The Untapped Power of Predictive Analytics in Hospitals

Transcript

This has been generated by AI and optimized by a human. 

Show ID (00:04):

The power of data is undeniable and, unharnessed, it's nothing but chaos.

(00:09):

The amount of data was crazy.

(00:11):

Can I trust it?

(00:12):

You will waste money.

(00:14):

Held together with duct tape.

(00:15):

Doomed to failure.

Jess Carter (00:16):

This season, we're solving problems in real time to reveal the art of the possible, making data your ally, using it to lead with confidence and clarity, helping communities and people thrive. This is Data-Driven Leadership, a show by Resultant. 

Hey guys. Welcome back to Data-Driven Leadership. Today you're getting into one of the biggest shifts happening in health care and data right now. If you have been listening for a while, you know we love digging into how data shapes real people, real operations, and real decisions across every kind of organization. Today's topic brings all of that together in a meaningful way. Over the last decade, health systems have invested heavily in building centralized data assets packed with clinical operations and financial information. These systems were designed to give leaders clarity and control. Yet, many teams are still relying on reports that only explain what happened without helping them anticipate what comes next.

(01:12):

In health care, when patient volumes, staffing demands, and quality outcomes can change by the hour, prediction is becoming essential. It is the difference between constantly reacting and being able to make a confident, proactive decision that supports both the care teams and the patients. We're joined today by Tony Pastorino, commercial health strategy lead here at Resultant. In his previous role, Tony spent years overseeing information systems at IU Health, one of the largest hospital and healthcare networks in Indiana. That experience gave him a front-row seat to how organizations move from basic reporting to data that truly drives decisions and meaningful outcomes. He's here to break down how predictive analytics can strengthen operations, support clinicians, accelerate research, and improve the patient experience from the moment someone walks through the door. Let's dive in. 

Tony, welcome.

Tony Pastorino (02:03):

Thank you. Thanks for having me, Jess.

Jess Carter (02:06):

I am super excited to have this conversation because we've had a few conversations about health care and data, but we really haven't broken the surface on a really deep conversation about how hospital systems or health entities could be leveraging their data or already are leveraging their data in exciting new ways that change the patient experience for the better. Pretend you still worked in one of those entities and I was on my first day there. Can you help orient me to what exactly does data management, data usage, the value proposition of a health entity look like? Why does it matter?

Tony Pastorino (02:42):

I've worked in three or four different industries and by far the healthcare provider healthcare data is the most complex set of data that I've ever worked with. There's so many pieces and parts between if you think of—everybody thinks clinical data, so my medical record and all that data there—that is a big part of it, but there's a bunch of other clinical systems that are involved. There's a ton of business systems involved. All of the data that's in your medical record that then translates into a actually signed off set of information that we use to get reimbursed on and to bill on and all that kind of stuff. So it's a lot of pieces and parts. If you think about, as a patient, all this different coding that we do in health care, you come in and you get a set of diagnosis codes and then you move to being treated and now you have procedural codes and then now you're gone and now we have to get reimbursed or we need to bill you. Now it's some combination of those codes or some new codes that get involved.

(03:43):

So there's a lot to it. I think probably the cleanest industry I've ever worked in is consumer packaged goods. You're doing manufacturing, supply chain things. There's a lot more variables here. So the first thing I would try to do, and it would take more than a day, is to start to get folks used to what that whole dataset looks like and how do all these pieces interact. And on top of that, healthcare data is super private. So you can't just willy nilly go look at stuff and I'm going to go see about this and do some research over here. We have to be very cognizant when we work with healthcare data about the privacy factor that's there for our patients.

Jess Carter (04:19):

That's the HIPAA piece, is that right?

Tony Pastorino (04:21):

Correct.

Jess Carter (04:21):

What is HIPAA-protected? What is not HIPAA? Is there a clear line?

Tony Pastorino (04:25):

It's pretty clear. I don't remember off the top of my head. There's 17 or 18 data fields that you can look for to say this is protected data, but if you think anything that could infer to me that I know who you are and I know what's wrong with you or what kind of treatment you're seeking, it's probably HIPAA-protected data.

Jess Carter (04:46):

Oh, interesting. So what you're saying is most people have a portal of some kind and they log into it and they can see their results or their last visit or a summary or something or their billing. You're basically saying there is so much more beyond that portal that's your scheduling system and your billing system and your insurance, whatever. There's a thousand other systems and you'd be orienting people to the complexity that is those systems. Is that right?

