Creating the human health map
Project Baseline was created to map human health, but who is responsible for thinking about what data we collect to build that map and how to make it actionable?
Project Baseline was created to map human health, but who is responsible for thinking about what data we collect to build that map and how to make it actionable? We sat down with Vanessa Ridaura, genomics scientist, and Naxin Wang, data product manager, to learn more.
Thanks for joining us, both! Can you talk a little bit about your background and what you focus on within Project Baseline?
Vanessa: I'm a senior scientist and technical lead for Project Baseline's microbiome efforts, which means I'm focused on using science and technology to understand how the microorganisms associated with the human body, known as the human microbiome, impact our health. I'm also responsible for Project Baseline's science strategy more broadly, including the tools and processes we use to study humans on a molecular level.
Naxin: I'm a product manager, focused on data collection and analysis within the Baseline Platform. Broadly, I work on ensuring we have the right data streams to help researchers understand health and making that data useful for analysis. This can include everything from traditional clinical data, like test results and other medical information, to more novel data streams like sensor data and historical information like electronic health records.
What are some of the challenges that go into collecting this data?
Naxin: One of the biggest data challenges, especially with novel sources of data, is context. For example, with data from the Study Watch – a sensor used in the Project Baseline Health Study that captures activity information – we know you're moving, but are you walking or are you riding a bike? We handle these questions by making our algorithms and devices smarter and more effective over time, as well as by working directly with participants.
Both of you are dedicated to creating insights from health data. How do we align on which types of data we want to collect?
Naxin: We start by understanding why this data is useful for understanding health by working with scientists like Vanessa, biostatisticians, clinicians, patient advocacy groups and other industry experts. Then we turn to how we can actually gather a particular data type–some methods are more feasible than others. For example, within the Health Study, we decided to begin collecting geolocation data because participants can share it in an easy and seamless way if they choose to–and evidence suggests that physical location can have a significant impact on health outcomes. To move science forward, however, it's not just about how much data we can gather. We also need to organize and unify this data to make it meaningful.
Vanessa: Exactly. From a scientific perspective, data starts to become valuable and interesting when we can bring it together to get a holistic look at human health. Traditionally, most of us have a point-in-time-snapshot of our health based on clinical labs. But with a broader set of data, we can start to make comparisons and explore relationships between different processes in the body. For instance, what effect do nutrition, activity level, and genetics have on our microbiome? How does each affect the other and what's the net impact on health? These are some of the questions we can begin to explore.