Shane Cooke Explains Why Intensive Care Unit Doctors Need a Dashboard

Episode Summary

This week Harry interviews the head of Etiometry, a Boston-based startup building visualization systems and decision support software for hospital intensive care units. Shane Cooke says critical care “is an incredibly complex environment where speed matters and information matters.” By aggregating real-time data, lab results, and historical patient records on a single screen, Cooke says, Etiometry hopes to show caregivers that they can glean more value from the data that’s already collected by intensive care units but seldom unified.

Episode Notes

This week Harry interviews the head of Etiometry, a Boston-based startup building visualization systems and decision support software for hospital intensive care units. Shane Cooke says critical care “is an incredibly complex environment where speed matters and information matters.” By aggregating real-time data, lab results, and historical patient records on a single screen, Cooke says, Etiometry hopes to show caregivers that they can glean more value from the data that’s already collected by intensive care units but seldom unified.

Etiometry’s visualizations run on any hospital-approved web browser, and can therefore be used to monitor patients remotely. Not only does this unified visual presentation of input from monitoring devices and medical records can increase the effectiveness and efficiency of ICU care, Cooke says—it also enables real-time, risk-based analytics that help medical staff anticipate a patient’s course.

Cooke joined Etiometry in 2019 as the president and CEO, bringing over 20 years of experience in the medical device and pharmaceutical marketplaces in a variety of sales, marketing, strategy, and portfolio management roles. Before joining Etiometry, Shane spent five years as chief strategy officer at Cheetah Medical, and prior to that role, Shane spent 11 years with Covidien in the patient care, vascular therapies and corporate sectors, with positions such as corporate strategy, market and competitive intelligence, leading the market development center of excellence, and leading strategy efforts for Japan, Europe, Australia and Canada.

Please rate and review MoneyBall Medicine on Apple Podcasts! Here’s how to do that from an iPhone, iPad, or iPod touch:

1.Open the Podcasts app on your iPhone, iPad, or Mac.

2.Navigate to the page of the MoneyBall Medicine podcast. You can find it by searching for it or selecting it from your library. Just note that you’ll have to go to the series page which shows all the episodes, not just the page for a single episode.

3.Scroll down to find the subhead titled “Ratings & Reviews.”

4.Under one of the highlighted reviews, select “Write a Review.”

5.Next, select a star rating at the top — you have the option of choosing between one and five stars.

6.Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.

7.Once you’ve finished, select “Send” or “Save” in the top-right corner.

8.If you’ve never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out.

9.After selecting a nickname, tap OK. Your review may not be immediately visible


Harry Glorkian and this is Moneyball Medicine, the interview podcast, where we meet researchers, entrepreneurs, and physicians who are using the power of data. To improve patient health and make healthcare delivery more efficient, you can think of each episode is a new chapter in the never-ending audio version of my 2017 book Moneyball Medicine, thriving in the new data-driven healthcare market.

If you liked the show, please do us a favor and leave a rating and review. At Apple podcasts. When we watch TV, medical dramas, we see doctors moving around ICU rooms, checking different monitors on different medical devices, all of them showing different data, making strange sounds. Have you ever thought to yourself, how did they keep track of all that?

My guest today, Shane cook heads accompany. Etiometry. That sees an opportunity to help doctors and other medical professionals in the ICU setting increase the effectiveness and efficiency of caring for patients by better leveraging of all that data there. Right? Innovative software solution provides an unified visual presentation of input from various monitoring devices and medical records so that medical practitioners can see all that info in one place.

Call it a dashboard. A further key benefit to integrating all this data into one platform is that their technology enables real time analytics of that data, thereby allowing doctors to see the patient’s history, their current status, and where they’re likely headed, given comparative population analytics,

Shane, welcome to the show.

Shane: Thanks for having me. It’s good to have you.

Harry: I’ve watched your company from afar, just keeping an eye on it. Etiometry Shane, tell us a little bit about the company so that anybody who’s not familiar with, it can sort of get a, a bird’s-eye view of, of the company and sort of what its immediate goals are.

