Explanatory predictive model for COVID-19 severity risk employing machine learning, shapley addition, and LIME.

The rapid spread of SARS-CoV-2 threatens global public health and impedes the operation of healthcare systems. Several studies have been conducted to confirm SARS-CoV-2 infection and examine its risk factors. To produce more effective treatment options and vaccines, it is still necessary to investigate biomarkers and immune responses in order to gain a deeper understanding of disease pathophysiology. This study aims to determine how cytokines influence the severity of SARS-CoV-2 infection. We measured the plasma levels of 48 cytokines in the blood of 87 participants in the COVID-19 study. Several Classifiers were trained and evaluated using Machine Learning and Deep Learning to complete missing data, generate synthetic data, and fill in any gaps. To examine the relationship between cytokine storm and COVID-19 severity in patients, the Shapley additive explanation (SHAP) and the LIME (Local Interpretable Model-agnostic Explanations) model were applied. Individuals with severe SARS-CoV-2 infection had elevated plasma levels of VEGF-A, MIP-1b, and IL-17. RANTES and TNF were associated with healthy individuals, whereas IL-27, IL-9, IL-12p40, and MCP-3 were associated with non-Severity. These findings suggest that these cytokines may promote the development of novel preventive and therapeutic pathways for disease management. In this study, the use of artificial intelligence is intended to support clinical diagnoses of patients to determine how each cytokine may be responsible for the severity of COVID-19, which could lead to the identification of several cytokines that could aid in treatment decision-making and vaccine development.

Type I and III interferons are good markers to monitor COVID-19 pathophysiology.

The COVID-19 pandemic has caused millions of deaths and has resulted in disastrous societal and economic impacts worldwide. During SARS-CoV-2 infection, abnormal levels of pro-inflammatory cytokines have been observed and were associated to the severity of the disease. Type I (-α/ß) and Type III (IFN-λ) interferons are family members of cytokines that play an important role in fighting viral replication during the early phases of infection. The location and timing of the IFNs production have been shown to be decisive for the COVID-19 outcome. Despite the effectiveness of COVID-19 vaccines and with the emergence of new SARS-CoV-2 variants, a better understanding of the involvement of IFNs as players in antiviral immunity in the COVID-19 pathophysiology is necessary to implement additional potent prophylactic and/or therapeutic approaches. In this study, we investigated the role of type I and III IFN in COVID-19 pathophysiology. We first analyzed the IFN-α, IFN-ß and IFN- λ mRNA expression in nasopharyngeal swabs and blood samples from Moroccan patients infected with SARS-CoV-2 and secondly correlated these IFNs expressions with COVID-19 clinical and biological parameters. Our results showed that in the upper airways of patients with mild, non-severe, or severe COVID-19 manifestations, the IFN- α, - ß and - λ are expressed in the same manner as in controls. However, in blood samples their expression was downregulated in all groups. Univariate linear models with interferons as predictors to evaluate clinical-biological parameters highlighted that the main clinical-biological relations were found when testing: FiO2, Lymphocyte values and virus load. Furthermore, the multivariate models confirmed that quantifications of interferons during COVID-19 are good biological markers for tracking COVID-19 pathophysiology.

The ongoing enigma of SARS-CoV-2 and platelet interaction.

Since the onset of the global pandemic of coronavirus disease 2019 (COVID-19), there is an urgent need to understand the pathogenesis of the common inflammatory and thrombotic complications associated with this illness leading to multiorgan failure and mortality. It is well established that platelets are hyperactivated during COVID-19. Data from independent studies reported an angiotensin-converting enzyme (ACE2)-dependent severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) platelet interaction, raising the concern whether ACE2 receptor is the "key receptor" in this process, while other platelet research groups demonstrated that thrombotic events occur via ACE2-independent mechanisms, where the virus probably uses alternative pathways. In this study, we discuss the conflicting results and highlight the ongoing controversy related to SARS-CoV-2-platelet interaction.

Platelet activation by SARS-CoV-2 implicates the release of active tissue factor by infected cells.

