Curated genomics data to advance discovery and treatment

So this is the big question, right? Because you start with a very large cohort at Optum, we have 109 million people with clinical data, and that's growing. But when you start to ask very specific questions, that number can become very small very quickly. And so one of our challenges is figuring out the best cohort to answer the questions. And sometimes that becomes, you know, we've had meaningful cohorts of 75 people because they're highly characterized. There's a lot of information about the people and the longitudinal data is very strong with other types of studies. We need 10, 20, 30, 40, 50,000 people. And so it's always figuring out what we need, where do we have data? Are, you know, we talked about claims and clinical data and genomics. Are they all overlapping or do we have the broken arm problem where we have cancer genomics, we have clinical data from IBD, and then we have claims from broken arms. So that's another challenge is making sure when we build the cohort, we know that we have all of the pieces of data needed to answer specific research questions. And then I'm gonna put a plug in here too, diversity is increasingly important. So we have seen throughout time that people talk about this great cohort, but you know what, it's all people who have the exact same demographics. And so when we lack that diversity in these foundational data sets, we're missing information on how to develop diagnostics, how to understand disease progression, and certainly how to develop drugs that are safe and effective for everyone. So it's, it's thinking about all those different parts. What question are you asking? What types of data do you need? Do we have it? And then have you addressed diversity in the issue as well