Shane: Sure. Absolutely. Yeah. So we’re really focused on driving efficiency in care by really unlocking the full potential of all of the patient data that is out there. We focus primarily on the ICU right now and what we’re really focused on is driving efficiency and care streamlining decision-making.

And we do that and improving outcomes, of course with our clinical decision support platform that we have. So we have an FDA cleared clinical decision support. Software platform for the ICU. And that aggregates data from multiple sources pulls it into one. visualization gives you the full context of the patient, all of the longitudinal trends for that patient going back a couple of weeks, or as long as those inputs have been coming into the system.

And then on top of that, we have developed two proprietary risk algorithms that are FDA cleared as well for the pediatric population. So we show that on one visualization to really help guide decision-making for patients in the critical care environment, which is an incredibly complex environment where speed matters the right information matters, really guiding that decisions for, for those key clinicians in critical care environment.

Harry: Yeah. So, so just for everybody, like ICU means intensive care unit. And you know, if you’ve, if you’ve been in a hospital, which I always, you know, you know, as much as I love them, I hate them. You know, the, the beeps and the boops will drive you nuts. You know, if you only had one thing beeping a booping, that might be one thing, but you know, there can be five, 10 different things beeping and booping which at some point you become, I think desensitized to, I would assume based on longitudinal data and the way the system tracks it, it can sort of almost like your car with a warning light ahead of time. Tell you that something. Is going wrong that you may want to take a look at. Can you, can you walk us through sort of a typical example, maybe.

Shane: Yeah. And I think what you’re saying is right on target, because it is the ICU is an incredibly complex environment with numerous data sources. There are numerous instances of data overload.

There’s just so much data out there that it’s almost too much to come to comprehend and process for your patient. You know, frankly, there are clinical studies out there talking about clinician burnout syndrome where. There’s just so much to do so many patients to manage. It’s very in-depth and so many data sources to, to constantly take a look at that. Pulling it all together and then streamlining those decisions. There, there’s a real, there’s a real basis for that and a real market for that. And that’s what we’re focused on doing. So for instance, a good example is, you know, when you walk into a patient room in the ICU, you see a patient monitor, you see numerous other devices and they all have readouts on them and, and in a display What we do is essentially pull that into one visualization, which oftentimes at our sites sits right by the bedside.

So that can clinicians can look at that they can, they can impact the system and look back over the course of a couple of weeks really dig into key parameters and see the interplay from things such as lab results that are coming into our system in context, with the vital signs and our algorithms that are on our system as well.

Harry: So. Instead of looking at all these different tick. I think about this. I mean, if you know, the analogy that I would think of is like in a, in a big seven 47, there’s a lot of dials. Right. But, but the pilots are trained to sort of look at some very specific things. And now with the, you know, autopilots and everything else that are in there, it sort of made it easier to manage this.

And a plane is not as simple. No device by any stretch of the imagination. How are, how are the physicians utilizing this technology? And is it, is it making it easier to sort of identify this? Cause if you think about like the financial world, you can look at incredibly complicated data that we figured out how to present to people visually that makes it much easier to understand how things are going.

Shane: Yeah, there are a number of use cases of the technology that are utilized on a daily basis in our sites. One common one frankly, is rounding daily rounding for the patients on every shift for the clinicians to get together, discuss what’s going on with the patient, with what’s the current situation, the diagnosis, how they’re trending Having that, having that all in, in one platform and to be able to look at all of that data in context with one another really helps to drive those decisions.

There are clinical studies pointing towards up to nine decisions are made per patient on rounding. So again, having all of that information at your fingertips that is a very common use case event reviews. So if a patient has a cardiac arrest and you want to look back and look at the history of that patient or, or other types of events that happen, it’s great to be able to look at all of those.

Longitudinal trending to make, to, to really assess what happened in that situation. And then frankly, we have a web-based platform, so you can access it. If you’re a physician at your desk in the hospital, you can access it at home or you can access it right by the bedside. Whether that’s on an iPad or on a dedicated screen.

