Pre- and in-hospital anticoagulation therapy in coronavirus disease 2019 patients: a propensity-matched analysis of in-hospital outcomes.

AIMS: To estimate if chronic anticoagulant (CAC) treatment is associated with morbidity and mortality outcomes of patients hospitalized for SARS-CoV-2 infection. METHODS: In this European multicentric cohort study, we included 1186 patients of whom 144 were on CAC (12.1%) with positive coronavirus disease 2019 testing between 1 February and 30 July 2020. The average treatment effect (ATE) analysis with a propensity score-matching (PSM) algorithm was used to estimate the impact of CAC on the primary outcomes defined as in-hospital death, major and minor bleeding events, cardiovascular complications (CCI), and acute kidney injury (AKI). We also investigated if different dosages of in-hospital heparin were associated with in-hospital survival. RESULTS: In unadjusted populations, primary outcomes were significantly higher among CAC patients compared with non-CAC patients: all-cause death (35% vs. 18% P < 0.001), major and minor bleeding (14% vs. 8% P = 0.026; 25% vs. 17% P = 0.014), CCI (27% vs. 14% P < 0.001), and AKI (42% vs. 19% P < 0.001). In ATE analysis with PSM, there was no significant association between CAC and primary outcomes except for an increased incidence of AKI (ATE +10.2%, 95% confidence interval 0.3-20.1%, P = 0.044). Conversely, in-hospital heparin, regardless of dose, was associated with a significantly higher survival compared with no anticoagulation. CONCLUSIONS: The use of CAC was not associated with the primary outcomes except for the increase in AKI. However, in the adjusted survival analysis, any dose of in-hospital anticoagulation was associated with significantly higher survival compared with no anticoagulation.

Development of machine learning models to predict RT-PCR results for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in patients with influenza-like symptoms using only basic clinical data.

BACKGROUND: Reverse Transcription-Polymerase Chain Reaction (RT-PCR) for Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-COV-2) diagnosis currently requires quite a long time span. A quicker and more efficient diagnostic tool in emergency departments could improve management during this global crisis. Our main goal was assessing the accuracy of artificial intelligence in predicting the results of RT-PCR for SARS-COV-2, using basic information at hand in all emergency departments. METHODS: This is a retrospective study carried out between February 22, 2020 and March 16, 2020 in one of the main hospitals in Milan, Italy. We screened for eligibility all patients admitted with influenza-like symptoms tested for SARS-COV-2. Patients under 12 years old and patients in whom the leukocyte formula was not performed in the ED were excluded. Input data through artificial intelligence were made up of a combination of clinical, radiological and routine laboratory data upon hospital admission. Different Machine Learning algorithms available on WEKA data mining software and on Semeion Research Centre depository were trained using both the Training and Testing and the K-fold cross-validation protocol. RESULTS: Among 199 patients subject to study (median [interquartile range] age 65 [46-78] years; 127 [63.8%] men), 124 [62.3%] resulted positive to SARS-COV-2. The best Machine Learning System reached an accuracy of 91.4% with 94.1% sensitivity and 88.7% specificity. CONCLUSION: Our study suggests that properly trained artificial intelligence algorithms may be able to predict correct results in RT-PCR for SARS-COV-2, using basic clinical data. If confirmed, on a larger-scale study, this approach could have important clinical and organizational implications.