
Reducing Documentation Burden Through Real-Time Data Capture with Dr. Stephanie Lahr of Artisight
Dr. Stephanie Lahr
AI isn’t magic — it’s science powered by quality data. Dr. Stephanie Lahr, Chief Experience Officer of Artisight, sits down with us to explain how data, computer vision and ambient sensors are transforming patient care. She reveals how Artisight helps clinicians reclaim time by automating documentation, improving the quality of data and restoring focus to human connection. Stephanie also shares her journey from internal medicine physician to healthcare technology leader, emphasizing that reducing burnout and elevating care begins with smarter data collection.
I'd rather read the transcript of this conversation please!
In this episode, Dr. Stephanie Lahr, Chief Experience Officer of Artisight, shares how AI and ambient sensors are transforming healthcare. She explains how Artisight automates documentation, improves data quality and empowers clinicians to focus on patient care.
Key Takeaways:
(03:04) Stephanie’s journey from clinician to digital health leader started with a hurricane and an EMR revelation.
(08:38) Even in the time of Hippocrates, medicine has always relied on data through observation and testing.
(12:08) In healthcare, patient care comes first — data entry comes second.
(17:40) Computer vision captures real-time patient data without burdening clinicians.
(21:30) Virtual care uses real-time support without recording or storing sensitive data.
(27:39) High-quality insights depend on high-quality data — it’s a continuous cycle.
(31:20) AI success in healthcare requires collaboration between clinicians, data scientists and system leaders.
(34:41) Precision medicine improves treatment, but restoring humanity to care is what truly drives innovation.
Resources Mentioned:
Dr. Stephanie: [00:00:00] We have a massive high quality dataset of, consistent radiologic images, which then can be used to train algorithms. To help us. Right. And I think that's a key element that everyone has to realize around AI is it's not magic. It's another form of science and math, and it needs training.
Anthony: welcome to another episode of Data Masters. I'm your host, Anthony Dayden. Today I'm joined by Dr. Stephanie Lar. The Chief Experience Officer at Artis, [00:01:00] an innovator in the intersection of healthcare. Artificial intelligence. Dr. Lara brings a unique perspective as a physician who's championed transformative digital technology implementations.
Served as a CIO and A-C-M-I-O at Monument Health, and she's really known for pushing the envelope in healthcare technology. At Artis site, she's helping revolutionize patient care through their smart hospital platform, leveraging ai, computer vision and voice recognition to untether physicians from data collection tasks and put patient care back at the center of medicine.
Now we spend a lot of time on this podcast talking about how we use and improve the quality of data, but in this episode, I hope to kind of explore innovations and how we capture and gather data, healthcare and our decide in particular, our interesting ways [00:02:00] to explore this important area through the work that they're doing, and particularly what Stephanie's doing.
In redefining healthcare experiences, this has the effect of reducing clinician burnout, building a smarter and more responsive healthcare system. So Dr. Lahr, welcome to Data Masters. I.
Dr. Stephanie: Well, thanks so much for having me. What a great introduction and summary of what has become my most recent part of my career.
Anthony: let's talk a little bit about that actually, because I believe you are the first medical doctor on the Data Masters, podcast, and that's obviously. Atypical for data practitioners. so maybe if you start a little bit just for context for folks and share a little bit about your background and how you ended up on a data podcast.
Dr. Stephanie: Yeah, well, Hopefully I understand it to even be able to explain it. and certainly an honor to be the first, clinical, [00:03:00] physician on your program. I'm sure I will not be the last. you know, I'm an internal medicine physician by background and training. I practiced as a hospitalist. so. For those who may or may not be as familiar, I spent all of my time in the hospital every day caring for acutely ill patients. and when I went to interview for that job, actually, I met with the CEO of the health system and I had just gone through kind of an interesting experience in my final time of my training. We had a hurricane, in Galveston, Texas where I was finishing my training. We had recently gone through an EMR implementation, had all the bumps and bruises from that experience, but had become kind of a believer, that yeah, you know,I'm used to this.
And then we had this hurricane and really became a believer because what two weeks before was, would've been, is now underwater. If we'd have been in a paper world. As we started to recover from that disaster and our patients and families were recovering from that, I had [00:04:00] an ability to be able to help them with a tool set that honestly, a year before when we were, before we had gone live, just wouldn't have been possible.
