Ribbon Health’s CTO Nate Fox on APIs, machine learning, and how data science can improve healthcare
Nate Fox or “Fox” as he’s known to the Ribbon team, recently joined Jon Krohn on the SuperDataScience podcast to discuss (you guessed it!) data science in healthcare at Ribbon.
It’s all about application programming interfaces (APIs) and machine learning in this episode, as the two dive into how data science has the power to significantly improve healthcare. Beyond the enthusiasm for really cool technology, Nate shares more on how Ribbon’s values play into every aspect of the culture and product decisions and what it’s like to tackle a wide number of interesting tech challenges at a fast-growing company. Listen to the full episode here.
How and why does Ribbon Health exist?
Ribbon’s mission has always been to make every care decision convenient, cost effective, and high quality. This mission hasn’t changed since founding the company 6 years ago, but the “how” has. The first iteration of Ribbon’s product (then called HealthWiz) was actually a care navigation platform that aimed to make it easier for patients to find and utilize care, by reminding them of their benefits, finding them doctors, and booking appointments. Fox recalled, “The utilization of this feature was phenomenal. People were like, “Oh, wow, I’ve been meaning to go to a doctor, but it’s kind of a pain. So, sure, find me that doctor.” However, as the team went to find and book that care on the back end, they realized they were spending countless hours sifting through inaccurate provider information- providers that no longer practiced, weren’t accepting new patients, were out of network, moved offices… the list goes on. They had a massive data problem on their hands. After some testing and learning, they realized that they could apply machine learning to predict the accuracy of a provider data point and thus… Ribbon Health was born.
Building an API to Simplify Healthcare
As Fox and co-founder Nate Maslak set out to design an API for healthcare data, they were determined to address the gaps they had experienced in their own application. “We actually had a lot of empathy as a company because we were utilizing other data services and provider data solutions before we built what is now Ribbon Health. And so I think in having built healthcare applications ourselves, a lot of what we wished for guided some of our initial product development,” Fox said.
Tackling the massive problem of provider data inaccuracy requires collaboration across multiple teams, especially data science and product engineering. Ribbon uses machine learning models to identify which data points are more likely to be correct than others. Fox explained a unique element of Ribbon’s data model: “We actually have confidence scores for the data points that we share… We wanted to simplify it. So we made a five point system. And so “five” is verified, validated. It is true. We know it to be true. Four is a super high confidence of 90%+ accuracy, all the way down to one where it’s the inverse- we’re actually very confident that it’s wrong.”
Listen to the full episode for more on how to train a data science model to assign confidence scores, and how to ensure the uptime and reliability of APIs.
What’s it like to be on the tech team at Ribbon?
As the CTO of a tech company that’s quickly growing, Fox’s day to day is focused on how to best scale and grow Ribbon’s technology organization more broadly. That often falls into three major buckets- hiring and building out a robust team, improving the existing technology organization and those operating processes, and thinking through Ribbon’s technical architecture and the products that should be prioritized.
Fox emphasized that the people at Ribbon Health are really what makes the company special. “We have company values that we take seriously and we really lean into. And so the people here, they’ll have to solve hard problems. They’re highly kind, empathetic and yes, there’s a lot’s happening, but it’s a lot of fun, especially when you’re building things with people that you enjoy working with.” The hiring philosophy at Ribbon focuses on both technical aptitude and values alignment, to build a team that’s highly aligned with the overall company mission and vision.
One of Fox’s goals is to continuously build out Ribbon’s internal processes, and ensure that tech team members are successfully set up to do their best work. He shared one example of how Sameer, a Data Scientist at Ribbon, was able to innovatively leverage AWS Lambda, a serverless event-driven compute service that AWS provides. The tool has had two major impacts: “The first is, it allows us to paralyze really, really compute-intensive… work. Every time we get a new location endpoint, we have to recluster that data at that address node. And so we can run a lot of these micro transactions or micro events and paralyze millions and millions and millions of them in a given day. The second thing is it sets the bedrock of which our data engineers and data scientists can actually interact with each other by having a landing function that they can call where they can say, ‘Hey, I scored this data point, tell us how accurate it is.’ And then once that interaction node is established, data science can update and change their code and how things work with the core data pipelines still running as they do. So it allows for a more seamless interaction between data engineering and data science.”
Beyond the innovative technology and tools that Ribbon team members get to utilize, there’s an opportunity to make a big impact on the world of healthcare. With so many interesting data science problems out there, Fox stressed that, “our challenges are really driving value within healthcare. If you’re the kind of data scientist that wants to focus on helping patients find care as opposed to optimizing the next ad click, Ribbon Health is a great place for you to come to. We’re working on hard problems and building technologies that are affecting real humans and patients at the end of the day.”
To dig into more fascinating tech topics like knowledge graphs and XGBoost models, listen to the full SuperDataScience podcast episode. If you’re interested in joining Ribbon’s rapidly growing tech team, take a look at our amazing benefits and open roles here.