So oftentimes they use cases, doctors and nurses will confer around the patient at the bedside by looking at the trends for that particular patient. And then for instance, our algorithms that sit right on the top of our visualization in the pediatric world they are essentially. Calling an early warning sign to bring more attention to a patient.

So as that is trending higher, that is, that is assigned for, Hey, let’s pay attention to this patient, dig in, find out what’s going on. And then you can impact that with an intervention.

Harry: Well, that was going to be my next set of questions, which is once you have enough data from enough patients, especially, you know, being treated in a particular way, you can start to see that one intervention has a better outcome than another intervention or be able to actually highlight something is happening that needs attention before the event actually happens. And so, you know, when one of the examples I’ll give you when I was interviewing the CEO of the Aura ring, his comment was is you could see or measure physiological.

Changes three, four, maybe even up to five days before the patient actually feels that there’s a problem. And I, and I think about it, like if you’re developing a temperature, you don’t feel the first feud, you know, upticks, right. It’s got to get to a certain point where your body says, Oh, I’m not feeling well.

Right. And so I would assume that the systems that you guys have can with enough data and with you know, putting together the right analytics, you could start to see these trends come up before they actually become a problem.

Shane: So, Yeah, and I think that there’s a, there are a few different ways to look at that.

The data that that goes through our system is, is stored at the hospital level. And the hospital has access to that. And we, we can help them with that. From a quality improvement perspective of assessing all of that data. We have a data science team on, on our, on our R & D team who helps, who helps hospitals with that quality improvement aspect, but then you also have the aspect of.

Every patient is such, it’s such a heterogeneous patient population within the ICU. So of course there may be trends across them that you can look at most, most, most often retrospectively to, to assess that data. But the power of what we do is we’re actually pulling in that data every five seconds.

Into our system. So you can essentially do it in near real time at the bedside for that particular patient. Right now, it is a essentially personalized medicine where you’re looking at that patient comparing that patient to themselves and the trends that have been happening over the course of the last couple of hours or a couple of weeks.

And you can really see when, when something may be out of the, out of the ordinary, if you will, and come in and intervene. So there are a few different ways to look at it from a, from a full retrospective almost like a machine learning type of approach where you’re looking at all this data and looking at different patterns and outcomes, but then there’s the model based approach that we do that actually helps clinicians in near real time read at the bedside.

Harry: And so, I mean, could you walk us through an example of how. That would take place to give somebody, you know, the people listening, something real to sort of [00:11:00] have in their mind.

Shane: Sure, sure. So we have a number of case studies and that, that I could point to. So, so for instance, a patient comes out of cardiac surgery.

And they’re in the ICU. And you start to see our algorithm for essentially hypoxia it’s called inadequate delivery of oxygen is an FDA cleared out, really moves the first one that we had FDA cleared going back a few years. And when that is trending red, that is the, the increasing probability that a patient has a mixed venous oxygenation below a certain level.

So. When a clinician looks at that and sees that that has been trending red and trending red for some time. What their first action is, is really to bring more attention to that patient and bring the doctors and nurses next, next to the bedside, look at all of the various trends for the patient and look at what may be out of normal range that they could perhaps intervene on.

So for instance, they may look at the Al algorithm and say, okay, the blood pressure is really low for this particular patient. So we have a few different options that we could. We could intervene on, we could give the patient intravenous fluids. We could give the patient of vasopressor et cetera, to, to impact those, those metrics and get them back online.

So that’s a, that’s a very common use. And what it’s often called is this escalation of care. As you see the algorithm trending in a particular direction, you are escalating care with the care team to make sure that that patient gets back on track.

Harry: And so my assumption is being able to get ahead of this or being able to manage this better, theoretically should have two impacts, right?

One is somebody recovering faster or spending less time in an ICU, and then therefore, a decrease in costs. Moneyball Medicine is all about trying to achieve those two outcomes in my mind. So is that, are you guys seeing that happen with with your platform?

Shane: We are, we have, we have evidence clinical evidence showing reduction in length of stay.