I was e-prescribing medications. I could see their records, I could share their records, all kinds of powerful things. So I thought, well, this is definitely improvement. We need to keep doing this. We need to keep working on this. And I met with the CEO of the health system and I said, Hey, what are you? What are you doing in this space for an MR? And he was like, well back it up. Like, are you a doctor who wants to use an EMR? Because this is a new experience for me. And I said, well, you know, I mean they have their challenges and this was, almost 20 years ago now. And I said, but this is, I can definitely see this is where things are going.
And he was like, well, that would be, that's great and maybe you can help others along the way. And that started an informatics journey for me, at a time when I didn't even really know what informatics was, but I got involved as a physician saying, here, how can we bring these things together? I was lucky enough to work for a CIO in that [00:05:00] organization, who was technical, very technical by background, and sort of took me under his wing to help me understand the technical nuances of some of the way things worked.
I got additional education and training in informatics. And started really moving my career into this, as you mentioned, kind of intersection of technology and healthcare delivery, and found that I was really passionate about being able to bring those things together and could see the opportunity that presented itself as we moved beyond sort of, EHR and Healthcare Tech 1.0 and moving into the more advanced opportunities.
And so my career sort of. Took a shift and I, started focusing on that. And then at another organization, another CEO said to me, Hey, our CIO is leaving, who is my boss at the time. And he was retiring and he thought, well. With this intersection becoming as important as it is, maybe we should have a clinician leading these teams.
Maybe you wanna do that. And I [00:06:00] said, yes, I would love to be the CIO at this health system. And, even though I wasn't even really for sure exactly what that was gonna look like and did that work with Monument and what I loved about that role. Was it broadened the horizon of what I was able to do beyond the CMIO into really the entirety of the ecosystem of healthcare technology, got me more involved in the data science aspects of it.
While those teams weren't necessarily all reporting directly to me, certainly I was supporting them. and then fast forward to,the exciting things that I then saw. Andrew Gossing, our CEO here at Artis site doing, with even more advanced technologies and the opportunity to, really change healthcare delivery in a positive way for our clinical teams.
And so two and a half years ago, I made a jump again to another area where I had not done that work before, but had, passion and excitement and enthusiasm to see how we could make things work. And here we are.
Anthony: Yeah. And I think that, pulls on an important [00:07:00] theme and thread of, and something we've talked a lot about on Data Masters, which is this idea that fundamentally every business is at its core at data business. And that is sort of, I think. Easy and obvious for people when we think about a software company, or maybe even if you think about, it's like manufacturing and things like that, where you're like, oh, clearly data is really important.
but I do think. That's less obvious for something like healthcare where the feeling is that, well, the point of healthcare is to have a personal interaction with a doctor. or at its extreme, like, if you've broken your leg, they're setting a bone. I mean, that quite literally is not, I would think a particularly data oriented experience.
It's about getting you healthy. and you even sort of said this, under your breath, like most physicians. Don't love using EMRs and doing data entry, and maybe even patients don't love this experience of interacting with their doctor and then [00:08:00] having them turn and they're back to you and start typing into a computer.
But before we get into the specifics of it, maybe share a little bit about why healthcare really is a data. Driven business or at minimum a data-driven experience and why it's so important to think about gathering and capturing data and you know how that's both different and also in a sense the same in healthcare.
Dr. Stephanie: I mean, maybe I'll jump philosophical and go super old school here for a minute. And maybe this is because my 12-year-old and I have been doing, ancient history research. But when you look back at even Hippocrates, I mean part of what made Hippocrates a differentiator. Was he realized that the science and precision of medicine was about observation, testing, understanding, I mean. that's really what the whole purpose of data is, right? Is, capturing our [00:09:00] observational or experimental, ideas,and tests and then analyzing those with rigor and figuring out how to move forward. So in the moment, even if you leg is being set in an emergency room. That at that very second may not be, a data-driven sort of experience. But how, what and when to do exactly what you need is absolutely a data-driven experience. and we are now in an era of healthcare where. We can capture and collect and analyze huge amounts of additional data, all kinds of data that we didn't even have, access to before. Whether that's precision medicine kinds of things in genetics, whether that's observational things about how a patient responds,whether that's lab, traditional lab work and all those things.
And so really as we try to move the needle on how to help people maintain health. And how to [00:10:00] solve disease. Those are scientific questions that need data and analysis to continue to move us along in improving the answers to those questions. I think the reason that we see, physicians, clinicians, even patients.
