The next iteration of the virtual ICU with Roberta Schwartz with Houston Methodist Hospital on Today's Interview in Action. I hope you enjoy.
This transcription is provided by artificial intelligence. We believe in technology but understand that even the smartest robots can sometimes get speech recognition wrong.
Today we have another interview in action from the conferences that just happened down here in Miami and Orlando. My name is bill Russell. I'm a former CIO for a 16 hospital system and creator of this week health, a set of channels dedicated to keeping health it staff current and engaged. We want to thank our show sponsors who are investing in developing the next generation of health leaders, Gordian dynamics, Quill health tau site nuance, Canaan, medical, and current health.
Check them out at this week. health.com/today. Here we go. All right. Where we are from him is 2022 and we're here with reporters, Roberta Schwartz, our first interview in the morning, I'm already making mistakes. , EVP and a chief innovation officer, welcome to the chef.
Thank you so much. It's , you know, at least you started out not calling me, Rebecca, which is pretty much what people do about half the time.
So I just roll with it. And it's every,
it's the morning show. This is the third time I've done the morning show on the first one. I, I mess up something either a title or. , so you, you smoke here?
I did. I, I spoke about the, , virtual ICU and, , it kind of forced me to go back through our like five-year journey, , to get to where we are today, which is kind of a, a virtual ICU rolled out any, all of our different hospitals
and our ICU, or
Yeah, no, it's, it's pretty much the same thing. , I think the difference is. It's interesting that, , virtual ICU's have kind of an EIC use, whatever, , tele enabled ICU's depending on who you want to do have, , to a certain extent been re-imagined from the first time it used to be kind of 10, 15 years ago.
Version 1.0 happened. It was this bunker concept. And then we're going to be a whole bunch of people living in a bunker. And, , they really kind of now are now, , a program that is very, , side-by-sides, it's almost side by side. There's some day people, some night people within an institution that have to on the ground support people.
That are backed up by a virtual ICU and in some institutions that is people who go back and forth, actually intensivist who go back and forth between the live and the tele environment. And for some people who are, , who have them. , individuals within the environment and then have an outsourced company that kind of works with you.
So it's really kind of interesting. There's, there's a million hybrids of what a virtual ICU looks like these days.
Well, you've given me three directions. I can go one, I, I do want to talk about the clinical staffing shortages and how this potentially works around. , I did do a, an interview with, , , nurses from atrium who were talking about their virtual nursing program.
And, , that was interesting as well, to hear how they are taking experienced nurses and bringing them along side all these new nurses that they're bringing into the health system to give them the benefit of that experience. Also want to talk to you about sensors. I mean, this week health, we were at the intersection of technology and health.
, the virtual ICU, let's start with sensors, virtual ICU. It's interesting to me because it requires, I don't know if it's new sensors, we've the ICU has always been really well wired and a lot of sensors and those kinds of things, but are they changing to adapt to the new demands that we're putting on it?
So the, as you said, the ICU's have always been super wired. I mean, you know, you get every piece of data coming out of a. And I think that's, what's really interesting is every piece of data coming out of a machine, continuous data. Right. And let the Russ of continuous data. And, , one of the things that we've been discussing, which you find actually very interesting here is that, , like epic and a record is not really.
For continuous data. You know, if you think about the floor, let's just take an acute care patient for the moment, because it's a really easy example to understand. We live in Q4 vital signs and every four hours, you get a new piece of discreet data that is dumped into a field and we've built fields that have discrete pieces of data.
Now in a world of continuous data, either from a sensor or from all of this data coming out of all of these machines, we now are looking at this data aggregation business. So there's, there's kind of the stuff coming out of the machines. Then there's a layer of where does that go? And then there's a layer of algorithms that go on top of it.
Right. And right now a lot of those algorithms tell you what's happening today or what has happened today. And we're working towards a world of what is going to happen in the future. And, and so there's, there is, , what you find is there's innovation at each one of those three lever layers, there's innovation happening at the actual sensor level.
There's innovation happening at the data aggregation level. And there's, there's innovation that's happening at the algorithm level. And it's interesting because oftentimes when we sit down with a company, we have to do the, okay. Help me. Start me off. What space are you in? Right. With like define for me what you're doing and what you're doing well, and then you even have to separate for people.
Cause they'll see me while I'm a data aggregator. And then you realize what they're a data aggregator for is patients who are going home with a single device, not the plethora of data. And there are really only a few companies that can really take in this extraordinary amounts of data that can come out of continuous machines on the inpatient environment.
It's, it's incredible. We're talking about AI a lot at this conference and one of the things I, I start with this, you need clean data and. Camera's give you really clean data. This is why we're seeing it in radiology and cardiology. The other place that gets you a really clean data is those devices. It's, it's, you know, it's a constant stream of data.
Now you need to be able to process it, but I've talked to some people who have done interesting things around code blues. Cause you, you have. Information. And you're looking at it over a, I mean, we've been doing it now for a number of years. And if you're able to take that information process, it, put the algorithms around it.