Tony Pastorino (05:12):

Yep.

Jess Carter (05:12):

So then those systems are, so if I'm used to some level of IT, those are source systems. Does every hospital or hospital association have a giant data lake? Are they doing analytics or is this new in health care?

Tony Pastorino (05:27):

If we look at most health systems today of any size, we probably still have some smaller health systems that have a single medical record system and maybe a single finance system, single HR system. They may not have everything all pulled together yet. They can hit those source systems directly and kind of meet their needs. Most health systems at this point in time have put together what I'll call an enterprise data lake where they're pulling in that meaningful information from the medical record system. They're pulling in meaningful information from their billing system. They're probably pulling certain data from their supply chain system into the mix there. They are definitely pulling data in from their workforce management solutions, everything from HR-level data about their employees, what are they licensed for, all that kind of stuff, all the way to when did nurse Susie clock in and when did she clock out?

(06:22):

So think of those are all there. There may be some clinical data that is enhanced, so it's outside of the medical record system, but it provides some additional in-depth detail that might be pulled in. So that might be another clinical dataset that gets pulled in, but most places have pulled all that together into a consolidated data store somewhere and then put, likely, a few layers on top of that. So if you can imagine all this raw data that I just talked about might not be super useful to somebody that is not a subject matter expert or knows every in and out of every one of those source systems. So what we'll often do from a data management standpoint is we pull that together and then we sit with subject matter experts and we engineer a couple layers and data in there that are more usable and more accessible. And then that gets us to, if I'm looking for financial-specific things around health care, I might go to this layer over here. If I'm looking for more clinically-focused things, I may go to this layer over here. So it's really getting that data into something that's useful for data analysts or knowledge workers within the actual operational areas in a hospital.

Jess Carter (07:35):

Okay. People in leadership, they're trying to operate a hospital might be looking for things like how successfully are we getting reimbursed for codes that should require reimbursement from insurance providers or something, like, are we actually making ends meet, if you will, by getting those reimbursements that we need. Or are we starting to see more elective procedures than we expected in the past? Is our supply and our demand aligned? Do we have enough doctors to see enough patients, et cetera. Then there's the doctors and the nurses who are actually maybe doing some clinical like, hey, when we see these kinds of patients with these kinds of diagnoses, how are their outcomes related to their, what is it called, their standard of care? So the way you traditionally treat them when they come in with that diagnosis or something. So you're saying this data lakehouse could meet the needs of all these different personas who really want to use sometimes overlapping data or in different ways to solve different problems. Is that right?

Tony Pastorino (08:30):

It is. Think of the big health system. There's been all this over the years sort of acquisition and consolidation, mergers and acquisition stuff within health care. So I may have a healthcare system that has 20 hospitals in it under the umbrella of a one-name healthcare system. It is very likely the case that I don't have one medical record system, I have five across those 20 hospitals. I may also have two different billing systems. I may have two different supply chain systems. If we think about the most basic analytics of, hey, put a dashboard together, like you were saying, put a dashboard together for me on something around reimbursement or around the patient flow that I have at this particular hospital on any given day, whatever it might be. If I'm trying to pull that from five different places, you can imagine I probably have five different trend reports on the same thing you asked for and they all show a different trend, which doesn't make even historical reporting very useful to anybody. So by getting all of that stuff pulled into a single store and us being it, we know that this field in this EMR is the same piece of data as this different field in this EMR. We can pull that together in one spot and then when analysts go into run things on it, they're at least running off of a single source of truth. So I don't have five trend reports on length of stay that all have five different answers to it.

Jess Carter (09:57):

Okay, and when you said EMR, what is that?

Tony Pastorino (ten:00):

I'm sorry. The Electronical Medical Record system.

Jess Carter (10:02):

Thank you. Okay. Alright, so then let's talk about this sort of move towards predictive analytics and I think we have to start with what do you mean when you say predictive analytics?

Tony Pastorino (10:14):

So it can mean a few different things and I'm going to try to visually do this with my hands. If I think of a maturity curve here, so the first thing we talked about, if I'm looking at data and analytics within health care, I've got this base thing down here, which is getting all my data together. We talked about that. That's getting the enterprise data lake together. Then typically the next thing that happens is I start to do descriptive analytics over that data. Meaning, hey, I can paint you a really cool picture of what happened yesterday and last week and last month in the last 720 days. I can show you all that. I can show you these trend lines. I can really get good at doing that kind of reporting and analytics. The next piece we jump into then is there's sort of two tranches of predictive analytics that I'll go into.