I feel the rub of, but I don't know how much I love that. is less about the fact that they aren't interested in the outcomes of that. They absolutely are. I think it's because of the way that we've brought it into the workflow, hasn't been as elegant as it could be. and now as our hunger for data rapidly expands. We haven't rapidly expanded the tool set that we have at our, disposal to be able to influence that process and support that process.
Anthony: and, to be snarky about it, we've, only reached the level of expecting doctors to be data entry professionals, meaning, data entry technicians even worse. So, that's [00:11:00] part of what causes this problem. We're asking people who, fundamentally want to interact with patients, quite literally lay hands on them, to turn those hands to a keyboard and start typing stuff and, and asking them to document all kinds of what seemed like minutiae and things that, you know, like, that are important, from a data perspective and, but are not important to their providing of care.
Dr. Stephanie: not in that moment. Totally.
And, and, and and goes way beyond just the physician, right. I mean. Nurses have as much or more of a documentation burden, as physicians do. My husband is a physical therapist, even in private practice and comes home at the end of a day saying, well, I didn't quite get to all my documentation today.
Dr. Stephanie: but again, we're hungry to capture this information. The other thing that's ironic about, the element that you mentioned around making them, information gatherers and documentaries. Humans aren't good at that,
whether you're a [00:12:00] doctor or a nurse or whether you are, an associate at a department store. It doesn't really matter as humans, data entry is not something we're fabulous at. And that's, and actually that's where we see a lot of errors for a variety of reasons. time, the user interface, the, you name it, there are a variety. Variety of things. And then in clinical care. You get to the point that you made, which is the focus at the moment is on delivering of the care.
Therefore, for sure secondary is any kind of data, capture that needs to be done. And there we now have a, juxtaposition of two things that are in conflict with each other because they're both important, but one of them is definitely going to take second. It's going to be the thing that as humans, we're less good at to begin with, and now I'm gonna delay it and sort of make it second tier.
Because honestly, at this moment, making sure that you're getting the care that you need is my focus.
Anthony: And is [00:13:00] more important,
Anthony: let's make this. Really kind of practical for people. can you share a really practical example of how, you guys are using computer vision, voice recognition,to actually achieve this, at a very practical, maybe almost like, since I think. Many listeners have been patients, I suspect [00:14:00] relatively few have been doctors, but walk it through from the perspective of how a patient might experience it and kind what's happening almost behind the scenes to make this experience real.
Dr. Stephanie: I'll use an example in the operating room. again, our CEO is a physician. He's an anesthesiologist, and one of the first, when he decided, to really dig in to work on this. you solve your own problems first, right? And so he looked at his own environment and said, what are some of the things that are a challenge here? So in an operating room, I. Which is a very complex environment, where, making sure that things happen in the right sequence and all of those things is really important and where data and process can add a huge amount of value, but they need to be workflow driven. so one of the first things that happens in an operating room during a new case is the patient comes into the room.
Well, that seems obvious. what's interesting is that we know that both from a process flow perspective, so what the health system cares about as [00:15:00] far as managing where patients are and how long they take. So from that viewpoint, it's important to know how long a patient is in the room for any kind of case. But clinically, there are also quality related elements that we know when a patient is in an operating room, which is a high risk environment. The longer they're in there based on different, variables that are going on, the more risk there is potentially. So we, a piece of data that we really want to capture is. Is the patient in the room and how long are they there? And even better, how long are each of the stages? How long does it take before the patient goes to sleep? How long does it take when we wake them up? How long from the time they're aw awoken to the time that they go to a recovery room? Those are all important pieces of information.
Historically, our strategy around documenting that, it used to be a couple of people sat with paper maybe right where they were, and so I'm talking to you, but I'm just. Scribbling down some notes and then we kind of formulated [00:16:00] and made sure it all looked good. later we moved to electronic, which was good, so that we didn't have to worry about bad handwriting or, things getting, miswritten. but so we said just click this box. Like that will be so much easier. You'll love it. You just have to click this box. Usually the computer is across the room, or at least across the way, and again, not the primary focus when I'm bringing you into the room and getting you settled to quickly run over and do a real-time data capture of when you entered the room. So what happens? Well, people do the best they can. They get the patient settled. They maybe look up at the clock. They're like, oh, it's 10 47. Okay, fine. 10 minutes later when they get a chance, run over to the computer and they're like, was it 10 40? No, 10, 10 57. Yeah, it was 10 57. And so 10 57 goes into the chart and everybody moves on with their lives. The problem is that's inaccurate data. it's was not collected truly in real time, which is where we would see the most advantage from it. And the [00:17:00] reality is it's not the fault of the clinician. We didn't prioritize and give them the right tools for how to do that. So. How, what if we could use computer vision to train an algorithm, just like we do with, driving cars. We train it to understand the environment. An operating room is actually a relatively limited environment where we can constrain some of the variables. We can teach the algorithms what it's seeing and what it's not. What is a patient. What isn't a patient? What is a hospital bed? What is not a hospital bed?