Platelets are hyperactivated in coronavirus disease 2019 (COVID-19). However, the mechanisms promoting platelet activation by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) are not well understood. This may be due to inherent challenges in discriminating the contribution of viral vs host components produced by infected cells. This is particularly true for enveloped viruses and extracellular vesicles (EVs), as they are concomitantly released during infection and share biophysical properties. To study this, we evaluated whether SARS-CoV-2 itself or components derived from SARS-CoV-2-infected human lung epithelial cells could activate isolated platelets from healthy donors. Activation was measured by the surface expression of P-selectin and the activated conformation of integrin αIIbß3, degranulation, aggregation under flow conditions, and the release of EVs. We find that neither SARS-CoV-2 nor purified spike activates platelets. In contrast, tissue factor (TF) produced by infected cells was highly potent at activating platelets. This required trace amounts of plasma containing the coagulation factors FX, FII, and FVII. Robust platelet activation involved thrombin and the activation of protease-activated receptor (PAR)-1 and -4 expressed by platelets. Virions and EVs were identified by electron microscopy. Through size-exclusion chromatography, TF activity was found to be associated with a virus or EVs, which were indistinguishable. Increased TF messenger RNA (mRNA) expression and activity were also found in lungs in a murine model of COVID-19 and plasma of severe COVID-19 patients, respectively. In summary, TF activity from SARS-CoV-2-infected cells activates thrombin, which signals to PARs on platelets. Blockade of molecules in this pathway may interfere with platelet activation and the coagulation characteristic of COVID-19.

Machine learning approaches in Covid-19 severity risk prediction in Morocco.

The purpose of this study is to develop and test machine learning-based models for COVID-19 severity prediction. COVID-19 test samples from 337 COVID-19 positive patients at Cheikh Zaid Hospital were grouped according to the severity of their illness. Ours is the first study to estimate illness severity by combining biological and non-biological data from patients with COVID-19. Moreover the use of ML for therapeutic purposes in Morocco is currently restricted, and ours is the first study to investigate the severity of COVID-19. When data analysis approaches were used to uncover patterns and essential characteristics in the data, C-reactive protein, platelets, and D-dimers were determined to be the most associated to COVID-19 severity prediction. In this research, many data reduction algorithms were used, and Machine Learning models were trained to predict the severity of sickness using patient data. A new feature engineering method based on topological data analysis called Uniform Manifold Approximation and Projection (UMAP) shown that it achieves better results. It has 100% accuracy, specificity, sensitivity, and ROC curve in conducting a prognostic prediction using different machine learning classifiers such as X_GBoost, AdaBoost, Random Forest, and ExtraTrees. The proposed approach aims to assist hospitals and medical facilities in determining who should be seen first and who has a higher priority for admission to the hospital.

Chemokines and eicosanoids fuel the hyperinflammation within the lungs of patients with severe COVID-19.

BACKGROUND: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection can lead to a variety of clinical outcomes, ranging from the absence of symptoms to severe acute respiratory disease and ultimately death. A feature of patients with severe coronavirus disease 2019 (COVID-19) is the abundance of inflammatory cytokines in the blood. Elevated levels of cytokines are predictive of infection severity and clinical outcome. In contrast, studies aimed at defining the driving forces behind the inflammation in lungs of subjects with severe COVID-19 remain scarce. OBJECTIVE: Our aim was to analyze and compare the plasma and bronchoalveolar lavage (BAL) fluids of patients with severe COVID-19 (n = 45) for the presence of cytokines and lipid mediators of inflammation (LMIs). METHODS: Cytokines were measured by using Luminex multiplex assay, and LMIs were measured by using liquid chromatography-tandem mass spectrometry. RESULTS: We revealed high concentrations of numerous cytokines, chemokines, and LMIs in the BAL fluid of patients with severe COVID-19. Of the 13 most abundant mediators in BAL fluid, 11 were chemokines, with CXCL1 and CXCL8 being 200 times more abundant than IL-6 and TNF-α. Eicosanoid levels were also elevated in the lungs of subjects with severe COVID-19. Consistent with the presence chemotactic molecules, BAL fluid samples were enriched for neutrophils, lymphocytes, and eosinophils. Inflammatory cytokines and LMIs in plasma showed limited correlations with those present in BAL fluid, arguing that circulating inflammatory molecules may not be a reliable proxy of the inflammation occurring in the lungs of patients with severe COVID-19. CONCLUSIONS: Our findings indicate that hyperinflammation of the lungs of patients with severe COVID-19 is fueled by excessive production of chemokines and eicosanoids. Therapeutic strategies to dampen inflammation in patients with COVID-19 should be tailored accordingly.

High levels of eicosanoids and docosanoids in the lungs of intubated COVID-19 patients.

