HC2HC Event – Andrew Gostine, MD and CEO of Artisight

Bill Russell 00:00:03 Today in health, it, Bill Russell 00:00:04 Another one of our interviews and action. Bill Russell 00:00:05 This comes from the healthcare to healthcare event, which I was a guest Bill Russell 00:00:09 at from the serious health care team. Bill Russell 00:00:11 It was in Montana. Bill Russell 00:00:13 And I was able to sit down with a handful of CEOs. Bill Russell 00:00:16 And I'm going to share those with you here shortly. Bill Russell 00:00:19 My name is bill Russell. Bill Russell 00:00:20 I'm a former CIO for a 16 hospital system and creator of this week in health. Bill Russell 00:00:24 It. Bill Russell 00:00:24 A channel dedicated to keeping health it staff current and engaged. Bill Russell 00:00:28 I hope you're enjoying these interviews and action. Bill Russell 00:00:31 We were able to do these interviews at the health conference, the Bill Russell 00:00:34 chime conference, and now the healthcare to healthcare event. Bill Russell 00:00:37 I've really enjoyed doing them. Bill Russell 00:00:39 , just a reminder. Bill Russell 00:00:40 We're going to get back to our normal programming where I take Bill Russell 00:00:42 a new story, break it down. Bill Russell 00:00:44 And talk about why it matters to health. Bill Russell 00:00:46 It. Bill Russell 00:00:47 We're going to be doing that as soon as the interviews are done we have Bill Russell 00:00:51 done 10 from the chime conference eight from the health conference and Bill Russell 00:00:55 we have five from the healthcare to health care conference so i hope you Bill Russell 00:00:59 enjoy another one of these interviews Bill Russell 00:01:02 All right. Bill Russell 00:01:02 We're doing an interview from the healthcare to healthcare event. Bill Russell 00:01:05 It's a serious invite only event. Bill Russell 00:01:07 And I'm joined today by Dr. Bill Russell 00:01:09 Andrew Gustine, our CEO, CEO, Andrew Gostine, MD 00:01:13 founder Bill Russell 00:01:13 CEO, founder of artist site. Bill Russell 00:01:16 And we're going to talk a clinical automation essentially Bill Russell 00:01:20 is what we're gonna do. Bill Russell 00:01:21 So tell us a little bit about artist's site Andrew Gostine, MD 00:01:23 before we get going. Andrew Gostine, MD 00:01:25 Doug artist's site is it's really an IOT sensor-based automation. Andrew Gostine, MD 00:01:31 To bring automation into the clinical space. Andrew Gostine, MD 00:01:35 You know, as a practicing physician, I was looking out at the different automation Andrew Gostine, MD 00:01:38 tools that were available and I realized most of them were focused on back office Andrew Gostine, MD 00:01:43 types of automation, but the biggest problems we have in healthcare often, Andrew Gostine, MD 00:01:47 not in the back office or at the bedside. Andrew Gostine, MD 00:01:50 And I saw a huge gap in the marketplace. Andrew Gostine, MD 00:01:52 And so developed this platform as a solution to a lot of the problems Andrew Gostine, MD 00:01:56 I was seeing at the bedside. Andrew Gostine, MD 00:01:59 Th Bill Russell 00:01:59 the reason we do it on the administrative side and not the Bill Russell 00:02:03 clinical side is the quality of data. Bill Russell 00:02:06 And so I think it's fascinating that you're getting the data raw Bill Russell 00:02:10 data directly from a camera that's embedded in that clinical setting. Bill Russell 00:02:15 And then that obviously for our listeners is going to create a whole Bill Russell 00:02:17 bunch of questions, but talk about Andrew Gostine, MD 00:02:19 the solution. Andrew Gostine, MD 00:02:21 So you talk about the first part of your statement, you know, Andrew Gostine, MD 00:02:24 the back office automation. Andrew Gostine, MD 00:02:26 Just the first evolution of automation because of all the discreet data Andrew Gostine, MD 00:02:30 that was available, uh, you know, the amount of charges we generated, Andrew Gostine, MD 00:02:34 the, um, different