What is in the room? What is not fully in the room? And we can then say. With computer vision, Hey, we've taught an algorithm to identify that patient's in the room. Let's take that piece of data and send it to wherever it belongs. In this case, the EMR. And now we've got great real time, high quality data that represents the patient's experience, wasn't collected on the back of the clinician who's trying to manage the care [00:18:00] of the patient. And everybody moves on with the best possible information. If you think about. The number of elements in any kind of hospitalist stay in particular, and I, and the inpatient stay, because of its complexity, whether it involves a surgery or not, is definitely a ripe opportunity for all of this because there's so many things happening. If you think about all of the areas where we might wanna collect little pieces of information like that, that over time and collected with you. Other elements in congregate or aggregate can help us improve processes. We really have an opportunity to go in and leverage things either that we heard. Or that we saw or leveraging things like ultra wideband technologies, knowing where things are in space. We saw it move from here to here. maybe that's a combination of we saw it move with a tag and we saw it with a camera. Maybe it's a combination of, we heard this said, and we saw this with a camera, so it's some constellation of using ambient sensor technologies to. [00:19:00] Uncouple the sort of data entry elements of relatively simplistic things that need to be captured. and then the sky's the limit. I mean, over time we'll be able to move toward much more advanced things, but even peeling off five of those very simple box checking tasks to a clinician that has 50 of them to do will be helpful and will help their work, will help the quality of the data and will help the patient.
Anthony: Again, I think that's,brilliant because you'retaking away the, the annoying bit of the, and to be clear, the data entry piece and leaving the actual work behind. There's another element of that I think is really, exciting and interesting, which is a sense that this is work that people are good at.
if you told a person, stand in this room and record when the patient came in and record when this happened, they can do that. The problem is, I. No hospital is gonna afford to put a human being in every single operating room. But, and to your point, we can train machines to do these. At least [00:20:00] today, we can train machines to do this.
And I think this is a general truth, which is increasingly in ai, we're finding tasks that previously we imagined only people could do. We can now train computers to do them, and then we can turn them over and then we can afford, in a very literal sense of that word, we can afford to do them more readily.
so this all sounds great, but I imagine that there have been some challenges associated with introducing AI powered technology from the perspective of the provider. I'll ask in a moment from the perspective of the patient, but. What are the reactions or, the challenges associated with getting doctors and nurses and hospitals to think about this approach versus, just click the checkbox or the other normal strategies?
Dr. Stephanie: I think foundationally, the first thing that you hear about, or you might think about is, well, we're clearly introducing cameras and speakers, and we're watching and listening to people. And [00:21:00] anybody who's watched any sci-fi fu, you know, futuristic thinking movie is like, well, wait a second, that can't be good. and so a lot of it is initially about the conversation about what is the purpose of that technology? What is it doing and what is it not? For example, it's not recording anything. There's no visualization that can be reproduced. After any of this, in some cases, in many cases, there's not even buddy who's watching.
Now, if we leverage this same technology as your virtual care, in your virtual care continuum, and you've got a nurse on the other end of that camera supporting a patient, well sure that nurse is watching and seeing, but again, there's no recording, there's no terabytes of a data center somewhere.
Where somebody's gonna be able to reproduce something that happened. and again, actually both patients and staff,are concerned about things like that. the next piece is, well are, are you gonna use this only for good? [00:22:00] And I think one of the things we can say at our site, being founded by clinicians and driven by clinician leaders, we are only here to help our clinical people. Make it easy to do the right thing. We know at their heart and soul that is what they are there to do. When those things fall apart, it's usually process related, and so if we can improve process. In order to support that. And so then it's really a dialogue about, tell me about some of the things that create friction for you and let me help figure out if that's something that we could unload by leveraging these kinds of technologies.