You could say, you could potentially predict a code blue. You're looking at it and go, this is what this looks like. And we can potentially get in front of this thing.
Right. But you have to have right. You have to have the, the stuff. The data coming out and then really good algorithms on top. So, so the, the interesting part is I, I don't let people use the term AI.
It drives me absolutely bonkers, right. Only because I need to understand, like it's such a generic term. Right, like in, and I'll be like, okay, so are you building me a, what happened piece of a predictive model? Are you building me? What's going to happen? And, and it was interesting because in the virtual ICU, a lot of the time I spent with them was going, it's not about the technology anymore.
Technology is fabulous. You have to pick the right ones. , when it as Sarah, Pletcher our VP of strategy, innovation said you got to Colombo, you know, that the various modules, but once you Colombo them, the technology spectacular. Now the question is really around the change management because, and that's where I spent a huge amount of time talking yesterday is your doc.
I can tell you, you know, their answer was, how are you going to tell me if this virtual ICU is better? And like, I'll tell you what my job is actually, to make it no worse. So how about we start out with the same score cards that we've got, right. And I figure out how to get you more predictable. And make it no worse.
Then what they found is actually we had a reduction in Copeland's and they were like, well, maybe it's better. And I'm like, I know you don't want to admit it. Like I I'm, I'm not going to take it like, and they're, they're starting to realize that they can't, they, with our intellectual capital can build those predictive models with some good data scientists and build from where they were, which is no worse.
And get you back.
But the cultural transformation is interesting yesterday. I did an interview, a 3d mammography. And again, I'm going to say the word AI, you can hit me if you want, but that the AI model was essentially going through these images and it was, it was physician assisted, right? So it's circling these things saying, look at these things, these look like anomalies.
We're not going to diagnose because we don't want to diagnose, but we want to make your job easier. And they were talking about the fact that, you know, you end up by just doing this. 55% decrease in the amount of time they're doing reads because it's like, oh yeah, that's, that is what I would normally look at.
But changing that culture, first of all, we can't say machines diagnosing or machines replacing, but it is machine assisted. We can, and we use machines all over the place to assist us. Are we starting to see physicians? , become more open to that concept of machine assisted performance.
You know, it's interesting because the answer is yes, they love the concept of machine assistant, but what they want to do is keep all of the resources they've currently got.
And get the technology on top. And the reason that I was very specific, right? My executive vice president role and my chief innovation role is to say to them, I love you, but it can't be amped, right? Like there's only so much and we will be able to afford it. Does you? We are going to have to change. The structure and that's like atrium.
It's fantastic. They're right, right. I don't, I mean, the tele precepting is probably a cheaper role at precepting than the role we've currently got, which is, is hard. And we do have an awful lot of new nurses coming up through our system at the same time. One of the challenges that we have is that layering on we're going to have to return the investment, right?
for me, , of four to one ratio or five to one ratio, but that's what I heard in the nurse informatics meeting yesterday. Don't change our ratios.
Right? Give me all the tools and don't take change my ratios. And, and I look at that and I say like, as an operator and I do, I operate a large academic center.
When I put something in, I'll say to them, I'm changing your budget and here's the way I'm changing your budget. And if you don't believe that this piece of technology is going to give you that lift don't buy it.
It's interesting. So nursing. Really clinical staff shortage. It's not just nursing. There's, it's all across the board.
How are you looking at that challenge? Are there specific things you're looking at at this point?
So, , I will tell you, , right now I'm concentrating very heavily on the Q4, our vital sign, , focus. It's a big focus of mine. , I, a little big one, one could call it that I've gotten a little obsessive. , which is I need to get out of the Q4 vital sign business for a whole bunch of reasons, which actually probably won't see fan and nursing staffing, but will save me on the nursing support staffing and then enable me to both reduce the amount of support that in, in that area, because they turn over way to.
, it's not just nurses that turn it for your nursing assistant turnover and enable me to give better support to my nurses. So that's, that's kind of our current focus, , in the nursing tele precepting, again, looking at the amount of time our nurses are spending precepting and whether or not we can get those new nurses up to speed, much quicker to take patient loads is a big deal.
Most people will tell you it's 12 weeks or 20 weeks in an ICU. The question is, can you get them there? You know, eight weeks, if you give them, then when they're done tell a precepting support. So, , I think that everyone's looking at how you solve this problem. A little different, I will tell you in the nursing, in the nursing area, it's pretty new.
Yeah, absolutely. Roberta. We're going to leave people wanting more. Cause I could have talked to you for another 20 minutes. Fantastic conversation. I really appreciate your time. You got it.
Thank you. Take care.
Another great interview. I want to thank everybody who spent time with us at the conferences. It is phenomenal that you shared your wisdom and your experience with the community, and it is greatly appreciated.
We also want to thank our channel sponsors who are investing in our mission to develop the next generation of health leaders, Gordian dynamics, Quill health tau site nuance, Canon medical, and current health. Check them out at this week. health.com/today. Thanks for listening. That's all for now.