Correlating drug prescriptions with prognosis in severe COVID-19: first step towards resource management.

BACKGROUND: Optimal COVID-19 management is still undefined. In this complicated scenario, the construction of a computational model capable of extracting information from electronic medical records, correlating signs, symptoms and medical prescriptions, could improve patient management/prognosis. METHODS: The aim of this study is to investigate the correlation between drug prescriptions and outcome in patients with COVID-19. We extracted data from 3674 medical records of hospitalized patients: drug prescriptions, outcome, and demographics. The outcome evaluated was hospital outcome. We applied correlation analysis using a Logistic Regression algorithm for machine learning with Lasso and Matthews correlation coefficient. RESULTS: We found correlations between drugs and patient outcomes (death/discharged alive). Anticoagulants, used very frequently during all phases of the disease, were associated with good prognosis only after the first week of symptoms. Antibiotics very frequently prescribed, especially early, were not correlated with outcome, suggesting that bacterial infections may not be important in determining prognosis. There were no differences between age groups. CONCLUSIONS: In conclusion, we achieved an important result in the area of Artificial Intelligence, as we were able to establish a correlation between concrete variables in a real and extremely complex environment of clinical data from COVID-19. Our results are an initial and promising contribution in decision-making and real-time environments to support resource management and forecasting prognosis of patients with COVID-19.

HDL proteome remodeling associates with COVID-19 severity.

BACKGROUND: Besides the well-accepted role in lipid metabolism, high-density lipoprotein (HDL) also seems to participate in host immune response against infectious diseases. OBJECTIVE: We used a quantitative proteomic approach to test the hypothesis that alterations in HDL proteome associate with severity of Coronavirus disease 2019 (COVID-19). METHODS: Based on clinical criteria, subjects (n=41) diagnosed with COVID-19 were divided into two groups: a group of subjects presenting mild symptoms and a second group displaying severe symptoms and requiring hospitalization. Using a proteomic approach, we quantified the levels of 29 proteins in HDL particles derived from these subjects. RESULTS: We showed that the levels of serum amyloid A 1 and 2 (SAA1 and SAA2, respectively), pulmonary surfactant-associated protein B (SFTPB), apolipoprotein F (APOF), and inter-alpha-trypsin inhibitor heavy chain H4 (ITIH4) were increased by more than 50% in hospitalized patients, independently of sex, HDL-C or triglycerides when comparing with subjects presenting only mild symptoms. Altered HDL proteins were able to classify COVID-19 subjects according to the severity of the disease (error rate 4.9%). Moreover, apolipoprotein M (APOM) in HDL was inversely associated with odds of death due to COVID-19 complications (odds ratio [OR] per 1-SD increase in APOM was 0.27, with 95% confidence interval [CI] of 0.07 to 0.72, P=0.007). CONCLUSION: Our results point to a profound inflammatory remodeling of HDL proteome tracking with severity of COVID-19 infection. They also raise the possibility that HDL particles could play an important role in infectious diseases.

Prognostic accuracy of MALDI-TOF mass spectrometric analysis of plasma in COVID-19.

SARS-CoV-2 infection poses a global health crisis. In parallel with the ongoing world effort to identify therapeutic solutions, there is a critical need for improvement in the prognosis of COVID-19. Here, we report plasma proteome fingerprinting that predict high (hospitalized) and low-risk (outpatients) cases of COVID-19 identified by a platform that combines machine learning with matrix-assisted laser desorption ionization mass spectrometry analysis. Sample preparation, MS, and data analysis parameters were optimized to achieve an overall accuracy of 92%, sensitivity of 93%, and specificity of 92% in dataset without feature selection. We identified two distinct regions in the MALDI-TOF profile belonging to the same proteoforms. A combination of SDS-PAGE and quantitative bottom-up proteomic analysis allowed the identification of intact and truncated forms of serum amyloid A-1 and A-2 proteins, both already described as biomarkers for viral infections in the acute phase. Unbiased discrimination of high- and low-risk COVID-19 patients using a technology that is currently in clinical use may have a prompt application in the noninvasive prognosis of COVID-19. Further validation will consolidate its clinical utility.

Covid-19 Automated Diagnosis and Risk Assessment through Metabolomics and Machine Learning.

COVID-19 is still placing a heavy health and financial burden worldwide. Impairment in patient screening and risk management plays a fundamental role on how governments and authorities are directing resources, planning reopening, as well as sanitary countermeasures, especially in regions where poverty is a major component in the equation. An efficient diagnostic method must be highly accurate, while having a cost-effective profile. We combined a machine learning-based algorithm with mass spectrometry to create an expeditious platform that discriminate COVID-19 in plasma samples within minutes, while also providing tools for risk assessment, to assist healthcare professionals in patient management and decision-making. A cross-sectional study enrolled 815 patients (442 COVID-19, 350 controls and 23 COVID-19 suspicious) from three Brazilian epicenters from April to July 2020. We were able to elect and identify 19 molecules related to the disease's pathophysiology and several discriminating features to patient's health-related outcomes. The method applied for COVID-19 diagnosis showed specificity >96% and sensitivity >83%, and specificity >80% and sensitivity >85% during risk assessment, both from blinded data. Our method introduced a new approach for COVID-19 screening, providing the indirect detection of infection through metabolites and contextualizing the findings with the disease's pathophysiology. The pairwise analysis of biomarkers brought robustness to the model developed using machine learning algorithms, transforming this screening approach in a tool with great potential for real-world application.