Algorithms for predicting COVID outcome using ready-to-use laboratorial and clinical data.

The pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is an emerging crisis affecting the public health system. The clinical features of COVID-19 can range from an asymptomatic state to acute respiratory syndrome and multiple organ dysfunction. Although some hematological and biochemical parameters are altered during moderate and severe COVID-19, there is still a lack of tools to combine these parameters to predict the clinical outcome of a patient with COVID-19. Thus, this study aimed at employing hematological and biochemical parameters of patients diagnosed with COVID-19 in order to build machine learning algorithms for predicting COVID mortality or survival. Patients included in the study had a diagnosis of SARS-CoV-2 infection confirmed by RT-PCR and biochemical and hematological measurements were performed in three different time points upon hospital admission. Among the parameters evaluated, the ones that stand out the most are the important features of the T1 time point (urea, lymphocytes, glucose, basophils and age), which could be possible biomarkers for the severity of COVID-19 patients. This study shows that urea is the parameter that best classifies patient severity and rises over time, making it a crucial analyte to be used in machine learning algorithms to predict patient outcome. In this study optimal and medically interpretable machine learning algorithms for outcome prediction are presented for each time point. It was found that urea is the most paramount variable for outcome prediction over all three time points. However, the order of importance of other variables changes for each time point, demonstrating the importance of a dynamic approach for an effective patient's outcome prediction. All in all, the use of machine learning algorithms can be a defining tool for laboratory monitoring and clinical outcome prediction, which may bring benefits to public health in future pandemics with newly emerging and reemerging SARS-CoV-2 variants of concern.

New, fast, and precise method of COVID-19 detection in nasopharyngeal and tracheal aspirate samples combining optical spectroscopy and machine learning.

Fast, precise, and low-cost diagnostic testing to identify persons infected with SARS-CoV-2 virus is pivotal to control the global pandemic of COVID-19 that began in late 2019. The gold standard method of diagnostic recommended is the RT-qPCR test. However, this method is not universally available, and is time-consuming and requires specialized personnel, as well as sophisticated laboratories. Currently, machine learning is a useful predictive tool for biomedical applications, being able to classify data from diverse nature. Relying on the artificial intelligence learning process, spectroscopic data from nasopharyngeal swab and tracheal aspirate samples can be used to leverage characteristic patterns and nuances in healthy and infected body fluids, which allows to identify infection regardless of symptoms or any other clinical or laboratorial tests. Hence, when new measurements are performed on samples of unknown status and the corresponding data is submitted to such an algorithm, it will be possible to predict whether the source individual is infected or not. This work presents a new methodology for rapid and precise label-free diagnosing of SARS-CoV-2 infection in clinical samples, which combines spectroscopic data acquisition and analysis via artificial intelligence algorithms. Our results show an accuracy of 85% for detection of SARS-CoV-2 in nasopharyngeal swab samples collected from asymptomatic patients or with mild symptoms, as well as an accuracy of 97% in tracheal aspirate samples collected from critically ill COVID-19 patients under mechanical ventilation. Moreover, the acquisition and processing of the information is fast, simple, and cheaper than traditional approaches, suggesting this methodology as a promising tool for biomedical diagnosis vis-à-vis the emerging and re-emerging viral SARS-CoV-2 variant threats in the future.

In silico and in vitro arboviral MHC class I-restricted-epitope signatures reveal immunodominance and poor overlapping patterns.

Introduction: The present work sought to identify MHC-I-restricted peptide signatures for arbovirus using in silico and in vitro peptide microarray tools. Methods: First, an in-silico analysis of immunogenic epitopes restricted to four of the most prevalent human MHC class-I was performed by identification of MHC affinity score. For that, more than 10,000 peptide sequences from 5 Arbovirus and 8 different viral serotypes, namely Zika (ZIKV), Dengue (DENV serotypes 1-4), Chikungunya (CHIKV), Mayaro (MAYV) and Oropouche (OROV) viruses, in addition to YFV were analyzed. Haplotype HLA-A*02.01 was the dominant human MHC for all arboviruses. Over one thousand HLA-A2 immunogenic peptides were employed to build a comprehensive identity matrix. Intending to assess HLAA*02:01 reactivity of peptides in vitro, a peptide microarray was designed and generated using a dimeric protein containing HLA-A*02:01. Results: The comprehensive identity matrix allowed the identification of only three overlapping peptides between two or more flavivirus sequences, suggesting poor overlapping of virus-specific immunogenic peptides amongst arborviruses. Global analysis of the fluorescence intensity for peptide-HLA-A*02:01 binding indicated a dose-dependent effect in the array. Considering all assessed arboviruses, the number of DENV-derived peptides with HLA-A*02:01 reactivity was the highest. Furthermore, a lower number of YFV-17DD overlapping peptides presented reactivity when compared to non-overlapping peptides. In addition, the assessment of HLA-A*02:01-reactive peptides across virus polyproteins highlighted non-structural proteins as "hot-spots". Data analysis supported these findings showing the presence of major hydrophobic sites in the final segment of non-structural protein 1 throughout 2a (Ns2a) and in nonstructural proteins 2b (Ns2b), 4a (Ns4a) and 4b (Ns4b). Discussion: To our knowledge, these results provide the most comprehensive and detailed snapshot of the immunodominant peptide signature for arbovirus with MHC-class I restriction, which may bring insight into the design of future virus-specific vaccines to arboviruses and for vaccination protocols in highly endemic areas.

Timeline Kinetics of Systemic and Airway Immune Mediator Storm for Comprehensive Analysis of Disease Outcome in Critically Ill COVID-19 Patients.

In the present study, the levels of serum and airway soluble chemokines, pro-inflammatory/regulatory cytokines, and growth factors were quantified in critically ill COVID-19 patients (total n=286) at distinct time points (D0, D2-6, D7, D8-13 and D>14-36) upon Intensive Care Unit (ICU) admission. Augmented levels of soluble mediators were observed in serum from COVID-19 patients who progress to death. An opposite profile was observed in tracheal aspirate samples, indicating that systemic and airway microenvironment diverge in their inflammatory milieu. While a bimodal distribution was observed in the serum samples, a unimodal peak around D7 was found for most soluble mediators in tracheal aspirate samples. Systems biology tools further demonstrated that COVID-19 display distinct eccentric soluble mediator networks as compared to controls, with opposite profiles in serum and tracheal aspirates. Regardless the systemic-compartmentalized microenvironment, networks from patients progressing to death were linked to a pro-inflammatory/growth factor-rich, highly integrated center. Conversely, patients evolving to discharge exhibited networks of weak central architecture, with lower number of neighborhood connections and clusters of pro-inflammatory and regulatory cytokines. All in all, this investigation with robust sample size landed a comprehensive snapshot of the systemic and local divergencies composed of distinct immune responses driven by SARS-CoV-2 early on severe COVID-19.