• We are excited to announce that our first Patient-Level Prediction paper has been sent to MedRxiv and is being submitted for peer review. This paper “Seek COVER: Development and validation of a personalized risk calculator for COVID-19 outcomes in an international network” is designed to inform individual behavioral choices and help design shielding strategies during de-confinement.
Led by co-first authors @RossW and @aniekmarkus, the team designed a nine-predictor COVID-19 Estimated Risk (COVER) model that was validated using more than 43,000 COVID patients (following initial development and validation using more than 6.8 million patients with influenza or flu-like symptoms). This model predicts hospitalization, intensive services, and death, and can help provide reassurance for low-risk patients, while shielding high-risk patients, as many start to enter the de-confinement stage of the pandemic.
@Rijnbeek is the corresponding author, and both he and @jennareps are co-last authors. Overall there are 43 authors involved in the study, once again highlighting the global collaborative nature of the OHDSI community. Congratulations to all who were involved in this work.
• The characterization team plans to post a revised manuscript on MedRxiv with updated data (the original is available here) from its original characterization study on patients hospitalized with COVID-19. The original characterization study was run on four databases, while the most current version has data from eight sources, including a SIDIAP database that includes just under 17,000 COVID patients. This study is the first to systematically summarize medical history in COVID patient populations in the U.S., Europe, and Asia at once.