastic methods and microparticle formation are promising tools for the identification of patients at risk for developing CAT. Recent guidelines from the American Society of Clinical Oncology counsel against the estimation of thrombotic risk through a single test and recommend the use of scoring systems that take into account several risk factors. The present review outlines the current insights into the pathophysiological mechanisms of CAT and provides a comprehensive review of the latest advances in the laboratory assessment of CAT and the recent guidelines for the management of patients at risk for developing thromboembolic complications.

Extracorporeal Membrane Oxygenation (ECMO)-Associated Coagulopathy in Adults.

Extracorporeal membrane oxygenation (ECMO) is used for the management of severe respiratory and cardiac failure and as a bridge to achieve definite treatment or transplantation. ECMO-associated coagulopathy (EAC) is a frequent complication leading to high rates of thrombosis or severe haemorrhage, contributing to morbidity and mortality among patients. Understanding the pathophysiology of EAC is substantial for effectively managing patients on ECMO. We analyse the underlying mechanism of EAC and discuss the monitoring of the coagulation profile, combining the viscoelastic point-of-care assays with the conventional coagulation laboratory tests.

Nucleated Red Blood Cells: Could They Be Indicator Markers of Illness Severity for Neonatal Intensive Care Unit Patients?

BACKGROUND: We aimed to assess whether nucleated red blood cells (NRBCs) count could serve as a diagnostic and prognostic biomarker for morbidity and mortality in critically ill neonates. METHODS: The association between NRBCs count and neonatal morbidity and mortality was evaluated in an observational cohort of critically ill neonates hospitalized in our neonatal intensive care unit over a period of 69 months. The discriminative ability of NRBCs count as diagnostic and prognostic biomarkers was evaluated by performing the Receiver Operating Characteristics (ROC) curve analysis. RESULTS: Among 467 critically ill neonates included in the study, 45 (9.6%) of them experienced in-hospital mortality. No statistically significant difference was found with regards to NRBCs count between survivors and non-survivors, although the median value for NRBCs was sometimes higher for non-survivors. ROC curve analysis showed that NRBCs is a good discriminator marker for the diagnosis of perinatal hypoxia in neonates with area under the curve (AUC) [AUC 0.710; 95% confidence interval (CI), 0.660-0.759] and predominantly in preterm neonates (AUC 0.921 (95% CI, 0.0849-0.0993)) by using a cut-off value of ≥11.2%, with 80% sensitivity and 88.7% specificity. NRBCs also revealed significant prognostic power for mortality in septic neonates (AUC 0.760 (95% CI, 0.631-0.888)) and especially in preterms with sepsis (AUC 0.816 (95% CI, 0.681-0.951)), with cut-off value ≥ 1%, resulting in 81.6% sensitivity and 78.1% specificity. CONCLUSION: NRBCs count may be included among the early diagnostic and prognostic markers for sick neonates.

Coagulation Profiles of Pulmonary Arterial Hypertension Patients, Assessed by Non-Conventional Hemostatic Tests and Markers of Platelet Activation and Endothelial Dysfunction.

Many pathophysiologic processes of pulmonary arterial hypertension (PAH), namely, excess vasoconstriction, vascular remodeling and in situ thrombosis, involve the coagulation cascade, and more specifically, platelets. The aim of this study was to globally assess coagulation processes in PAH, by using non-conventional hemostatic tests, along with markers of platelet activation and endothelial dysfunction. We studied 44 new PAH patients (22 with idiopathic PAH and 22 with connective tissue disease) and 25 healthy controls. The following tests were performed: platelet function analyzer-100 (PFA-100), light transmission aggregometry (LTA), rotational thromboelastometry (ROTEM), endogenous thrombin potential (ETP), serotonin, thromboxane A2 and p-selectin plasma levels, and von Willebrand antigen (VWF:Ag) and activity (VWF:Ac). Our results showed that PAH patients had diminished platelet aggregation, presence of disaggregation, defective initiation of the clotting process and clot propagation, and diminished thrombin formation capacity. Serotonin, thromboxane A2 and p-selectin levels were increased, and VWF:Ag and VWF:Ac decreased in the same population. The results of this study suggest that the platelets of PAH patients are activated and present functional abnormalities. The procoagulant activity, in general, appears to be impaired probably due to a sustained and prolonged activation of the procoagulant processes. Larger observational studies are warranted to confirm these laboratory findings.

The prognostic utility of ICH-score in anticoagulant related intracerebral hemorrhage.