Severe acute respiratory syndrome coronavirus 2 is responsible for coronavirus disease 2019 (COVID-19). While COVID-19 is often benign, a subset of patients develops severe multilobar pneumonia that can progress to an acute respiratory distress syndrome. There is no cure for severe COVID-19 and few treatments significantly improved clinical outcome. Dexamethasone and possibly aspirin, which directly/indirectly target the biosynthesis/effects of numerous lipid mediators are among those options. Our objective was to define if severe COVID-19 patients were characterized by increased bioactive lipids modulating lung inflammation. A targeted lipidomic analysis of bronchoalveolar lavages (BALs) by tandem mass spectrometry was done on 25 healthy controls and 33 COVID-19 patients requiring mechanical ventilation. BALs from severe COVID-19 patients were characterized by increased fatty acids and inflammatory lipid mediators. There was a predominance of thromboxane and prostaglandins. Leukotrienes were also increased, notably LTB4 , LTE4 , and eoxin E4 . Monohydroxylated 15-lipoxygenase metabolites derived from linoleate, arachidonate, eicosapentaenoate, and docosahexaenoate were also increased. Finally yet importantly, specialized pro-resolving mediators, notably lipoxin A4 and the D-series resolvins, were also increased, underscoring that the lipid mediator storm occurring in severe COVID-19 involves pro- and anti-inflammatory lipids. Our data unmask the lipid mediator storm occurring in the lungs of patients afflicted with severe COVID-19. We discuss which clinically available drugs could be helpful at modulating the lipidome we observed in the hope of minimizing the deleterious effects of pro-inflammatory lipids and enhancing the effects of anti-inflammatory and/or pro-resolving lipid mediators.

Platelet Function in Viral Immunity and SARS-CoV-2 Infection.

Platelets, as nonnucleated blood components, are classically recognized for their pivotal role in hemostasis. In recent years, however, accumulating evidence points to a nonhemostatic role for platelets, as active participants in the inflammatory and immune responses to microbial organisms in infectious diseases. This stems from the ability of activated platelets to secrete a plethora of immunomodulatory cytokines and chemokines, as well as directly interplaying with viral receptors. While much attention has been given to the role of the cytokine storm in the severity of the coronavirus disease 2019 (COVID-19), less is known about the contribution of platelets to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. Here, we give a brief overview on the platelet contribution to antiviral immunity and response during SARS-CoV-2 infection.

Platelets Can Associate with SARS-Cov-2 RNA and Are Hyperactivated in COVID-19.

Rationale: In addition to the overwhelming lung inflammation that prevails in COVID-19, hypercoagulation and thrombosis contribute to the lethality of subjects infected with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Platelets are chiefly implicated in thrombosis. Moreover, they can interact with viruses and are an important source of inflammatory mediators. While a lower platelet count is associated with severity and mortality, little is known about platelet function during COVID-19. Objective: To evaluate the contribution of platelets to inflammation and thrombosis in COVID-19 patients. Methods and Results: Blood was collected from 115 consecutive COVID-19 patients presenting non-severe (n=71) and severe (n=44) respiratory symptoms. We document the presence of SARS-CoV-2 RNA associated with platelets of COVID-19 patients. Exhaustive assessment of cytokines in plasma and in platelets revealed the modulation of platelet-associated cytokine levels in both non-severe and severe COVID-19 patients, pointing to a direct contribution of platelets to the plasmatic cytokine load. Moreover, we demonstrate that platelets release their alpha- and dense-granule contents in both non-severe and severe forms of COVID-19. In comparison to concentrations measured in healthy volunteers, phosphatidylserine-exposing platelet extracellular vesicles were increased in non-severe, but not in severe cases of COVID-19. Levels of D-dimers, a marker of thrombosis, failed to correlate with any measured indicators of platelet activation. Functionally, platelets were hyperactivated in COVID-19 subjects presenting non-severe and severe symptoms, with aggregation occurring at suboptimal thrombin concentrations. Furthermore, platelets adhered more efficiently onto collagen-coated surfaces under flow conditions. Conclusions: Taken together, the data suggest that platelets are at the frontline of COVID-19 pathogenesis, as they release various sets of molecules through the different stages of the disease. Platelets may thus have the potential to contribute to the overwhelming thrombo-inflammation in COVID-19, and the inhibition of pathways related to platelet activation may improve the outcomes during COVID-19.