insurance broker that was handling the payments. Andrew Gostine, MD 00:02:40 All of that information was quantifiable and available. Bill Russell 00:02:43 Just brief data easily to work off of. Andrew Gostine, MD 00:02:45 Okay. Andrew Gostine, MD 00:02:46 All of the information I have available at the bedside to Andrew Gostine, MD 00:02:49 me is coming from a clinician. Andrew Gostine, MD 00:02:51 It's a clinician that is seeing. Andrew Gostine, MD 00:02:54 Is talking to the patient is feeling the patients and then putting Andrew Gostine, MD 00:02:58 that information into the EMR. Andrew Gostine, MD 00:03:01 If you don't have the clinician that is there to capture the data, Andrew Gostine, MD 00:03:04 you don't have any discrete data. Andrew Gostine, MD 00:03:07 And so what we saw in the marketplace, uh, really at the Andrew Gostine, MD 00:03:10 bedside was that there was a gap. Andrew Gostine, MD 00:03:12 We didn't have access to the discrete data. Andrew Gostine, MD 00:03:15 So we developed these IOT sensors to structured data for us, putting Andrew Gostine, MD 00:03:21 a camera in the room and developing. Andrew Gostine, MD 00:03:24 To look for events or pieces of information that we can capture Andrew Gostine, MD 00:03:28 in real time and build automation around so that we could remove Andrew Gostine, MD 00:03:32 the human component of data entry. Andrew Gostine, MD 00:03:35 No, Bill Russell 00:03:36 we only remove the component, but actually assist them Bill Russell 00:03:39 because now you take that error away there, you know, they forgot Bill Russell 00:03:42 to put in information about whatever whatever's going on in that room. Bill Russell 00:03:48 That's missing information. Bill Russell 00:03:49 You can't really act on it, but the camera is there. Andrew Gostine, MD 00:03:53 The camera's always there. Andrew Gostine, MD 00:03:54 It's a lot cheaper than a clinician. Andrew Gostine, MD 00:03:56 It doesn't need a bathroom break. Andrew Gostine, MD 00:03:58 It can always be watching, looking for things that we tell it to, to see, Andrew Gostine, MD 00:04:02 and kind of to the other side of that, won't look for things that I don't Andrew Gostine, MD 00:04:06 want it to see, because I don't want to put a system in a hospital that Andrew Gostine, MD 00:04:10 clinicians feel like his big brother. Bill Russell 00:04:12 And that was interesting. Bill Russell 00:04:13 So looking at some of the video clips that you were showing Bill Russell 00:04:16 yesterday, everything's blacked out. Bill Russell 00:04:18 The patient's face is blacked out. Bill Russell 00:04:20 Blacked out, but you're still picking up that data. Bill Russell 00:04:23 You're still processing that data. Bill Russell 00:04:25 So what are you doing around privacy? Bill Russell 00:04:26 Obviously that's one step, but you're doing some other Bill Russell 00:04:28 things around privacy as well. Andrew Gostine, MD 00:04:30 So I think people have to change how they think about a camera. Andrew Gostine, MD 00:04:33 When people think about an IP or security camera, they think of it Andrew Gostine, MD 00:04:37 as the closed circuit TV system. Andrew Gostine, MD 00:04:39 That's recording video. Andrew Gostine, MD 00:04:41 That was a lot of the initial use cases. Andrew Gostine, MD 00:04:44 When we talk about an IP camera, we really think of it as just a light switch. Andrew Gostine, MD 00:04:50 That if you look at those pixels makes a picture, but we don't have to record it. Andrew Gostine, MD 00:04:55 We have elder rhythms that just watch the video feeds in real time. Andrew Gostine, MD 00:04:59 And we'll look for different combinations of pixels that represent Andrew Gostine, MD 00:05:03 objects or events of interest. Andrew Gostine, MD 00:05:05 They will structure some type of data from the event that it's witnessing, but Andrew Gostine, MD 00:05:11 we can then just save the discrete data. Andrew Gostine, MD 00:05:13 We don't have to save the video. Andrew Gostine, MD 