Internal and emergency medicine
-
Multicenter Study
Machine learning versus traditional methods for the development of risk stratification scores: a case study using original Canadian Syncope Risk Score data.
Artificial Intelligence and machine learning (ML) methods are promising for risk-stratification, but the added benefit over traditional statistical methods remains unclear. We compared predictive models developed using machine learning (ML) methods to the Canadian Syncope Risk Score (CSRS), a risk-tool developed with logistic regression for predicting serious adverse events (SAE) after emergency department (ED) disposition for syncope. We used the prospective multicenter cohort data collected for CSRS development at 11 Canadian EDs over an 8-year period to develop four ML models to predict 30-day SAE (death, arrhythmias, MI, structural heart disease, pulmonary embolism, hemorrhage) after ED disposition. ⋯ The AUCs and calibration slopes for the ML models and CSRS were similar. Two ML models used fewer predictors than the CSRS but matched its performance. Overall, the ML models matched the CSRS in performance, with some models using fewer predictors.
-
Multicenter Study Observational Study
Low in-hospital mortality rate in patients with COVID-19 receiving thromboprophylaxis: data from the multicentre observational START-COVID Register.
COVID-19 infection causes respiratory pathology with severe interstitial pneumonia and extra-pulmonary complications; in particular, it may predispose to thromboembolic disease. The current guidelines recommend the use of thromboprophylaxis in patients with COVID-19, however, the optimal heparin dosage treatment is not well-established. We conducted a multicentre, Italian, retrospective, observational study on COVID-19 patients admitted to ordinary wards, to describe clinical characteristic of patients at admission, bleeding and thrombotic events occurring during hospital stay. The strategies used for thromboprophylaxis and its role on patient outcome were, also, described. 1091 patients hospitalized were included in the START-COVID-19 Register. ⋯ All patients were treated with antithrombotic drugs; 5.4%, had venous thromboembolism [30.5% deep vein thrombosis (DVT), 66.1% pulmonary embolism (PE), and 3.4% patients had DVT + PE]. In our cohort the mortality rate was 18.3%. Heparin use was independently associated with survival in patients aged ≥ 59 years at multivariable analysis. We confirmed the high mortality rate of COVID-19 in hospitalized patients in ordinary wards. Treatment with antithrombotic drugs is significantly associated with a reduction of mortality rates especially in patients older than 59 years.