And you can pretty quickly get people past some of the idea of thinking about some of those sensors being in the room. So that's first. Then I think there's the whole AI. Side of everything right now, it's become a buzzword. It's a really broad topic. One form of AI is not the same as another. and so clinicians I think are particularly sensitive right now to this [00:23:00] idea that we're, potentially wanting to, I. impact their autonomy and their decision making and maybe drive,recommendations or directives at them that they don't feel comfortable with because they don't know where that data came from and they don't know, that it hasn't been, adequately brought into their workflow or their education for us.
We're not starting there. Right. We're starting with, could we click the box for you that says the patient's in the room. No one's gonna say, man, my life in Soul is about clicking that box. So it allows us to start a conversation and create,a sense of comfort, and experience with a new kind of technology that then we can build and learn on together and take to those more advanced steps.
Because right now the, we're not trying to solve the problem of telling you what the diagnosis is or. How to treat that cancer. That is not the goal. We want you to think about that and we want to give you as much time and cognitive focus to [00:24:00] do that. So let us unload some of these other things and the conversation usually really quickly goes to, let me tell you about the 10 things I would love for you to do.
Anthony: Right. No. What I love about that is in a good way, like to your point about not recording the video and storing it. At a hard drive in the cloud or whatever,the thing that's watching the video, that's making decisions about, in your example, does the patient arrive or leave or, is in fact a machine.
So in that sense, I think I. you feel in a way more comfortable with it versus there was actually a person in the room recording the thing, or like yet another person in this invasive experience. And then very much to your point, from the, clinician's perspective, focusing energy on. You can do your job and not do data entry.
And I think there's a lesson there and a way for any industry or anybody, the way to get people to think differently about data entry is to have them not think about data entry, like focus on the job and not focus [00:25:00] on the data entry. As data people, we often center our experience around we want the data, so of course you should do the data entry or you should be recording the metrics or whatever it is, and it's no, actually what you should be doing is the job and the data will come.
As a natural, output of that. So I wanted to make sure we talk about patience since as a guest. Again, most listeners are probably patients. and I would also imagine that many listeners and. Patients have turned to AI and chat GPT and tools like it to, make sense of, medical data and medical diagnoses.
and maybe expanding the aperture slightly in the context of this conversation, just thinking a little bit about what are. The limits and opportunities as it relates to AI and healthcare, clearly can make a big impact on, collecting data. But I'm just curious from your perspective, especially as a physician [00:26:00] yourself and obviously some very capable and,in the area of data and ai, what do you think are some of the, opportunities and limits from a patient perspective?
Dr. Stephanie: Yeah, I mean, I think patience. Want humans. We've all, I get to your point, we've all been, a patient at some point or will be, or our family members. when we are in that setting, we want to feel like we reliably are getting high quality, efficient, affordable, compassionate care and. Patients I think are actually. Maybe even more excited about some of this stuff than on the clinician side. Just from the standpoint of, again, to your point, everyone is using this in their, are starting to dabble in using this in their day to day. My grandmother, who's in her nineties, who is working on some final elements memoir book for the rest, for the family.
Is [00:27:00] using some chat GPT stuff to sort of refine, her writing. So these things are,pretty mainstream. I think that people are comfortable with them to an extent. So they see it as an extension of like, well, yeah, I mean, why wouldn't healthcare use it? I think they want to see us use them. Responsibly. I think they want us to be transparent about where they are being used and where they're not. But again, if it's improving their quality, improving their experience, I think, we generally see, a really favorable and almost excited,approach from the patient side as far as, what are the opportunities. Again, honestly, in many ways the sky is gonna be the limit. one of the things that I really feel strongly about right now, and this kind of goes way back to the beginning of our conversation, is the more data we can crunch, the more insights we can get. That data needs to be high quality in order for those insights to be high quality. And [00:28:00] so it's this sort of, circular process, right? Of doing what we can with what today is a vast but challenged data set. For a variety of reasons, which is a whole other podcast conversation. and, doing something with it, gaining the experience, figuring out how to, harness that the best, working on the tools. Using some of the same tools to improve data collection so that then we can put higher quality data into some of those same kinds of algorithms with, a new and maybe elevated sense of what we can get out of it, because we're more certain and confident in what's going into it. And I think it's,gonna be this iterative process for, many years of. Clinicians and I think this is super important when we're talking about care delivery, clinician driven and clinician, validated tools and that we, but that there are again, our. So many [00:29:00] opportunities for these tools to come together, whether it's s it's gonna be the basics right now.
