# Reimagining healthcare delivery and public health with AI

- **Show:** Microsoft Research Podcast
- **Published:** 7 Aug 2025
- **Source:** https://www.microsoft.com/en-us/research/podcast/reimaging-healthcare-delivery-and-public-health-with-ai/
- **Transcript:** https://podcasts.opennash.com/shows/microsoft-research-podcast/reimagining-healthcare-delivery-and-public-health-with-ai-cab567/
- **Provider:** OpenNash Podcasts (machine-generated)

## In brief

Leaders of public health and of large health systems say AI is already useful, and that their fields must help shape it. Umair Shah argues that public health, the invisible work that keeps whole populations healthy, is neglected by tech companies. Gianrico Farrugia argues that Mayo Clinic's early bet on AI and data is paying off in patient outcomes, pathology and education.

The tension runs between promise and readiness. Shah describes an under-funded field with fax machines, incomplete data and low AI capacity, where AI could help but risks bias and invented information. Farrugia shows what a well-resourced institution can do, and he urges aiming at fundamental transformation instead of tuning a broken system. Both say people must stay involved and be at the table.

## Key insights

1. **Tech companies neglect public health for diagnosis** Shah and Lee note that AI developers gravitate toward diagnosis and care delivery, which receives roughly 95 cents of every health dollar. Population-level work, such as outbreak signals, gets little attention, so insights from population data have come more slowly than the book predicted.
2. **Messy data hampered the COVID response** Shah describes agencies still relying on faxes with misspelled names and missing birth dates. He argues AI could clean and organise such data, and help forecast the effects of decisions like curfews.
3. **AI should be overseen, not trusted blindly** Shah warns that AI can make up information and can absorb inequities already present in its training material. He says people must stay in the loop for now, and that skilled AI users will gain an edge over those who are not.
4. **Mayo decentralised AI and let departments own it** Against consultants' advice, Mayo pushed AI ownership into clinical departments about six years ago, supported by shared infrastructure. Farrugia says this meant generative AI arrived as an enabler rather than a disruption.
5. **Early heart-algorithm proof justified big investment** A 2019 electrocardiogram algorithm detecting weak heart pumping gave Farrugia concrete evidence to show his board and other CEOs. Mayo now runs about 320 algorithms, and one hospital monitoring program reduced length of stay, ICU transfers and mortality.

## Questions this episode answers

### Why does public health get less attention from AI developers than hospital care?

Shah says healthcare delivery takes about 95 to 96 cents of every health dollar and is more familiar to tech companies, so they build for it first. Lee adds that technologists tend to focus especially on diagnosis.

### How could AI have helped during the COVID-19 pandemic?

Shah says it could have cleaned up incomplete data such as misspelled names, synthesised fast-changing global information, and modelled the effects of policies like curfews or masks. He cautions it cannot be 100% accurate.

### What is the Mayo Clinic Platform?

It is Mayo's data platform, started around the end of 2018, which lets Mayo and partners gain insights from de-identified clinical data. Farrugia says it was built to link data and AI to better patient outcomes.

### Does Mayo Clinic actually use AI on patients today?

Yes. Farrugia says Mayo has about 320 algorithms in practice, some running on every patient. One program monitors hospital patients and predicts decline early, and he says it shortened stays and reduced ICU transfers and deaths.

### Will AI replace doctors or public health workers, according to these guests?

Neither says so outright. Shah says people should not yet be removed from the process but that those skilled with AI will outcompete those who are not, and Lee declines to ask Farrugia the replacement question.