(11:02):

One is what I just call operational predictive analytics, which is, okay, this is not going to improve or harm anybody if I do it. It's around how do I predict how long someone's going to be at the hospital? How do I predict how many people are going to come to this hospital with this particular problem on this particular day? It's really, like I said, operational in nature. In those types of situations right now, I have this sort of thumb in the air crystal ball in many cases that I'm trying to make decisions around, predictive analytics and operations get me if it's not 95% accurate, probably doesn't matter if I can put a model together that's 75 or 80% accurate, that's a way clearer operational crystal ball than I have in front of me today. Then we get into this next level, which is sort of the top of the heap here.

(11:51):

There are hospital systems that are very deep into this already, and that's really what you might hear people refer to as precision medicine where we've got somebody's health record, we know procedures that happened at other hospital systems. We now also have their genome sequenced. So now I know what their genetic makeup of that particular person is, and I start to tie all that together and it could be used by physicians to help figure out what's the best treatment often used in a pharmacological setting to determine, hey, there's five different treatments for this type of cancer. Which one is this particular patient going to metabolize better than this one? So that's really intricate care stuff, that deep impact and we got to be accurate on those things. No, 75, 80% accurate. That's medicine being performed with data in the back there.

Jess Carter (12:41):

That sounds incredible because one of the things that I've been curious about, I was just reading, I think in The New York Times, there was a whole article about how I'm in the Midwest and how there's been this large change to the way cancer is spreading in younger generations. They kind of focused on Iowa, but they really said all throughout the Midwest, Iowa, Illinois, Indiana, that there was sort of this like, hey, what's going on? Is it environmental? Are we just getting more medical care so we're getting diagnosed earlier versus we're getting sicker? What is it? And then to your point, then we can apply treatment. I mean it sounds like some hospital systems are doing some really innovative things to say hopefully there will be better patient outcomes because of the depth of the ladder of what you just explained to us of, hey, we can actually understand which treatment, which standard of care. Maybe there's not just one anymore, maybe there's multiple for a certain instance or condition, and then we actually know that we can predict that you will be more successful and have a long longevity because you went through treatment A versus B. Is this becoming normal or those hospital systems doing that early adopters, or is that sort of the expectations these days?

Tony Pastorino (13:50):

I don't know if I would say it's expectations yet. I know, and this is in my experience where I've seen it used probably the most right now is in an oncology setting. So we are talking about cancer. We are talking about there's multiple trials available based on the things down to, I don't want to sound like a doctor because I’m not, but down to like, hey, we sequenced the actual tumor from your body and we think because of what we found there, this is going to be the best treatment, that kind of stuff.

Jess Carter (14:20):

Well, Tony, I felt like I lucked out when I had shared on a different episode that I had breast cancer and I had the kind that's called HER2. So it's when your body creates more HER2 proteins tied to your cells. I felt like I got lucky because the chemo I received was able to better focus. It actually was the immune treatment that went along with it basically helped identify all the cells that had extra HER2 and apply the chemo more efficiently to those cells. So in a weird way, I kind of experienced that. It was like the standard of care for my kind was aligned and I realized I'm sharing HIPAA data in a podcast setting, which is fine, but I didn't know that to use these terms or to understand that's what was happening to me and I didn't need to.

(15:03):

What I knew was as much as I didn't want to hear the word chemo, I also heard the efficacy tied to it for my general condition, and that was really successful. And so to your point, there's all these new trials and we're trying to figure out how to fight these things and we want to apply our resources as thoughtfully as possible for the right conditions for the best outcomes. And so it's like I'm sure if you're somebody who has a lesser known cancer, there's probably a bunch of different trials and you're trying to get into them, but how do you apply your energy to get into the most right trial for you? That's pretty incredible.

Tony Pastorino (15:38):

I talked about sort of operational predictive analytics and then we jumped into this precision medicine bucket. The folks that need to be involved I think is an interesting question or two. I feel like when we talk operational analytics or predictive analytics around operations, I feel like with the right data set pulled together and the right set of data scientists and some subject matter experts around how a hospital works, not necessarily how we provide care, but how do things move and function within a hospital system. I can bring a lot of value to you there and I can do predictions that are going to help those operational folks on a day-to-day basis run the system better. 

