What’s my personal risk for a bad COVID outcome should I become infected?

Clinical Symptoms Infection and Spread Staying Safe

A: A variety of “risk calculators” have been developed to help you answer this very question (Links below). BIG CAVEAT: There are huge margins of error on the results, often making the risk scores MORE PRECISE THAN ACCURATE.


As much of the country continues to move through re-opening phases, we as individuals are having to make our own, individualized risk/benefit calculations about how best to navigate the new normal. It’s such a tough puzzle – we all have incredibly unique circumstances, constraints, and supports under which we’re operating. Putting together the pieces of this puzzle often leads to the question “what’s my personal risk for a bad outcome should I contract COVID?” Indeed, the Nerdy Girls have been fielding many related questions.

Both clinical medicine and health care policy rely on statistically sophisticated prediction models to estimate an individual’s risk for an outcome of interest (good or bad). Much of the buzz around machine learning (ML) and artificial intelligence (AI) in medicine relates to their potential to improve the accuracy of person-specific “clinical risk scores.” [Editorial note: This particular Nerdy Girl spent a chapter of her career developing, testing, and translating such models for policy-makers.]

Many new COVID-specific risk calculators have popped up to meet individuals’ needs in making risk/benefit calculations during the pandemic. (Links are at the bottom of this post.) It’s so, so important note that these are built on new data that haven’t been widely validated, and that these tools perform best at the POPULATION level, as opposed to the INDIVIDUAL level. For example, we know that on average 100,000 people with preexisting heart conditions are more likely to have a poor COVID prognosis than 100,000 people with no conditions. But for any given person within either of those groups there’s a large margin of error with respect to the individual outcomes.

If, on balance, you feel like having incomplete information is better than no information about determining your individual risk (this Nerdy Girl’s personal take!), then by all means check out the calculators. And note that it’s best to triangulate estimates from a variety of tools as opposed to having complete faith in one individual tool, an “ensemble approach” in science-speak. Finally, look for calculators with LARGE underlying data sets that GENERALIZE WELL TO YOUR CONTEXT.

Links to risk calculators (see table 1).

Link to original FB post