← Becker’s Healthcare Podcast
Loading summary
Transcript11 lines
- [00:01]
A
Philips is a health tech leader focused on innovation that improves the health and well being of people. Our healthcare technology and informatics solutions help care teams diagnose, treat and manage more patients with greater precision, speed and confidence. Across the care journey with Philips, clinicians are empowered with streamlined insights in the moments that matter for every patient. Better care for more people Phillips Foreign.
- [00:29]
B
This is Gracelyn Keller with the Beckers Healthcare Podcast and we are recording live at the 2025 Health IT Digital Health and RCM Conference. I'm currently joined by Chris Horvat who is the Senior Director of Clinical Informatics at upmc. So Chris, thank you for being here and I'd love for you to start off by sharing a little bit more about yourself and your work in healthcare.
- [00:50]
C
Well, it's my pleasure to be here and so I am a practicing Pediatric Intensivist at UPMC Children's Hospital Pittsburgh, but also a clinical informatician and have a role in our ICU Service center at UPMC and then also in the Department of Critical Care Medicine where I help with all things informatics across our more than 50 ICUs in the health system. And so this has a really heavy analytics focus where we are actively working on standardizing a lot of our workflows throughout both adult and pediatric ICUs and then measuring our performance improvement using best practice analytics strategies across the health system.
- [01:32]
B
Wonderful. Well, thanks for taking the time to be here and let's start off our conversation by talking about AI that's such a hot topic in healthcare right now. Nearly half of medical practices reported using AI in some capacity in the last year and it remains a key topic for health IT leaders. So from your perspective, what are the use cases that are making a difference right now and how are you leveraging them in your organization?
- [01:56]
C
One of the main ways that we've been leveraging generative AI, specifically over the last last three years is to elevate individual skill sets to accomplish more sophisticated tasks or to streamline tasks that used to take many hours into hopefully just a handful of hours. So some specific examples of that would be we took upon ourselves to do a major risk adjustment project across our ICUs over the last couple of years. And what I mean by that is we needed, as we've grown as a system, we needed to understand how ICUs were performing relative to one another. And we ended up partnering with the Lab for Computational Physiology at MIT to integrate a more advanced machine learning based risk adjustment algorithm that assesses individual patient illness severity and gives us a better picture about the differences in the populations between ICUs across the system so we can compare relative performance more accurately. To embed this really sophisticated ML approach, it involved harmonizing data streams across multiple electronic records. It involved deploying a machine learning model into our data and analytics landscape. And in order to do that with a relatively small team, we leverage generative AI a lot to help us refine our code, to debug our code, to build IT pipelines, and to develop the harmonized data strategies that we needed in order to deliver this solution. We could have accomplished it without AI, but AI dramatically accelerated that work.
- [03:39]
B
Absolutely. And as virtual care expands from AI enabled tools and remote monitoring to broader digital health platforms, introducing new technology does bring challenges. So what advice do you have for leaders navigating everything from governance to patient engagement? And can you share an example of how your organization has balanced innovation with operational constraints?
- [03:59]
C
I guess my first piece of advice that comes to mind, which might be the most important, is don't try and boil the ocean when you start. And what I mean by that is focus on what needs to happen immediately in order to accomplish the major objective, and then think about bringing things into a more unified framework as an eventuality, but not something that needs to happen right away. And so a more specific example just to illustrate this would be as we continue to grow as a system and we bring on other hospitals into our analytics pipelines, we really focus on the pragmatic steps that are necessary to get their data flowing before we start building an end to end pipeline. So that means things that are simple, like trading flat files by email before building a harmonized query across multiple data structures, simply so that teams on the front line can see their data earlier, worry about the bigger picture as part of that process. But we take those small, very practical steps along the way that allow us to deliver before the entire product is completed.
- [05:10]
B
And as we wrap up our conversation, I'd love to know your top piece of advice for healthcare leaders as they prepare for future advancements in technology and rising demands for care.
- [05:20]
C
It continues to not be about the technology Healthcare, it is still about the people first. So what are the needs of the frontline clinicians in order to deliver deliver best possible care? What do the patients need in order to get from a state of illness into a state of health? What do the teams need to feel like they are well supported, that they are working in a good culture? And then after you've considered all of those things, how does technology actually help in supporting you to accomplish those objectives? So it's always people first. Technology second?
- [05:55]
B
Absolutely. Well, thank you so much for joining me today on the Beckers Healthcare Podcast. Again, we are recording live at the 2025 Health IT Digital Health and RCM Conference.
- [06:05]
C
Thank you very much.