00:05:16 So we can just retain the parts of that video feed that are interested Andrew Gostine, MD 00:05:20 to the hospital, but not any of the risks or any of the concern Andrew Gostine, MD 00:05:24 that a clinician might have. Andrew Gostine, MD 00:05:26 If we don't train the camera to see something, it is totally blind to it. Bill Russell 00:05:31 Yeah. Bill Russell 00:05:32 And it was interesting. Bill Russell 00:05:32 One of your users was here and they said their legal team came back and said, Bill Russell 00:05:36 Hey, can we get access to the video? Bill Russell 00:05:38 And the answer was, it doesn't exist. Bill Russell 00:05:41 It goes into the AI engine. Bill Russell 00:05:43 It gets. Bill Russell 00:05:44 It generates those insights, if you will. Bill Russell 00:05:47 And then it's, Andrew Gostine, MD 00:05:49 it's, it's somewhat like time where we live Andrew Gostine, MD 00:05:51 in the present and I don't really have a recording of the past. Andrew Gostine, MD 00:05:56 It's the same thing with our video feeds. Andrew Gostine, MD 00:05:58 We run inferencing on them in real time, but we don't save videos. Andrew Gostine, MD 00:06:03 There are some exceptions for other use cases where surgeons want records of their Andrew Gostine, MD 00:06:07 surgical videos for education purposes. Andrew Gostine, MD 00:06:10 But for the vast majority of our use cases, we don't say that. Bill Russell 00:06:14 So let's talk about some of the use cases. Bill Russell 00:06:17 So people are probably thinking right now, if I had a camera in there, Bill Russell 00:06:21 obviously we're doing tele-health, uh, fall detection, hand-washing clean rooms. Bill Russell 00:06:27 I mean, it really is limitless. Bill Russell 00:06:29 Really? Bill Russell 00:06:29 What if it's really limited by people's creativity of what they can imagine? Andrew Gostine, MD 00:06:35 Computer vision is very powerful, uh, in many Andrew Gostine, MD 00:06:38 ways, a lot better than humans in some ways it's not as powerful. Andrew Gostine, MD 00:06:42 That's the best way to think about computer vision is it's Andrew Gostine, MD 00:06:47 a much more cost efficient way that can capture the same data. Andrew Gostine, MD 00:06:52 As if I put an educated person in every part of the hospital, just Andrew Gostine, MD 00:06:57 collecting data with their eyes. Andrew Gostine, MD 00:06:59 Computer vision can see the same way that humans can see. Andrew Gostine, MD 00:07:03 And if a human can witness something with their eyes and tell me about it, Andrew Gostine, MD 00:07:06 I can most likely train a camera to do the same thing for a much cheaper. Bill Russell 00:07:12 It's really interesting. Bill Russell 00:07:13 So you showed up fall detection. Bill Russell 00:07:15 So I assumed, is there training that needs to go on at each Bill Russell 00:07:18 institution or do you have, are the algorithms already trained to detect? Bill Russell 00:07:22 So Andrew Gostine, MD 00:07:24 it's again, similar to humans. Andrew Gostine, MD 00:07:26 You know, if I teach you at one hospital, how to monitor what it looks like when Andrew Gostine, MD 00:07:31 the janitors are cleaning a room and then I take you to another hospital and Andrew Gostine, MD 00:07:35 you witnessed janitors cleaning a room, you're going to be pretty accurate. Andrew Gostine, MD 00:07:39 They might use. Andrew Gostine, MD 00:07:40 They might have different scrub colors on, but you're going to be able to Andrew Gostine, MD 00:07:43 tell me with reasonable certainty that you're pretty sure a janitors cleaning Andrew Gostine, MD 00:07:46 an operating room or a room or whatever, same thing with computer vision. Andrew Gostine, MD 00:07:51 If I train it at one institution and take it to a second out of the box, Andrew Gostine, MD 00:07:55 it's going to be pretty advanced, but we will do some retraining over a week Andrew Gostine, MD 00:08:00 or two to make sure that it lends the peculiarities of that new institution. Bill