## Facts

- **Peter Lee** [0:00:03]: "Shortly after OpenAI's GPT-4 was publicly released, Kerry Goldberg, Dr. Zak Kohani, and I published The AI Revolution in Medicine"
- **Peter Lee** [0:00:55]: "The book passage I write at the top is from Chapter 7, The Ultimate Paperwork Shredder."
- **Peter Lee** [0:02:12]: "He led one of America's top-rated pandemic responses as Washington State's Secretary of Health, a position he hailed from 2020 to 2025."
- **Peter Lee** [0:02:49]: "the president and CEO of Mayo Clinic, the world's top-ranked hospital for seven consecutive years and a pioneer in technology-forward platform-based healthcare."
- **Umair Shah** [0:07:14]: "Harris County is the third largest county in the U.S., so it had close to 5 million, and now it's probably exceeded the 5 million people."
- **Umair Shah** [0:07:14]: "home to Texas Medical Center as well, which is the largest medical center."
- **Umair Shah** [0:08:21]: "this was the state that had the first case in the continental United States, had the first outbreak and the first death."
- **Umair Shah** [0:08:58]: "we had the fifth lowest death rate in the U.S., and that was because we all came together to do so much."
- **Umair Shah** [0:15:37]: "NACCHO, the National Association of County and City Health Officials, had done a survey of local health agencies, and about two-thirds, if not three-quarters of local health agencies reported that they had an AI capacity that was low or lower than ideal."
- **Umair Shah** [0:25:16]: "a lot of agencies across the country were still using fax machines, you know, to get data that were coming in."
- **Umair Shah** [0:31:22]: "it was the nurse who picked up this time because the practitioner, the provider, the healthcare provider, the doc, missed it."
- **Umair Shah** [0:30:01]: "wasn't a patient number one in the united states discovered also because of the seattle flu study or at least that sort of syndromic surveillance"
- **Gianrico Farrugia** [0:41:54]: "We have about 83 ,000 staff members that work with us and we're very proud of the work we do in research, education and practice."
- **Gianrico Farrugia** [0:43:33]: "estimates biological age from an ectocardogram. My biological age jumped by 3.7 years when I became CEO."
- **Gianrico Farrugia** [0:44:29]: "a physician for way too long. I got my MD degree in 87."
- **Gianrico Farrugia** [0:47:48]: "And that's the genesis of MCP, Mayo Clinic Platform. So I'll timestamp that as end of 2018, beginning of 2019."
- **Gianrico Farrugia** [0:48:59]: "The first was that they created the first integrated healthcare system. And the second, they created the first unified record."
- **Gianrico Farrugia** [0:53:58]: "We made the decision against the advice of any consulting firm to completely decentralize AI at Mayo Clinic six years ago."
- **Gianrico Farrugia** [0:57:18]: "And we now have 320 algorithms in the practice and they run and we constantly are looking and seeing what else we can do to improve."
- **Gianrico Farrugia** [1:01:25]: "The first one was for diagnosing from an electrocardiogram, which is very cheap, very easy to do, left ventricular dysfunction."
- **Gianrico Farrugia** [1:04:02]: "we've shown we've decreased length of stay in the hospital, decreased transfers into the intensive care units, and interestingly, decreased mortality and morbidity"
- **Gianrico Farrugia** [1:06:04]: "And so we end up with 21 million of our slides digitized and that gives you now a massive opportunity."
- **Gianrico Farrugia** [1:06:04]: "And we, I think 120 years ago, invented frozen sections at Mayo Clinic."
- **Gianrico Farrugia** [1:07:22]: "the fact that 40% of people with rheumatoid arthritis don't respond to the first line therapy right but you have to wait six months to find out"

## Transcript

**[0:00:03] Peter Lee:** In U.S. healthcare, quality ratings are increasingly used to tie the improvement in patient health outcomes to the reimbursement rates that healthcare providers can receive. The ability of GPT-4 to understand these systems and give concrete advice has a chance to make it easier for providers to achieve success in both dimensions. This is the AI Revolution in Medicine Revisited. I'm your host, Peter Lee. Shortly after OpenAI's GPT-4 was publicly released, Kerry Goldberg, Dr. Zak Kohani, and I published The AI Revolution in Medicine to help educate the world of healthcare and medical research about the transformative impact this new generative AI technology can have.