And we have clinical evidence showing reduction in cost per patient as well. There’s also some studies that show that point towards a reduction readmission back to the ICU. So if you’re in the ICU for an extended period of time and leave to go to a. Step down unit or general care ward. Oftentimes those patients go back to the ICU.

So we’ve seen a pretty substantial decrease in readmissions back to the ICU in some of our clinical studies. So we continue to drive evidence. That’s one of the things that I’m most proud about the company is the, the level of evidence that, that we’re able to drive. And that’s frankly, that’s, that’s a key part of our system.

Being that it’s software being that the hospitals that we are involved with. We are collecting that data at the hospital level. They have access to that. They can mine through to drive that clinical evidence. So and frankly that the ability to collect that data for the hospital also points towards other potential utilizations of the technology as we move forward.

Harry: Yeah. I mean, I’m just thinking, like, if you’ve got all this data on all these different patients, you, you, you can almost create simulations . Understanding, you know, basically based on how other patients have reacted to either a medication or an intervention, what typically happens next on one hand, you could almost help people move towards a more efficacious intervention.

But on the other hand, I think for a simulation on training, that would also be a, a big. Step up having the system react to what would probably happen in a, in a real patient.

Shane: Yeah. Yeah. And I think that’s a really good point. And that, that is certainly something that, that we have given the data that we have access to.

We of course get de-identified data. We don’t do anything with, with Phi, but you know, the hospitals collect the data at their, their level of, we get the de-identified data for future algorithm development, et cetera, as we continue to work on new algorithms. So our data science team works on that data.

And, and looks at that. And from a, from a perspective of looking at key trends and, and looking at exactly what you’re talking about here, you know, are there key trends that we can help hospitals point towards? We automate reports for hospitals as well, based on quality improvement initiatives.

So yeah, it’s, it’s a big part of what we’re about. It’s again, it’s, it’s really getting back to unlocking the full potential of patient data.

Harry: That’s interesting. So I should, I should introduce you to a, another, you know CEO, I spoke to Charles Fisher from unlearn AI where they’re, they’re creating a digital twin for clinical trials, right?

So there might be some synergies that, that you guys can take advantage of because they’re trying to create the digital twin and you have actually the patterns that a patient would go through that might make that digital twin more real. Yeah.

Shane: And that that’s frankly, that’s the language that we use internally, as well as digital twin.

Yeah. Given that what separates us from a lot of companies out there and the way that they do data and analytics is we built a model of human physiology. So we have taken all of this data that we’ve collected all of the clinical literature that we have mined through and essentially looked at. All of the various functions in the body, cardiovascular mechanics, pulmonary mechanics, autonomic regulation, acid-base balance, essentially translated that to differential equations. So we have built a model, a mathematical model of human physiology that we essentially based on the data coming into our system is constantly updating to show what, what, and compared to that patient in the bed. So that’s, that’s very similar, frankly, the, the digital twin. I’m glad to hear that others, others using that, because I think it’s an important element of what we do.

Harry: Well, you know, it’s, it’s also something the FDA is interested in is, you know, can we create a digital twin To help trials go forward. Cause sometimes you can’t get as many people as you like into a trial, but if you had a digital twin that might serve as, as a proxy for a real patient, I want to ask something like, you know, how many patients do you have like that you’ve monitored and trying to get an idea of like, how, how, cause at some point you get to a big enough data set that you really can simulate things.

With much more clarity than in other situations.

Shane: Yeah, I think the best way I could characterize it is, is we have millions of hours of collected physiology data. Human physiology. So we are, we are constantly seeking out more and more information around that data. So diagnosis, information medication, information, et cetera.

That’s, that’s always what, we’re, what we’re working on doing more of. So we can have more, a richer data set to be able to do some of the analysis that you’re speaking of, but we have quite a bit at our disposal that we continue to work through internally for, for algorithm development.

Harry: So your main customer is, is our hospitals, but that data set you’ve got us has got to have, you know, data’s data.

I always tell people like the model is not just very singular and I sell a widget to, to someone and they use the widget data is, has a lot more uses and can be manipulated and, or have value to a lot of other stakeholders. So, are there other groups that you think would, would be able to extract value from what you’ve created?