Russell 00:08:04 What's interesting. Bill Russell 00:08:05 So I want to talk to you about deployment, but. Bill Russell 00:08:08 The, you talked a little bit about the highest, um, use case, the highest best Bill Russell 00:08:14 use for the first couple of, of, of things that you're gonna use it in your Bill Russell 00:08:19 health system, because the platform can really return almost a complete Bill Russell 00:08:24 return on investment with one or two use cases, but you still have the platform. Bill Russell 00:08:29 And I find that interesting in of itself. Bill Russell 00:08:32 What have you found to be some of the, some of the things Bill Russell 00:08:35 that people have deployed? Bill Russell 00:08:38 The initial. Bill Russell 00:08:39 So Andrew Gostine, MD 00:08:39 there's a, there's a lot of business strategy Andrew Gostine, MD 00:08:41 that goes around technology. Andrew Gostine, MD 00:08:43 And there's a lot of very interesting use cases that, you know, as a physician Andrew Gostine, MD 00:08:47 really interests me, but healthcare is still a business and we have to make Andrew Gostine, MD 00:08:51 sure that we're justifying the things that we're doing in the hospital. Andrew Gostine, MD 00:08:55 So we build business, use cases around some of what I would Andrew Gostine, MD 00:08:58 consider the first best use cases where hospitals are collecting. Andrew Gostine, MD 00:09:04 And we can show this is your baseline performance. Andrew Gostine, MD 00:09:08 And after you put in our fall algorithms, this is by how much you've reduced false. Andrew Gostine, MD 00:09:13 Well, the problem with healthcare is we don't collect data on most things. Andrew Gostine, MD 00:09:18 So if I could build an algorithm that reduced the amount of infections, but Andrew Gostine, MD 00:09:25 you have no idea what your baseline infection rate is, then I can't show you. Andrew Gostine, MD 00:09:29 You made X. Andrew Gostine, MD 00:09:31 You saved this many dollars and it will justify its existence. Andrew Gostine, MD 00:09:34 So all of the first use cases that we recommend to hospitals like reducing Andrew Gostine, MD 00:09:39 falls, reducing pressure ulcers, uh, bringing them up to compliance with new Andrew Gostine, MD 00:09:44 regulations for hand-washing is around things that we know they're measuring Andrew Gostine, MD 00:09:48 where we know they might be sustaining penalties, or they have a large expense Andrew Gostine, MD 00:09:52 to maintain some level of compliance. Andrew Gostine, MD 00:09:55 We go after those first to help them show to their board and decisions. Andrew Gostine, MD 00:09:59 That this is the quantifiable value. Andrew Gostine, MD 00:10:02 And then once the platform is in there returning that value from those first Andrew Gostine, MD 00:10:06 use cases, you can now use it for things that might be more interesting, Andrew Gostine, MD 00:10:10 might provide a greater impact to society, but are harder or more Andrew Gostine, MD 00:10:14 nebulous to quantify in terms of the Bill Russell 00:10:16 value. Bill Russell 00:10:17 So I thought the other thing that was interesting is innovation partners really. Bill Russell 00:10:21 I mean, when I think about the academic medical centers could really use this. Bill Russell 00:10:26 In a lot of different ways that we probably couldn't even imagine ourselves. Bill Russell 00:10:30 And, uh, you talked about sort of incenting that, that environment Bill Russell 00:10:36 of innovators to, can you talk about that a little bit? Andrew Gostine, MD 00:10:40 Yeah. Andrew Gostine, MD 00:10:40 So it kind of a two part answer. Andrew Gostine, MD 00:10:42 So I, I may be the world's best physician, most likely I'm not, but even the world's Andrew Gostine, MD 00:10:48 best physician is not going to think of all of the use cases for this technical. Andrew Gostine, MD 00:10:53 And the goal for this company is not to become the richest company Andrew Gostine, MD 00:10:57 in the world it's to fix