ABSTRACT
INTRODUCTION: The recent Sars-Cov-2 pandemic (COVID-19) has led to growing research to explain the poor clinical prognosis in some patients. EVIDENCE ACQUISITION: While early observational studies highlighted the role of the virus in lung failure, in a second moment thrombosis emerged as a possible explanation of the worse clinical course in some patients. Despite initial difficulties in management of such patients, the constant increase of literature in the field is to date clarifying some questions from clinicians. However, several other questions need answer. EVIDENCE SYNTHESIS: A novel disease (Covid-19) due to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection was responsible for thousands of hospitalizations for severe acute respiratory syndrome, with several cases of thrombotic complications due to excessive inflammation, platelet activation, endothelial dysfunction, and stasis. Covid-19 and hospitalizations for Covid-19 may carry several potential risk factors for thrombosis. Severe coagulation abnormalities may occur in almost all of the severe and critical ill COVID-19 cases. CONCLUSIONS: Despite a strong pathophysiological rationale, the evidences in literature are not enough to recommend an aggressive antithrombotic therapy in COVID- 19. However, it is our opinion that an early use, even at home at the beginning of the disease, could improve the clinical course.
ABSTRACT
BACKGROUND: During the SARS-CoV-2 pandemic, several biomarkers were shown to be helpful in determining the prognosis of COVID-19 patients. The aim of our study was to evaluate the prognostic value of N-terminal pro-Brain Natriuretic Peptide (NT-pro-BNP) in a cohort of patients with COVID-19. METHODS: One-hundred and seven patients admitted to the Covid Hospital of Messina University between June 2022 and January 2023 were enrolled in our study. The demographic, clinical, biochemical, instrumental, and therapeutic parameters were recorded. The primary outcome was in-hospital mortality. A comparison between patients who recovered and were discharged and those who died during the hospitalization was performed. The independent parameters associated with in-hospital death were assessed by multivariable analysis and a stepwise regression logistic model. RESULTS: A total of 27 events with an in-hospital mortality rate of 25.2% occurred during our study. Those who died during hospitalization were older, with lower GCS and PaO2/FiO2 ratio, elevated D-dimer values, INR, creatinine values and shorter PT (prothrombin time). They had an increased frequency of diagnosis of heart failure (p < 0.0001) and higher NT-pro-BNP values. A multivariate logistic regression analysis showed that higher NT-pro-BNP values and lower PT and PaO2/FiO2 at admission were independent predictors of mortality during hospitalization. CONCLUSIONS: This study shows that NT-pro-BNP levels, PT, and PaO2/FiO2 ratio are independently associated with in-hospital mortality in subjects with COVID-19 pneumonia. Further longitudinal studies are warranted to confirm the results of this study.
ABSTRACT
To realize a machine learning (ML) model to estimate the dose of low molecular weight heparin to be administered, preventing thromboembolism events in COVID-19 patients with active cancer. Methods: We used a dataset comprising 131 patients with active cancer and COVID-19. We considered five ML models: logistic regression, decision tree, random forest, support vector machine and Gaussian naive Bayes. We decided to implement the logistic regression model for our study. A model with 19 variables was analyzed. Data were randomly split into training (70%) and testing (30%) sets. Model performance was assessed by confusion matrix metrics on the testing data for each model as positive predictive value, sensitivity and F1-score. Results: We showed that the five selected models outperformed classical statistical methods of predictive validity and logistic regression was the most effective, being able to classify with an accuracy of 81%. The most relevant result was finding a patient-proof where python function was able to obtain the exact dose of low weight molecular heparin to be administered and thereby to prevent the occurrence of VTE. Conclusions: The world of machine learning and artificial intelligence is constantly developing. The identification of a specific LMWH dose for preventing VTE in very high-risk populations, such as the COVID-19 and active cancer population, might improve with the use of new training ML-based algorithms. Larger studies are needed to confirm our exploratory results.
ABSTRACT
The recent Sars-Cov-2 pandemic (COVID-19) has led to growing research on the relationship between thromboembolism and Sars-Cov-2 infection. Nowadays, endothelial dysfunction, platelet activation, coagulation, and inflammatory host immune response are the subject of extensive researches in patients with COVID-19 disease. However, studies on the link between microorganisms or infections and thrombotic or thromboembolic events met fluctuating interest in the past. We, therefore, aimed to briefly summarize previous evidence on this topic, highlighting common points between previous data and what experienced today with SARS-COV2 infections.