Shane: Yeah we’re really assessing that now, you know, as I came into the company coming up on a year ago one of the key goals was really to. Too. There’s been so much fantastic technical and clinical work done over the last number of years. And, and really my goal was to build out the commercialization function for the company.

So to continue to drive, to grow the company on an annual basis, get into and engage with more hospitals, help more patients help more clinicians throughout all of this. But right now what we’re doing is, is assessing just that, which what you mentioned is what are some of the other areas. That could benefit from this data.

Anecdotally, I think that there is an angle with, with pharma and with clinical trials around. Automatically collecting data and potentially impacting some of the potential patient selection. You could even look at speed to inclusion or exclusion, and these are just, these are, these are all just hypotheses that we have as we’re assessing different markets that we could enter into with, with our technology.

But for the most part, what we are focused on, and I think it’s important for all startups to, to have that. That intense focus is on the ICU right now. There’s no doubt that, that the potential for this technology in the operating room, in the emergency department and other care settings throughout the hospital, that’s our long-term vision to essentially be that hospital safety net with our algorithms, with our data, with streamlining the care and driving efficiency.

But right now it’s, it’s primarily with the, with the ICU.

Harry: That’s well, that was going to be one of my other questions is when you’re, you know, put this into a, a ICU, do you get that aha moment from people going? Damn, I wish I had this before. Like this would’ve made my life a whole lot easier and Oh, by the way, can we use this over here?

Because we could also use a monitoring system or a early warning platform. Over in this area

Shane: That, tends to happen quite frequently, to be honest. Yeah. So the, for sure, getting the system in and seeing that visualization where you’re pulling all of this information together it’s, it’s, it’s kind of that immediate benefit that immediate aha to the efficiency and the workload that you have as a clinician.

It’s all right here in one place. And then of course, with the algorithms on top of that as an early warning sign and to bring more attention to that, patient, that’s been really vital aha moments for them. So. We have seen, and that’s, that’s a key part of our growth this year as a company is moving to other, other departments, other ICU’s within the same hospital, that’s a cornerstone of our, of our commercial strategy.

And, and that’s, that’s certainly took taken place this year.

Harry: So have you seen it You know, getting a physician to do something different is not always a trivial exercise. But hopefully data sways someone’s decision-making. Have you, have you guys been able to sort of objectively measure a shift over time of how people might manage a patient based on the data that comes from the system?

Shane: Yeah I,  think it’s I think it’s. Probably anecdotal measurement right now, just based on feedback from customers. I, I, I’m very interested in driving adoption and assessing adoption on a, on a daily, weekly, monthly basis. So that’s, that’s definitely an undertaking that we are digging into with our customers to get more insight into that.

But there’s no doubt about it. Anytime you’re changing someone’s behavior, we’re all consumers, you know, think of yourself as you get a, get a new cell phone or something. Sometimes it takes a bit to get into to get into the flow with that. It’s the same thing with, with clinicians. What we, we focus on and pride ourselves on is, is reducing workload in driving efficiency.

So if you can show someone how you are taking time out of something, That might take it. Excuse me. Might’ve taken them longer before. That’s usually the, the path to driving adoption sooner. And when you can show them how easy to use it is that that’s been our path. So yeah. Having the web based platform as well.

And being able to access that anywhere, especially this year of all years, this, this strangest years that we are the, you know, having a remote platform where you can access it away from the bedside or at home that that’s been really important. And that that’s really driven. A lot of adoption of our systems

HarryCOVID has caused a big shift in.

I think adoption of technologies in a, in a way that we had had we planned this, I think I would have said, ah, some of this will take another five to 10 years. And COVID has sort of pulled everything closer, faster. How have you seen it affect what you guys are doing?

Shane: [00:23:26] I think the. Of course, it’s been a challenge for a lot of hospitals during this time, especially in the early days, everybody was, was, the clinicians were so overwhelmed with the influx of patients.