**[0:00:55] Peter Lee:** But because we wrote the book when GPT-4 was still a secret, it, we had to speculate. Now, two years later, what did we get right and what did we get wrong? In this series, we'll talk to clinicians, patients, hospital administrators, and others to understand the reality of AI in the field and where we go from here. The book passage I write at the top is from Chapter 7, The Ultimate Paperwork Shredder. Public health officials and healthcare system leaders influence the well-being and health of people at the population level.

**[0:01:37] Peter Lee:** They help shape people's perceptions and responses to public health emergencies, as well as to chronic disease. They help determine the type, quality, and availability of treatment. All this is critical for maintaining good public health, as well as aligning better health and financial outcomes. That, of course, is the main goal of the concept of value-based care. AI can definitely have significant ramifications for achieving this. Joining us today to talk about how leaders in public health and healthcare systems are thinking about and acting on this new generation of AI is Dr.

**[0:02:12] Peter Lee:** Umair Shah and Dr. Gianrico Farrugia. Dr. Umair Shah is a nationally recognized health leader and innovator. He led one of America's top-rated pandemic responses as Washington State's Secretary of Health, a position he hailed from 2020 to 2025. Umair previously directed Harris County Public Health in Texas, overseeing large-scale emergency response for the nation's third-largest county while building an emergency care career spanning 20-plus years. He now advises organizations on health innovation and strategy as founder and principal of Rickshaw Health.

**[0:02:49] Peter Lee:** Dr. Gianrico Farrugia is the president and CEO of Mayo Clinic, the world's top-ranked hospital for seven consecutive years and a pioneer in technology-forward platform-based healthcare. Under his leadership, Mayo has built and deployed the Mayo Clinic platform. The platform enables Mayo and its partners to gain practical insights from a comprehensive repository of longitudinal, de-identified clinical data spanning four continents. Gianrico is also a Mayo Clinic physician and professor and an author. Umair and Gianrico are CEO-level leaders representing some of the best of the worlds of public health, healthcare delivery, medical research, and medical education.

**[0:03:32] Peter Lee:** Here's my interview with Dr. Umair Shah. Umair, it's really great to have you here.

**[0:03:46] Umair Shah:** Peter, it's my pleasure. I've been looking forward to this conversation, and I hope you are well today.

**[0:03:53] Peter Lee:** I am doing extremely well. So, you know, what I'd like to do in these conversations is first just to start a little bit about you. You served actually during a really tumultuous time as the Secretary of Health in the state of Washington, but you recently stepped away from that and you started your own firm, Rickshaw Health. So can we start there? What's that all about?

**[0:04:21] Umair Shah:** Yeah, no, absolutely. First of all, I would say that the transition from Texas to Washington could not have been more geopolitically different, as you can imagine. Sure. You know, if you like the red-blue paradigms, you can be more red and you can be more blue, I think. Yes. But what happened is back in November this past year, as I saw some of the play out of continuation of this red-blue dynamic, I made the decision to step down.

**[0:04:54] Umair Shah:** And January 15th, I stepped down, as you mentioned. and I spent some time really thinking about what I wanted to do next and was looking at a number of opportunities. And then a moment in time, there were some things happening in my wife and our family's personal lives that sort of made me think that I wanted to focus a little bit more on family and I felt the universe was saying, stay still. And I launched Rickshaw Health and the notion that, as you know, Peter, rickshaws are oftentimes known across the globe as these modes of transport that reliably get you through ever-changing streets and traffic patterns and all sorts of ecosystems that are evolving at all times.

**[0:05:36] Umair Shah:** And they get you to the other side and they get you also with a sense of exhilaration. Like when I took my boys to Karachi and they jumped in a rickshaw in open air and they felt this incredible excitement. And so rickshaw health was speaking to the three wheels of a rickshaw that symbolize the three children that we have and the real notion of how do we bring balance and agility and performance to the forefront and then move in an ever, just like streets, ever-changing healthcare environment that is constantly evolving.