When you start talking about precision medicine, you're talking about highly trained people like geneticists and pharmacy folks that understand how people metabolize certain medicines. Obviously the oncologist, if we're talking about a cancer situation. So it's interesting, although they're both sort of predictive and trying to use data to figure out the best way to do something. I think the skillset mix that you're talking about of who's at the table is very different between those two things.

Jess Carter (16:45):

So even on the operation side, I feel like this was sort of a general experience of me coming out of college, but you kind of get your first job and you get, you're a big kid and you go find your first primary care doctor that your parents didn't set up, and it's like everyone I feel like has this experience. If you go to doctors to be like, oh, another form, you need to write it down again, sometimes in the same facility, sometimes every visit, and so there's this, why do you need this information again? It's still me now again, some information does change and so it makes sense that you update it, but to your point, even having that understanding that just because it's a hospital system doesn't mean that they're all on the same record system is really interesting to say. Wow. Are there moves to make that experience better for patients as well?

Tony Pastorino (17:32):

There is, I think a couple different fronts on that. I don't know if you've seen it personally. I've seen it a couple times versus ten years ago where you are always getting handed a pen and a pad of paper or clipboard to fill out. I at least feel like now many places you go to seek care, you're being handed an iPad or some sort of tablet. It doesn't necessarily have to be an iPad, and much of your information might already be prefilled on there that says, hey, go read through this and if we got something wrong, you changed your phone number or you have a different address now or since we last saw you have a new sort of chronic illness you want to tell us about, you just change things. You don't start over and spend 15 minutes writing everything down again. So I think there are definitely improvements being made there. Again, nothing ever moves as fast as I think any of us would like it to, but I think the vision of what can be done there has been figured out and we're moving forward on that.

Jess Carter (18:25):

So if I come back to brilliant basics here for a second, because I've never been in the hospital world. I have to remember that they are businesses and I don't want to remember that sometimes. I want to be a patient that just knows that they care about me deeply, right? That's where my parents take you when you're sick and you get good care, but it's actually, it is a business and I feel like we learned that really, really the hard way during COVID. I don't know if you could say more about this, but one of the things I did not understand at all, and I don't think society understood was how much elective procedures really help fund hospital systems that people who come in and say, hey, I do want an elective procedure. I also, even how you label some things elective is sort of interesting to me, but in general I would imagine it's fairly expensive to run a hospital system when that's not there.

Tony Pastorino (19:11):

Yeah, hospital systems. The reality is, and anybody can go find a report anywhere probably on the internet that makes it look like a hospital system has the same margins as a software company. I can promise you don't. It's a low margin business when it comes down to it. I can tell you hospital system, I worked at approximately 17 hospitals, 35,000 employees. We're talking everything from folks that clean the rooms to folks that work in the cafe, to doctors, to nurses, to everybody. So you can imagine as you get these bigger health systems, the number of people that work there grows pretty quickly. But it takes a lot of people to run these operations. It really does. And the ultimate goal of being, hey, let's make sure that the people that come here have a good experience, they get the right care they need, we get 'em out of here as quickly as we can.

(20:03):

Nobody that I've ever met wants to be in a hospital if they're not there working. So all of those factors you can imagine, it takes a lot. And all those people are getting paid, and all of those people are using supplies that cost money, and all of those people also have a health insurance program that they're on, the folks that are coming there to seek care have. So it is a business, it's not a super high-margin business. So this comes back to the, when we have something that is low margin and we've got financial pressures on us to pay these folks and make sure we're providing high care quality and all that, it's like any other business, I better be doing that as efficiently as I can. I need to try to get waste out of the pipeline. I need to make sure that I've got the right number of people there on the right day. All those things that we would normally think of if I was running something off of a manufacturing line, I've got the same things I've got to think about.

Jess Carter (21:00):

We have to talk about nurses for a second. So I mean, I think it is really eye-opening. When I think about a really large corporation, I think about a private company that has 35,000 employees and probably has really big margins. I don't think about a hospital, I don't think about how tiny the margins of error are when it comes. Nobody expects to go to a hospital and get sicker and you're going into a place that has statistically more disease because everybody's going there sick. And so it really is very interesting. But you think about the pressures of the last five years on nurses and the unpredictable workloads and the number of traveling nurses increased exponentially in some ways because of that. I was a talked a traveling nurse just the other day who said, my family's in South Carolina, but this is where I make more money traveling and that's what I need. And the hospital was trying to balance traveling nurses versus trying to keep people who stay. How do you use predictive analytics to try and help solve for the nursing crisis, if you will? I don't know if it's still considered that, but how does predictive analytics with data help with something like that?