Although intracerebral hemorrhage (ICH) score is used to provide an estimate on the probability of mortality following spontaneous ICH of any cause, its utility has not been exclusively tested in ICH patients with history of treatment with vitamin K antagonists (VKAs) or non-vitamin K oral anticoagulants (NOACs). The aim of the present report is to investigate the utility of ICH score for mortality prognostication of VKA-ICH and NOAC-ICH patients. We used receiver operating characteristic curve analyses to estimate the accuracy parameters for the different values of ICH score in the prognosis of mortality within 30-days after the onset of NOAC-ICH or VKA-ICH. We analyzed data from 108 NOAC-ICH and 241 VKA-ICH patients (median age 76 years, 58% males, median NIHSS score 11 points, median ICH-score 2 points). ICH score of 4 points was uncovered to be the most favorable threshold for the prediction of 30-day mortality both after NOAC-ICH (sensitivity: 57.7%, specificity: 98.8%) or VKA-ICH (sensitivity: 42.1%, specificity: 92.6%). However, comparison of the areas under the curve (AUC) suggested a cumulatively higher (p = .001) predictive value of ICH-score in the prognostication of 30-day mortality after ICH related to the use of NOACs (AUC: 0.92, 95%CI: 0.86-0.98) compared to the ICH related to the use of VKAs (AUC: 0.77, 95%CI: 0.70-0.83). In conclusion, ICH score seems to have an adequate predictive utility in the prognostication of 30-day mortality following an ICH related to the use of oral anticoagulants, with better yield in ICH cases associated with the use of NOACs.

Optimization of risk stratification for anticoagulation-associated intracerebral hemorrhage: net risk estimation.

BACKGROUND: Every anticoagulation decision has in inherent risk of hemorrhage; intracerebral hemorrhage (ICH) is the most devastating hemorrhagic complication. We examined whether combining ischemic and hemorrhagic stroke risk in individual patients might provide a meaningful paradigm for risk stratification. METHODS: We enrolled consecutive patients with anticoagulation-associated ICH in 15 tertiary centers in the USA, Europe and Asia between 2015 and 2017. Each patient was assigned baseline ischemic stroke and hemorrhage risk based on their CHA2DS2-VASc and HAS-BLED scores. We computed a net risk by subtracting hemorrhagic from ischemic risk. If the sum was positive the patient was assigned a "Favorable" indication for anticoagulation; if negative, "Unfavorable". RESULTS: We enrolled 357 patients [59% men, median age 76 (68-82) years]. 31% used non-vitamin K antagonist (NOAC). 191 (53.5%) patients had a favorable indication for anticoagulation prior to their ICH; 166 (46.5%) unfavorable. Those with unfavorable indication were younger [72 (66-80) vs 78 (73-84) years, p = 0.001], with lower CHA2DS2-VASc score [3(3-4) vs 5(4-6), p < 0.001]. Those with favorable indication had a significantly higher prevalence of most cardiovascular risk factors and were more likely to use a NOAC (35% vs 25%, p = 0.045). Both groups had similar prevalence of hypertension and chronic kidney disease. CONCLUSIONS: In this anticoagulation-associated ICH cohort, baseline hemorrhagic risk exceeded ischemic risk in approximately 50%, highlighting the importance of careful consideration of risk/benefit ratio prior to anticoagulation decisions. The remaining 50% suffered an ICH despite excess baseline ischemic risk, stressing the need for biomarkers to allow more precise estimation of hemorrhagic complication risk.

Microbleed prevalence and burden in anticoagulant-associated intracerebral bleed.

Prior studies suggest an association between Vitamin K antagonists (VKA) and cerebral microbleeds (CMBs); less is known about nonvitamin K oral anticoagulants (NOACs). In this observational study we describe CMB profiles in a multicenter cohort of 89 anticoagulation-related intracerebral hemorrhage (ICH) patients. CMB prevalence was 51% (52% in VKA-ICH, 48% in NOAC-ICH). NOAC-ICH patients had lower median CMB count [2(IQR:1-3) vs. 7(4-11); P < 0.001]; ≥5 CMBs were less prevalent in NOAC-ICH (4% vs. 31%, P = 0.006). This inverse association between NOAC exposure and high CMB count persisted in multivariable logistic regression models adjusting for potential confounders (OR 0.10, 95%CI: 0.01-0.83; P = 0.034).

