Abstract
Background: Detecting and isolating cases of COVID-19 are amongst the key elements listed by the WHO to reduce transmission. This approach has been reported to reduce those symptomatic with COVID-19 in the population by over 90%. Testing is part of a strategy that will save lives. Testing everyone maybe ideal, but it is not practical. A risk tool based on patient demographics and clinical parameters has the potential to help identify patients most likely to test negative for SARS-CoV-2. If effective it could be used to aide clinical decision making and reduce the testing burden. Methods: At the time of this analysis, a total of 9,516 patients with symptoms suggestive of Covid-19, were assessed and tested at Mount Sinai Institutions in New York. Patient demographics, clinical parameters and test results were collected. A robust prediction pipeline was used to develop a risk tool to predict the likelihood of a positive test for Covid-19. The risk tool was analyzed in a holdout dataset from the cohort and its discriminative ability, calibration and net benefit assessed. Results: Over 48% of those tested in this cohort, had a positive result. The derived model had an AUC of 0.77, provided reliable risk prediction, and demonstrated a superior net benefit than a strategy of testing everybody. When a risk cut-off of 70% was applied, the model had a negative predictive value of 96%. Conclusion: Such a tool could be used to help aide but not replace clinical decision making and conserve vital resources needed to effectively tackle this pandemic.