**[0:06:10] Umair Shah:** And we too must evolve with it. And that's what rickshaw health is all about, is taking clients to that next level of trying to navigate, especially at this time, a very, very different landscape than even several months ago. So excited about it.

**[0:06:26] Peter Lee:** Yeah, absolutely. You know, you made this transition from Texas to the state of Washington. And for people who listen to this podcast and don't know, the particular part of Texas where you were, Harris County, is really big, very, very important in that state. That's just not the normal county in Texas. It's actually known as quite a forward-looking place technologically. So what was the transition like then going from possibly the most sort of maybe advanced county in the state of Texas, a large place to the state of Washington?

**[0:07:14] Umair Shah:** Yeah, you know, Harris County is the third largest county in the U.S., so it had close to 5 million, and now it's probably exceeded the 5 million people. And very diverse, very forward-looking, as you mentioned, technologically very much looking at what's the next horizon. And home to Texas Medical Center as well, which is the largest medical center. Of course, it had to be Texas, so it can't be the largest in the state or the country, the largest in the world, right?

**[0:07:44] Umair Shah:** And TMC also had a number of different initiatives related to startups and venture capital and VC. And so they had launched something called TMCX. And that was a real opportunity. And I know you're familiar with it, an opportunity to really look at how do you incubate all sorts of different innovations and bringing private sector, public sector, as well as healthcare delivery alongside these startups to really look at the landscape. And so when I left Houston and came to Washington, I realized that obviously it was in the backyard.

**[0:08:21] Umair Shah:** I mean, you all at Microsoft Research and the work that you're all doing is part of an ecosystem of advanced innovation that's occurring in the Pacific Northwest. that when we see all the players that are here, all the ones that do so many different things, but they're doing them with an eye towards technology, advancements, and adoptions, it's been quite amazing. When I made that transition, it was really about vaccines and what was happening with COVID and fighting the, remember, this was the state that had the first case in the continental United States, had the first outbreak and the first death.

**[0:08:58] Umair Shah:** And fast forward, A few years later, we had the fifth lowest death rate in the U.S., and that was because we all came together to do so much.

**[0:09:08] Peter Lee:** Yeah. Well, maybe that gets us into a question that I ask a lot of our guests, which is, you know, and maybe let's, since we're on your time as the Secretary of Health in Washington State, with that job, I ask, how would you explain to your mother what you do every day?

**[0:09:32] Umair Shah:** I laugh because that's been such a fascinating conversation in public health because we have oftentimes been – it's been really hard to describe what that is. And there are so many metaphors and analogies that we've used. I've always wondered why we do not have more television shows or sitcoms or dramas that are about the public health workforce or the work that we do in the field. Because you have, you know, all sorts of health care delivery ones, right?

**[0:10:07] Umair Shah:** As a practicing physician for 20 years, I realized that people knew what doctors did. They knew what nurses did, right? They intimately touched the health care system. They understood that an ambulance picks you up at your home or somewhere else, transports you, gets you to the emergency department. The emergency department, they do some things to you or within the four walls of that ER. And then you're either admitted, sent home, and several days, weeks, whatever later, you get home if you're admitted and you start your post-hospital stay at home or your rehab or what have you.

**[0:10:46] Umair Shah:** And that all is known to people. But when you ask your mother, your grandmother, or your uncle, your brother, your neighbor, your coworker about what is public health, they have a very quizzical look on their face of what that is. And so what I've…

**[0:11:04] Peter Lee:** You know, one thing I've learned is it's not just all the people you mentioned. Even healthcare professionals sometimes have that quizzical look.

**[0:11:13] Umair Shah:** That's right. Good point. Right. And a lot of it is because we don't get exposed to it or trained in it. We think about public health when we're in our training, and I'm sure you had a very similar piece of this, is that you see it as, oh, that's the health department that takes care of STDs, or it does the immunizations, or maybe they do some water quality, or maybe they do vector mosquitoes and But the reality is we do all of those things and more.