You see so much en emphasis right now around NLP and helping us create notes and do things like that. Yes. Awesome. That'll give us higher quality data out of the gate as well. We'll use some of these other technologies we already know about. tools that are being used for clinical decision support, analyzing CT scans, imagery, and those kinds of things where we've got a massive high quality dataset.
That's one of the reasons that has really taken off. We have a massive high quality dataset of, consistent radiologic images, which then can be used to train algorithms. To help us. Right. And I think that's a key element that everyone has to realize around AI is it's not magic. It's another form of science and math, and it needs training.
It needs us to feed information to it and to guide it. And so as I think, [00:30:00] again, really it's very exciting to think about all of the different elements in a stepwise graduated fashion that we're gonna be able to do in a, what I believe will be synergistic,opportunity over the coming decade.
Anthony: Totally agree. and there's, a lot there. High quality training data or as we increase the amount of AI we use in any industry, IT forces back on that industry and that, user, the quality of the data. 'cause if you're training with bad data, you're gonna get, bad output.
One of the things I think is also, I just. Hold back something you said at the very beginning. there's an element of, translation, I think that's happening, language translation that,physicians, can often, they almost speak a different language than the patient. and I think,what these technologies are really good at is like that language to language transition.
It's not English to French, it's. Physician to patient or patient to physician. and I think that's also true in the data space. [00:31:00] Like as data people, we use all these, crazy words and terminologies and heaven forbid you layer in statistics with it and all of a sudden you are speaking a completely different language than your business partner.
I think there's an opportunity to think about using these technologies to bridge that divide.
Dr. Stephanie: completely agree. And I think that's why, the success that we're gonna see with artificial intelligence is gonna come from. Collaboration of experts from multiple different vantage points. 'cause the data scientists aren't gonna be able to do this by themselves.
The clinicians certainly aren't gonna be able to do this by themselves either. It's a combination of bringing in the clinicians, the health system leaders, the data scientists who all have an area of expertise and a knowledge base of what needs to happen to find future success.
Anthony: So in that spirit then maybe to, leave us, with a view to the future. cast your eye forward, I don't know, five, 10 years into the [00:32:00] future. a, a perfect world in the future where. AI technology is mainstream and widely adopted. Doctors and patients have access to large quantities of high quality training data.
And like, what does healthcare look like in the future in this AI driven world? And this is your opportunity to, like paint the vision for a perfect world.
Dr. Stephanie: I mean, to me, the whole reason I sit in any seat in this sort of healthcare, It, juxtaposition space is to bring the joy back to medicine, to healthcare. being a patient is rarely a joyful experience. It's a complex experience. it's a stressful and potentially fearful, experience. It can be a life altering experience and. the art of healthcare. The art of medicine has always been the ability [00:33:00] of clinical people to use science. To support people through those challenging times. And in order for them to do that, they have to have an inner joy about the work that they're doing. everyone starts with it. Everyone starts nursing school, PT school, medical school, you name it. With this idea of the ability to connect with humans and improve their life in some way, even if it's the end of their life and. If that erodes our ability to successfully manage health and care gonna be an impossible, an impossibility. And so we've gotta get that back to the center. And interestingly, I think advanced technologies, levering, leveraging ambient sensors and artificial intelligence is the way to get the humanity back at the center of healthcare.
Anthony: [00:34:00] I love that. 'cause that's ironically, decidedly not data answer to the question. It's a uniquely human answer to the question. And I guess it makes perfect sense that given that you are at, at your core of physician and about providing care, it's really about making that a human experience and not.
An AI experience, and yet to your point, if we can drive that and offload work, from humans into the machine, it actually in a way increases our -humanity. And that's actually, I think, a very positive vision and arguably when I don't, frankly don't hear that often, so I appreciate you sharing it.
Dr. Stephanie: it's what gets me up and going every day. I mean, there's other fun stuff too, right? I mean, precision medicine and all these different things that are gonna allow for highly specific, treatments for patients that will allow them to not have to go through three different things before they find the right thing.
And, you know, I mean,all kinds of really fun stuff from the science side of it. But, what keeps me charged is this humanity piece of the, you [00:35:00] know, keeping that at the core of what we do or bringing it back as we've sort of gone a bit adrift.
Anthony: Well, Stephanie, thank you so much, for joining us on Data Masters. This was definitely a unique perspective and hopefully a valuable one.
Dr. Stephanie: Well, thanks so much for the opportunity. Would love to come back if I'm ever asked.