Tony Pastorino (22:05):

To your point, you've got this very limited number of highly skilled professionals that are trying to service a need group that's way bigger than what they want it to be. And so to the question of I have more demand than I have capacity is, let's make sure I'm putting the capacity I have in the right place at the right time to do the best I can to service that demand that's coming in. So if we think about that from a predictive analytics standpoint, if I could take the general zip codes that a hospital services and I can pull in all of the clinical data, which shows me all the acuity or how sick, when we say acuity, we say, how sick is somebody that was coming in? I can pull that together. I can look and see how long people with these issues were at these hospitals.

(22:54):

Here's how long they were there, here's when they came in, here's how they got out. Oh, by the way, I'm going to pull in weather patterns also for a specific time of year because we know we get higher traffic on this weekend and that weekend. If I can pull all that stuff together and build some predictive models around that dataset, I should be able to get pretty darn close to knowing I'm going to have this many folks with this sort of average acuity level on this day, probably even down to a shift level. So within an eight hour, ten hour period, I'm going to have, this is what my picture's going to look like and then try to align my available nurses to that sort of staffing demand. It's not going to be perfect, but it's going to be way better than what we do today and what we've been doing for however farther back.

(23:44):

And ultimately what this helps battle, Jess, is we have this problem where nurses are overworked. It's a stressful job to start with and they get burned out. That's the bottom line. So if we already don't have enough of something, let's try not to burn out the ones that we do have. So that's going to help with that. It should help spread people more evenly across that patient population so that everybody's kind of doing the same type of work. And then last but not least, there's at least two studies that I've read that show that, and this is not like rocket science. Somebody actually had this hypothesis and then they proved it out. But if you are receiving nursing care from a nurse that is highly satisfied, your outcomes are likely going to be better than if you're getting care from someone that's about to burn out. And that's been factually proven out now with patient satisfaction and staff satisfaction surveys and linking those to outcomes and that kind of stuff. So

Jess Carter (24:47):

That's crazy.

Tony Pastorino (24:48):

It's a big area where I think predictive analytics can really help with what is honestly a really serious problem we have and not enough nurses.

Jess Carter (24:56):

Man, I get excited. We weren't even planning on a conversation about AI, but I think about whatever we're going to be able to do in the next few years with robots or with AI in general. There's obviously a need for human connection as part of healing, and it's really interesting to think about to your point, how do you more carefully and more thoughtfully apply that human care where it's needed most for the best outcomes? This is so interesting.

Tony Pastorino (25:22):

Yeah, on the AI front, one of the things I'll bring up on that, and I know I actually have a friend, they went to their doctor, I don't know, a few weeks ago because they were talking to me about this. It was the first time they had gone and they were told when they got there, they said, hey, this is being recorded. So in the doctor's office they call it, it's ambient listening. So there's microphones and stuff in there, and the doctor visit was like you and I talking now, not the doctor talking to me while they're typing and trying to record all this stuff and then having to go home at night and go back through their notes while they're sitting on their couch and trying to align everything up. With AI now and this ambient listening, we can go back to the doctor and the patient having a conversation and what the doctor has to do afterwards then is make sure did what was heard get captured the right way, and it's easier to read through something and make a correction than it is to be doing all that stuff while you're trying to interact with the patient.

(26:16):

So that's one area that's being used quite often now across the health systems.

Jess Carter (26:21):

That's unbelievable. That gives me so much hope that as we figure out technology and data, we can also figure out how to create those human interactions more distraction-free. Instead of worrying about your insurance and your billing code and your notes, you're able to just, let's have a conversation. That's really exciting. So if you're in a healthcare system listening right now and you wanted to begin this journey towards prediction, I assume there's probably some hospital systems that are smaller or more local that aren't doing anything right now. In your opinion, what's the simple most important thing they should do first? What's the first step towards this?

Tony Pastorino (26:57):

Yeah, I mean, I think the first piece is getting that data pulled together into some sort of enterprise data lake sounds like such a big giant thing, but it's getting that data pulled together like I talked about earlier. Let's not try to go ping ten different sources to try to extract data out of it for a one-time, ad-hoc need. So get the data together and then get the data engineered so that it's usable and that again, might be doing some technical work to pre join some datasets together for folks. Those are the two big first steps. And then the third one I'll mention is, and you can do this, this is not a predictive analytics thing. This is big on the sort of descriptive or old historical trend lining analytics also. Get the data into the hands of the people that know how to use it.

