Now the Health IT lead at Alphabet subsidiary Verily, Dr. Joshua Mandel was part of the team that created SMART Health IT, the open, standards-based platform that many health developers now use to build apps. But all that started when he got sick of some grunt work he was assigned as a medical student. Mandel told the story at Dev4Health at the HIMSS Innovation Center in Cleveland this week, during an onstage interview with Health 2.0 founder Matthew Holt.

“As a medical student, one of my tasks was to show up at the hospital at 5 o’ clock in the morning so I could copy down vital sign readings from the surgery board onto paper so we could have efficient rounds, knowing what are the most important cases,” he said. “This was about an hour-long task with very little educational value to it. It sucked.”

So Mandel spent what little free time he had building a system to automate the task.

“All this was a lesson for me in, number one, all systems are hackable if you care enough,” he said. “But it was also a great effort. It wasn’t the kind of thing that would scale very well. It took a lot of deep domain expertise and knowledge about how this particular EHR is configured. That really started me thinking of the whole world of medical informatics and how we could make a difference at scale.”

That was about a decade ago, in the late 2000s. When Mandel graduated medical school he decided to pursue the task of making EHRs easier to interface with, rather than going into practice. He joined the SMART team, one of a handful of ONC-sponsored research projects.

“There was on the order of $3 billion being spent to incentivize EHR adoption,” Mandel said. “And then there was a research community making the case that the government should also be investing in improving EHR technology. Adoption is important, but making sure the technology improves over time, incorporates what we learn from medical science and informatics, that’s important too.”

Mandel said that SMART came along pretty well as a toolkit for building apps that talk to the EHR. But, especially in dealings with EHR vendors, they were hampered by the lack of standards.

“The EHR vendor community at the time gave us mixed feedback,” he said. “But the key piece of feedback we got was ‘This is really interesting, but feels like a science fair project at Harvard rather than a robust technology that can be deployed at scale.’ And if you’re really serious about this, you need to use standards. But of course the Catch-22 is there weren’t any good standards at the time and it wasn’t obvious there were any on the horizon. So it wasn’t clear if that was a delaying tactic or they actually meant it. As FHIR came together, we had an opportunity to call that bluff.”

FHIR, Fast Healthcare Interoperability Resources, is a data standard maintained by standards body HL7, which launched in 2012 and has come to prominence in recent years. With SMART and FHIR working together, Mandel said, a lot of promising development is starting to happen. There’s still a lot of work to do, however, and Mandel has some ideas about where the next frontier might be.

“Almost any deep question you dig into requires data from across the healthcare continuum,” Mandel said. “Some of that is structured and some of it is unstructured and today almost everyone is focused on the structured part. … On the other hand there is a tremendous value to the unstructured clinical notes and reports and all of the light information that just exists as text in the EHR. Most clinical use cases have really specific questions like ‘what was the order of chemotherapy’ or ‘what was the size of this tumor’. All these things are stored in an EHR as text. You could drive tremendous value from deriving information from free text. And I think that’s going to be important.”