By using AI and cloud computing to analyze mountains of personal health information, it hopes to unlock a new era of customizable care and treatment.
“What makes an individual unique is a combination of so many things. Certainly a person's genome – his or her genetic ancestry – is critically important, but there is much more, including environmental exposures, cultural issues, personal experience, and many other factors,” Dr. Bruce Korf, chief genomics officer at the University of Alabama at Birmingham’s School of Medicine and principal investigator of the Southern All of Us Network, told NIH.
“Together these create a whole much greater than the sum of the individual parts. Now, for the first time, we have the ability to put this all together, and in my mind, that's what All of Us is all about – not looking at any one factor, but rather integrating multiple sources of information to paint a larger picture that will vastly increase our understanding of individual health.”
Genomics Cloud Solutions
Since its founding, All of Us has enrolled more than 366,000 participants and received more than 279,000 biosamples for genomic cloud sequencing, as well as amassed data from more than 233,000 electronic health records (EHRs) and more than 1.34 million completed surveys.
The program isn’t just designed to collect data, however. Rather, it’s intended to disrupt how researchers actually work with data. Specifically, NIH argues, researchers need to be able to process more data, more quickly.
Typically, researchers download datasets to a local computer, which works fine for small amounts of data, but fails at scale.
“That pattern doesn't work anymore. It means that you're copying data every time you want to work with it, and the data lives in many places, which makes it harder to monitor and control what happens to it, and harder to collaborate,” All of Us member David Glazer, research engineer at Verily, told NIH.
“So we are taking a very different approach: Instead of bringing the data to the researchers, we want to bring the researchers to the data. That’s a fundamentally different approach with a huge number of advantages, and it means we don’t just do things the way they’ve been done before.”