Direct oral anticoagulant- vs vitamin K antagonist-related nontraumatic intracerebral hemorrhage.

OBJECTIVE: To compare the neuroimaging profile and clinical outcomes among patients with intracerebral hemorrhage (ICH) related to use of vitamin K antagonists (VKAs) or direct oral anticoagulants (DOACs) for nonvalvular atrial fibrillation (NVAF). METHODS: We evaluated consecutive patients with NVAF with nontraumatic, anticoagulant-related ICH admitted at 13 tertiary stroke care centers over a 12-month period. We also performed a systematic review and meta-analysis of eligible observational studies reporting baseline characteristics and outcomes among patients with VKA- or DOAC-related ICH. RESULTS: We prospectively evaluated 161 patients with anticoagulation-related ICH (mean age 75.6 ± 9.8 years, 57.8% men, median admission NIH Stroke Scale [NIHSSadm] score 13 points, interquartile range 6-21). DOAC-related (n = 47) and VKA-related (n = 114) ICH did not differ in demographics, vascular risk factors, HAS-BLED and CHA2DS2-VASc scores, and antiplatelet pretreatment except for a higher prevalence of chronic kidney disease in VKA-related ICH. Patients with DOAC-related ICH had lower median NIHSSadm scores (8 [3-14] vs 15 [7-25] points, p = 0.003), median baseline hematoma volume (12.8 [4-40] vs 24.3 [11-58.8] cm3, p = 0.007), and median ICH score (1 [0-2] vs 2 [1-3] points, p = 0.049). Severe ICH (>2 points) was less prevalent in DOAC-related ICH (17.0% vs 36.8%, p = 0.013). In multivariable analyses, DOAC-related ICH was independently associated with lower baseline hematoma volume (p = 0.006), lower NIHSSadm scores (p = 0.022), and lower likelihood of severe ICH (odds ratio [OR] 0.34, 95% confidence interval [CI] 0.13-0.87, p = 0.025). In meta-analysis of eligible studies, DOAC-related ICH was associated with lower baseline hematoma volumes on admission CT (standardized mean difference = -0.57, 95% CI -1.02 to -0.12, p = 0.010) and lower in-hospital mortality rates (OR = 0.44, 95% CI 0.21-0.91, p = 0.030). CONCLUSIONS: DOAC-related ICH is associated with smaller baseline hematoma volume and lesser neurologic deficit at hospital admission compared to VKA-related ICH.

Red Blood Cell Transfusions in Greece: Results of a Survey of Red Blood Cell Use in 2013.

OBJECTIVE: Greece is ranked as the second highest consumer of blood components in Europe. For an effective transfusion system and in order to reduce variability of transfusion practice by implementing evidence-based transfusion guidelines it is necessary to study and monitor blood management strategies. Our study was conducted in order to evaluate the use of red blood cell units (RBC-U) in nationwide scale mapping parameters that contribute to their proper management in Greece. MATERIALS AND METHODS: The survey was conducted by the Working Committee of Transfusion Medicine&Apheresis of the Hellenic Society of Hematology from January to December 2013. The collected data included the number, ABO/D blood group, patients' department, and storage age of RBC-U transfused. RESULTS: The number of RBC-U evaluated was 103,702 (17.77%) out of 583,457 RBC-U transfused in Greece in 2013. RBC-U transfused by hospital department (mean percentage) was as follows: Surgery 29.34%, Internal Medicine 29.48%, Oncology/Hematology 14.65%, Thalassemia 8.87%, Intensive Care Unit 6.55%, Nephrology 1.78%, Obstetrics/Gynecology 1.46%, Neonatal&Pediatric 0.31%, Private Hospitals 8.57%. RBC-U distribution according to ABO/D blood group was: A: 39.02%, B: 12.41%, AB: 5.16%, O: 43.41%, D+: 87.99%, D-: 12.01%. The majority of RBC-U (62.46%) was transfused in the first 15 days of storage, 25.24% at 16 to 28 days, and 12.28% at 29-42 days. CONCLUSION: Despite a high intercenter variability in RBC transfusions, surgical and internal medicine patients were the most common groups of patients transfused with an increasing rate for internal medicine patients. The majority of RBC-U were transfused within the first 15 days of storage, which is possibly the consequence of blood supply insufficiency leading to the direct use of fresh blood. Benchmarking transfusion activity may help to decrease the inappropriate use of blood products, reduce the cost of care, and optimize the use of the voluntary donor's gift.