healthcare. Andrew Gostine, MD 00:11:00 And the only way we're going to be able to solve as many problems as this platform Andrew Gostine, MD 00:11:04 can solve is if we get everyone to help us, if we crowdsource the ideas and Andrew Gostine, MD 00:11:09 the opportunities, and co-develop the solutions now for the institutions, most Andrew Gostine, MD 00:11:14 often academic or very large medical. Andrew Gostine, MD 00:11:18 That want to help with that and are very interested in helping us bring new Andrew Gostine, MD 00:11:22 solutions on the platform to market. Andrew Gostine, MD 00:11:24 They should totally be able to share and the financial gains from those solutions. Andrew Gostine, MD 00:11:30 And so we have revenue sharing agreements. Andrew Gostine, MD 00:11:32 We have cost reduction terms and all of the contracts where if they help us Andrew Gostine, MD 00:11:36 develop a solution, we will start spitting back revenue from other clients that are Andrew Gostine, MD 00:11:41 using the solutions they co-developed to chip away at the contracts. Andrew Gostine, MD 00:11:45 These. Andrew Gostine, MD 00:11:46 As kind of a way of saying you participated, you helped provide this Andrew Gostine, MD 00:11:50 value to the healthcare ecosystem. Bill Russell 00:11:53 The overused phrase of app store comes to mind, essentially, Bill Russell 00:11:57 you're an app store for computer vision solutions in the hospital. Andrew Gostine, MD 00:12:02 And I think we will ultimately evolve into something that Andrew Gostine, MD 00:12:05 is even beyond the applications that we develop, where people who research. Andrew Gostine, MD 00:12:13 Develop a very interesting algorithm to solve a problem, but have no Andrew Gostine, MD 00:12:17 way of managing a camera network of 10,000 cameras securely behind the Andrew Gostine, MD 00:12:21 health system, firewall with security compliance and firmware upgrades. Andrew Gostine, MD 00:12:26 We can be that portal for them to deploy their algorithms on Andrew Gostine, MD 00:12:29 the infrastructure we maintain. Bill Russell 00:12:31 The nursing shortage is written about a lot at this point. Bill Russell 00:12:35 And I think we're, we're looking at potentially half a million Bill Russell 00:12:39 in the next three years, right? Bill Russell 00:12:41 How does this help in that with regard to that? Andrew Gostine, MD 00:12:44 So we're going after things that nurses have to do Andrew Gostine, MD 00:12:49 now, but shouldn't have to do tomorrow. Andrew Gostine, MD 00:12:52 So in some of the literature I've presented here, we see that nurses spend Andrew Gostine, MD 00:12:56 about a third of their time documenting. Andrew Gostine, MD 00:12:58 So eliminating some of the things that don't really require a nurse to do, Andrew Gostine, MD 00:13:03 like documenting that he or she turned to patient, eliminating that from their Andrew Gostine, MD 00:13:08 workflow is going to make them more. Andrew Gostine, MD 00:13:11 It's also going to burn them out less because they didn't go Andrew Gostine, MD 00:13:14 to nursing school so that they become a stenographer in the EMR. Andrew Gostine, MD 00:13:18 They went to nursing school so they could be at the bedside Andrew Gostine, MD 00:13:20 taking care of the patients. Andrew Gostine, MD 00:13:22 So we're trying to bring the joy back to nursing, eliminate the Andrew Gostine, MD 00:13:25 nonproductive non-patient care aspects of their workflow so that we can help Andrew Gostine, MD 00:13:30 them see more patients, more timely and take better care of patients. Andrew Gostine, MD 00:13:34 The Bill Russell 00:13:35 lastly, I want to talk to you about. Bill Russell 00:13:37 It's deployment because you're not talking massive, expensive care bros, and you guys Bill Russell 00:13:41 even have a mobile solution to move in. Bill Russell 00:13:42 It seems like you could actually ramp this up pretty quickly at a health system. Andrew Gostine, MD 00:13:46 So we, we did that even in the middle of