Drivers of Mortality in COVID ARDS Depend on Patient Sub-Type

The most common cause of death in people with COVID19 is acute respiratory distress syndrome (ARDS). To assess the impact of COVID ARDS on specific patient subgroups, our team applied an iterative clustering and machine learning framework to EMR data from thousands of hospitalized patients with the goal of defining subgroups, or phenoclusters. Our team then applied a supervised model to identify risk factors for mortality for each phenocluster, and compared these between phenoclusters and the entire cohort.

You can read more about this research and our findings, now available in pre-print on medRxiv. View the full study here.