Finding the Invisible Patient
Jason Pyle, CEO, BaseHealth
Delivering excellent patient care and controlling healthcare costs should not be an oxymoron. Given the unprecedented healthcare spending that is currently happening in this country, it’s hard to imagine a world where these two goals can coexist; however, there is hope.
It’s a hope that gets me excited to go to work each morning. It’s knowing that we can tackle two of the country’s greatest challenges — reduce the per capita cost of healthcare and provide access and critical care needed to both improve our overall population’s health and improve the individual patient’s experience with the healthcare system.
How? The short answer is data, but before I go any further, I know what you’re thinking: everyone says data. But where’s the example of data driving real change that both reduces healthcare spend and improves care?
At BaseHealth, we have that example, and it starts by identifying the “Invisible Patient.” We all know the story of an invisible patient. It’s someone who looks healthy on paper, until they hit a tipping point, and then it’s one adverse health event after the next. These are the people we all know. With the right medical intervention at the right time, their healthcare trajectory can be improved and can begin to center on well care instead of sick care.
Healthcare systems have a lot of data, yet they still have a hard time finding these patients. There are countless population health management solutions available today that leverage retrospective claims and ICD-10 data to “predict” the total risk of a health system’s population. These tools help (to a point) predict how many people within a total population will come down with diabetes, for example, or how many individuals who are already identified as high-risk based on previous claims will get sicker.
But they don’t help with understanding unknown risk within a population, and specifically, the invisible patients. Invisible patients don’t have a complicated claims history, and they’re currently considered healthy as far as their health system is concerned, but in reality, they have a very real and looming risk of a major health issue.
What if we could change this? What if we could enrich the retrospective claims and ICD-10 data with laboratory, biometric, social and family history, and even behavioral data and pass it all through an analytic engine that associates all known risk factors with all known disease conditions that are present in the entirety of the evidence based published and peer reviewed medical literature available today?
We can. This is what I’m doing at work that gets me so excited. At BaseHealth, we find the invisible patients for healthcare professionals, so they can intervene to both prevent diseases before they start and help guide their care before it’s too late. We don’t just find a general population of hundreds who are likely to be diagnosed with a disease, we break it down by individual patient — revealing how that person’s specific medical history correlates with known risk factors and identifies possible disease threats — 43 diseases, to be exact. Then, once we know who that person is, their healthcare provider can intervene and either diagnose a missed disease or recommend a preventative treatment plan.
So that answers the question of improving care, but where does the cost savings come in?
Well, for a health system, if they know who their invisible patients are, they can dedicate their outreach efforts with intervention programs toward very specific patients where the return on investment will be the greatest. Instead of offering a pricey, underutilized, “one-size-fits-all” wellness program to its entire population, they can intervene and help the patients who need it most.
Today, I’ll be in Santa Clara at Health 2.0 showcasing our demo in a session called “Transforming Care & Insights Through Big Data & Analytics.” If you’re at the show, I hope to see you there, if not, consider watching via the live stream. You can also look for our #InvisiblePatient social media campaign, where I encourage you to show support for the Invisible Patient by tagging a selfie or sharing a related story with the #InvisiblePatient hashtag on Twitter.
Questions or thoughts? Please comment below, I look forward to continuing the conversation!