I remember chatting with clinicians that, that I’ve known for years and they, they, they were telling me, well, we spend most of our time running around looking for PPE early days, which was just. Pretty crazy, obviously. I think the hospitals are much better suited now, just given that we’ve been through that initial initial days, it’s for sure.

It’s still a challenge. [00:24:00] Hospitals are still, still having challenges with that, but the way it’s affected us as a company we reached out to all of our customers and essentially worked with them to. Get our software wherever they needed it. You know, given the fact that it is remote given the fact that you can, you can hopefully, and potentially limit the viral exposure to clinicians by being able to remotely look at the patient and all of the key parameters and, and at times not, not need to be by the bedside.

That was really what we had spoken to customers about. I think you’ve seen many companies out there talk about how it’s been a challenging year medical device companies, and otherwise just given the lack of elective procedures, hospitals, budgets are there. They’re worried about budgets. Of course.

So I think that’s affected every company out there. We have been able to. And we’re, we’re really proud of this help more and more hospitals and patients this year than ever before. And that’s partly due to COVID for sure. Just, just given that I think if, if COVID has shown anything, it’s shown that if you can be efficient in your care, There’s a huge plus for that.

And ICU care is, a challenge to drive efficiency. And especially when you have this influx of patients, so anything that can make things faster and impact decision-making quicker, which is where we live with our technology. There’s that there’s always going to be a positive for that.

Harry: Well, and I, I do believe like, you know, if there’s more adoption, it means there’s more data coming in, which means analytics get better.

I mean, data has a way of, of getting, you know, giving you more and more to play with all the time. So it just gets richer and richer and its ability to, to tease out interesting, you know, trends or identify like what works over, what doesn’t work.

Shane: Sure. Agreed. Yeah.

Harry: So what’s what, what do you see next for the company?

Shane: So we, we are, are right now focusing on some key technical advancements of the platform. We have a couple of key things with our algorithms that will, when they’re, when they’re launched, provide more insight, not just about what is happening with the algorithm, but why, why an algorithm is elevated, which can hopefully inter.

Impact the interventions that take place with the clinicians. So again, we, we really focus on going deeper and deeper into the why. Not just what may happen, but why is what has happened? Why is the patient in the condition that they’re in right now? What can you, what can you hopefully do about it by, by assessing that information?

So we’re really excited about those. We are really pushing forward on a number of clinical studies as well, which Continuing to advance the science in this space and around using data most effectively is really what we’re all about. And then of course, growth. We, we are really in our growth phase interacting with more and more hospitals on a daily basis.

That that’s really what we’re focused on for, for the short term.

Harry: Well, if you if you actually know why, which would be, you know, just from a human physiology and. Understanding the mechanism of action. You can much clearer figure out what to do next. And then you can actually measure when you do something next, like which one gives you the best outcome.

I mean, it’s so I just look at this as a giant figure, eight feedback loop, right. That, that just gets better over time. You just have to have the data sciences, you know, can sit there and, and crunch through all this data.

Shane: Yeah. Agreed. And that’s, that’s really what we’re focused on. That’s where the name of the company comes from.

Etiometry we’re, we’re looking at the etiology. We’re trying to figure out the etiologies of what is causing a particular condition to better inform the decision-making around the intervention on the other side.

Harry: Awesome. Well, it was great to talk to you today. I know we’re COVID secluded, but. Hopefully, you know, by next summer we’ll, you know, start to get back to normal.

Shane: Yeah. Let’s let’s hope. Let’s. Let’s hope we get it under, under control here pretty soon. And yeah, it was a pleasure speaking with you and thanks for having me on and Look forward to chatting with you again soon. Hopefully.

Harry: Yeah. And I hopefully one of these days we’ll meet in person.

Shane: Yeah, absolutely.

All right. Excellent. Thanks Shane. Thanks. Thank you.

Harry: That’s it for this week’s show, we’ve made almost 50 episodes of Moneyball medicine, and you can find all of them at  dot com forward slash podcast. You can follow me on Twitter at H Gloria Keon. If you liked the show, please do us a favor and leave us a rating and review at Apple podcasts.

Thanks. And we’ll be back soon with our next interview.




Related Posts