(27:43):

So if you worked at a hospital that has 17 different facilities in it and you tried to centrally manage a group of analysts to do financial analysis and clinical analysis, you'd have a team of 5,000 people and you still probably couldn't do all of it. You have subject matter experts out in every one of these operational areas within a hospital. Give them access to the data that they need to make decisions around it. If we have all this gold, if you will, and all this data that we have and we've got it locked up in a safe that ten people have the code to the safe, we're not going to get a lot of value out of it. And again, we're back to the HIPAA conversation, back to security. Folks that work in a hospital system, they've all taken HIPAA training, they all understand the privacy of the data. We have tools in place that monitor at hospitals if somebody is accessing data that they should not be accessing or they're accessing data for some weird way and we can stop. So we've got the controls in place, they do have to be there, but get the data out in the hands of folks that can use it is probably the biggest piece there.

Jess Carter (28:45):

I really love that. I think it's okay to have a centralized team, I imagine, that's doing some analysis to your point, but when it comes to wondering why this one hospital has better outcomes with their patients than another hospital, you walk through and talk to the nursing staff and you'll understand very quickly that one of them opens the curtains and make sure there's sunlight and cracks a joke and make sure to make, there's these things that do matter, but they're not in the data yet.

(29:09):

People are going to have hypotheses and bash their heads against the wall because they didn't walk the halls with the people that actually create that data. And so I really appreciate your passion for don't leave them out. They are subject matter experts for a reason. You need to solve data problems with your teams, and that's hard to do, but it's so important. Maybe my last question for you is what makes you really excited about the future?

Tony Pastorino (29:34):

I'm going to answer this two ways. One of the things that really gets me jazzed is the precision medicine that we were talking about earlier. I'm not the right person to speak to that just because I've witnessed it at small scale, but that's just a topic that's just super thrilling to me. So things that I can actually grasp and impact. We've all of these hospital systems, they made big investments over the last five or ten years to pull their data together. It was the thing to do. Everybody needed to do it and it was the right thing to do. We have to build foundations for stuff before we build a skyscraper on top of it. I don't know in many cases that I've seen us use those foundations to build much more than a one-story house on top of. So I'm excited that we have those datasets there and we've got sets of data scientists that are super jazzed to come in and leverage those data assets to start to do some really cool stuff like predictive analytics and operational predictions and help truly drive a better healthcare environment for all of us.

(30:35):

That's what I'm excited about. I think the challenge we have there is, and this is sort of a catch-22 type situation, is the financial pressures on hospital systems right now are greater honestly than they've ever been in my lifetime, and especially in the time that I've worked in this industry, which says, okay, that makes it harder to make investments, right? Yes, it does. But if I don't make those investments, I'm just going to be in this endless cycle of, hey, I can still tell you what I did last week, but I can't tell you what next week's going to look like. So I think these financial pressures, just like they do in any other industry, are going to maybe be the tripping point where we say, okay, we got to move to the next rung on the ladder here. We've got to start to leverage these investments we already made to get more value out of them and to basically keep us sustainable. So I think that's exciting, and that's like anytime we're kind of moving to the next step on a ladder on something that's exciting.

Jess Carter (31:30):

Well, and to your point, there's so many different personas to help: the doctors and the nurses and the staff members and the patients of course, and the hospital leadership, and there's so many different people that can leverage it. It's sort of like a treasure chest that hasn't been opened. And so I really like your perspective on, there is value that's not being tapped at the level that it can generate, and it's going to be exciting to see hospital systems get their arms around that. That's cool.

Tony Pastorino (31:56):

Very much so.

Jess Carter (31:56):

There's so many people in the healthcare industry now. They use these terms and they talk about some of the things that you've explained to me that I think people assume we all know it, and it's actually really helpful to have a deep dive and understand. So I appreciate all the different perspectives that you can sort of round out an understanding of health care and data and where we're headed. So thanks so much for joining us, Tony.

Tony Pastorino (32:15):

Thanks for having me. It was fun talking through it.

Jess Carter (32:17):

Thank you for listening. I'm your host, Jess Carter. Don't forget to follow the Data-Driven Leadership wherever you get your podcast and rate and review, letting us know how these data topics are transforming your business. We can't wait for you to join us on the next episode.