COVID Andrew Gostine, MD 00:13:49 where there was a lot of challenges of getting into the patient rooms. Andrew Gostine, MD 00:13:52 We deployed 1300 cameras across 10 hospitals at Northwestern. Andrew Gostine, MD 00:13:57 In six weeks. Andrew Gostine, MD 00:13:59 So with the mobile systems, we can do that in a few minutes of bringing Andrew Gostine, MD 00:14:03 them into a hospital and adding them to the secure wifi network. Andrew Gostine, MD 00:14:08 When we talk about server infrastructure, for those that have Andrew Gostine, MD 00:14:11 a hybrid or a cloud presence, we can turn on new virtual machines Andrew Gostine, MD 00:14:15 for AI processing and a few hours. Andrew Gostine, MD 00:14:17 So the rate limiting step is typically camera installation. Andrew Gostine, MD 00:14:21 The rest of it is hours to minutes of the bringing new systems. Andrew Gostine, MD 00:14:25 So Bill Russell 00:14:26 people are going to ask me about security, talked about privacy. Bill Russell 00:14:29 They're going to ask about security. Bill Russell 00:14:30 You're streaming this information. Bill Russell 00:14:33 I'm not sure that this information itself has value to someone who's going Bill Russell 00:14:36 to hack it and that kind of stuff. Bill Russell 00:14:38 But if it did what, what's the, uh, what's the information around security. Andrew Gostine, MD 00:14:45 You know, just the, the first things we're going to do to Andrew Gostine, MD 00:14:47 keep this secure is always deployed behind the health system firewall. Andrew Gostine, MD 00:14:50 So the cameras for obvious reasons being in the patient rooms are by definition Andrew Gostine, MD 00:14:54 behind the hospital firewall, but even the server infrastructure or the Andrew Gostine, MD 00:14:59 cloud, we enter and deploy these on virtual machines in our client's cloud Andrew Gostine, MD 00:15:04 tenant, so that we're not streaming this outside of their ecosystem. Andrew Gostine, MD 00:15:09 So the first and second line of defenses are always the. Andrew Gostine, MD 00:15:12 Security measures the VPNs, that directly route things up to the cloud. Andrew Gostine, MD 00:15:17 If that's how they deploy us in terms of the data that we collect by not saving Andrew Gostine, MD 00:15:21 any video or in cases where we do save video, but de-identify, or anonymize Andrew Gostine, MD 00:15:26 the video, we're preventing that risk of any Phi leaving the health system with Andrew Gostine, MD 00:15:33 the data that we generate and structure for them from those unstructured. Andrew Gostine, MD 00:15:38 We send that into their enterprise data warehouses or their EMR is we're never Andrew Gostine, MD 00:15:42 holding our own version of the data. Andrew Gostine, MD 00:15:44 So we're trying to make sure that we're putting this data in a place that is Andrew Gostine, MD 00:15:48 super safe and controlled by the client. Bill Russell 00:15:51 Andrew, thanks for your time. Bill Russell 00:15:53 We're really excited to solution. Bill Russell 00:15:54 I'm looking forward to seeing what you guys Andrew Gostine, MD 00:15:55 do. Andrew Gostine, MD 00:15:55 Yeah. Andrew Gostine, MD 00:15:55 Thank Andrew Gostine, MD 00:15:56 you. Bill Russell 00:15:57 Don't forget to check back as we have more of these interviews Bill Russell 00:16:00 coming to you, that's all for today. Bill Russell 00:16:02 If you know of someone that might benefit from our channel, Bill Russell 00:16:04 please forward them a note. Bill Russell 00:16:05 They can subscribe on our website this week, health.com or wherever you listen Bill Russell 00:16:09 to podcasts, apple, Google, overcast, Spotify, Stitcher, you get the picture. Bill Russell 00:16:13 We are everywhere. Bill Russell 00:16:15 We want to thank our channel sponsors who are investing in our mission to Bill Russell 00:16:17 develop the next generation of health. Bill Russell 00:16:20 VMware Hill-Rom Starbridge advisors, McAfee and Aruba networks. Bill Russell 00:16:25 Thanks for listening.