Wellspan's Migration Journey to EPIC

Mick Murphy - CTO, WellSpan Health

CITI sits down with Mick Murphy, Chief Technology Officer of WellSpan Health, to discuss an array of digital health topics including IT implications from COVID-19, Telehealth, Data Warehousing, Analytics, Artificial Intelligence, Robotic Process Animation, and more.

Interviewed by

Bill Carter - Regional Director, CITI Healthcare

Elena Bradley - Sales Executive, CITI Healthcare

Elena: How has the pandemic impacted your daily life as a hospital CTO? I'm sure there's so many obstacles that have been thrown your way that you've had to overcome. How has that been?

Mick: Well it's really created some urgency around the topic of being flexible around working from home. And just being creative in general. So we entered the pandemic preparation all the way back in February. We launched our systemwide incident command rapidly and began looking at how we could expand intensive care space and looking at ventilator’s equipment. There quite a bit of work on innovation as well. So how can we use things differently and as well as what could we do about taking care of our community as we started separating? So if we went into the social distancing, we made a big emphasis on, on quickly going to virtual visits, ER visits, and video visits. So I'd say the biggest impact has been being agile and being creative.

Elena: Now that your company is up on Epic, what has been the overall experience for your end users? Have they openly embraced the new EHR?

Mick: On the whole? Yes. Folks have really seen the value, particularly those that had to work in multiple systems in the past. Being able to see everything together, I think has been truly impactful.

Elena: How have you worked with your clinicians? Could you discuss an example or two of that?

Mick: Being the non-clinician in the room, that is one of the most important things. Really to launch the product or the data analytics platform, the first person I partner with is our CMIO. I have an amazing CMIO, who is a surgeon by trade. He not only has the role as a CMIO, but he uses the system and understands the data needs. That's the first person that I partner with to be able to tell a good story. The next person, from a clinical perspective, that I partner with is our Quality Improvement Team. And so today, that is our Lean Improvement Initiative with a physician and other executive leaders that are in charge. So, we partner with our Quality Improvement Team to be able to understand the problem that we need to solve. They already have, fortunately, a physician and nurse or clinical leader that's taking initiative on whether it's quality improvement, CAD, Sepsis or CHF, or what have you. So really, the question is what data you are getting today, or not getting today that I can support using technology; I look at a problem that way. That's how I partner with my clinical leadership; they already have the frame and I just piggyback and add support.

Bill: How do you bring data or do you need to bring data from those two platforms together? And if so, what is your strategy to accomplish that?

Mick: So, we think that the value of health information drops off with age generally. So not saying that you're, for a research perspective, there might not be value in looking back. But our emphasis is certainly on what we're collecting and bring into Epic. We bring information then from third party systems into our warehouse, and we look at that together. We've started using some big data tools that let us do analysis there. So our first steps there, we now do some text recognition to look for incidental findings in radiology reports, for example. That's been really interesting, and it lets us help a human being be more effective. So it's, it's AI that's extending a person and making that person better.

Bill: I know you mentioned you had some AI for text recognition that you were working with. How about predictive analytics? Are you moving in that direction?

Mick: Yes, so we've implemented some of the algorithms from EPIC. So for example, the deterioration index, we actually wrote our own sepsis predictor. That's been highly effective for us. That's allowed us to achieve top decile performance and observe to expect it around sepsis. So it’s a combination. We try and use anything that's out there that's already done. We just want to leverage. So we don't feel a need to invent stuff, just to be creative. Then also where something doesn't exist, we'll go ahead and build it and get it running. But predictive, we think is, what everyone wants to get to. And we have some success so far. I still think it's a rich environment and there are a lot of opportunities out of us.