**[0:11:43] Umair Shah:** And so my metaphor has been that we are the offensive line of a football team. And the healthcare delivery is the quarterback. So everybody focuses on, you know, from a few years back, everybody knows Tom Brady, right? He won the Super Bowls. Everybody knows what. But if you asked people, who was number 75 on the offensive line of the New England Patriots or name your favorite football team? And the answer would be you would not be able to likely answer that question.

**[0:12:18] Umair Shah:** You would know Tom Brady, the quarterback, and that's health care delivery, the ER doc or the hospitalist or the nurse or the medical assistant or the people that are doing all the work in the field that are the ones that are more visible. But the invisible workforce of the offensive line, that's who we don't know. And yet these are the people that are blocking and sweating and doing all things to complement the work and make sure the quarterback is successful.

**[0:12:45] Umair Shah:** And here's where the metaphor breaks down, that when Tom Brady wins the Super Bowl, we continue to invest in the offensive line because we recognize the value of it. We want the quarterback to be successful the next season. But in public health or in society, we do the exact opposite. When tuberculosis rates come down, we say, well, you know what? We've solved the problem. We don't need it anymore. Or you have another environmental issue that's no longer there.

**[0:13:14] Umair Shah:** You say, we don't need it anymore. And we disinvest from public health or that offensive line. And then you start to see those rates go back up. And so my answer to mom and grandma and dad and grandpa is we are critical to your health because we touch you every single day. And so please invest in us.

**[0:13:35] Peter Lee:** Yeah. And, you know, I think I'm going to want to get a little deeper on that in just a few minutes here, because I think especially during the pandemic, that issue of not understanding the importance of that offensive lineman actually really came to the forefront. And so I'd like to get into that. But the kind of second kind of standard thing I've been probing with people is still just focusing on you and your background is what touch points or experiences you've had with AI in the past.

**[0:14:10] Peter Lee:** And not everyone has. Like, it maybe isn't too surprising that doctors and healthcare developers, tech developers, have lots of contact with AI. But would the top dog, you know, at a public health agency ever have had significant contact with AI? What about you?

**[0:14:32] Umair Shah:** You know, it's interesting. Several years ago, I was in the audience with the FEMA director who just did such an incredible job. And I remember he made this comment at that time. And Peter, this may have been like, I don't know, I'm dating myself 10, 15, maybe even 20 years ago. And he said, everybody in the audience, there's this app called Twitter. And how many people in the audience have ever sent a tweet or know about this?

**[0:15:05] Umair Shah:** And I don't know, maybe it was a public health audience. Maybe about 15 % of the people raised their hands. He said, I challenge you to right now pick up your phone, download the app, and go ahead and send a tweet right now. And I remember I sent my first tweet at that time. And it was so thought-provoking for me was that he was saying you need to be engaged in social media. But the other 85 % of the audience had not even done that or had even understood the importance of social media at that time.

**[0:15:37] Umair Shah:** Or maybe they understood, but they had restrictions on how to utilize, right? So that has stayed with me because that's very much about this revolution of AI, that I know that public health and population health practitioners like myself who have been in the trenches and understand the importance of it, they really believe in the importance or think they know the importance. But NACCHO, the National Association of County and City Health Officials, had done a survey of local health agencies, and about two-thirds, if not three-quarters of local health agencies reported that they had an AI capacity that was low or lower than ideal.

**[0:16:19] Umair Shah:** And that is very much where I come from. When I was in public sector and at the state health agency, our transformation was very much about how do we advance the work and how do we utilize this in a population health standpoint? And I was fortunate to have a chief of innovation at Washington State Department of Health, Les Becker, who understood the value of AI. And as you know, we did also hold a AI science convening that your team was there with University of Washington.

**[0:17:01] Umair Shah:** And that was really an opportunity for us to say that AI is here. It's not tomorrow. It's not next year. It's not the future. It's already here. We need to embrace it. But here's the problem, Peter. Far too few people in our field understand just how to embrace it. So I have become a markedly more champion of AI, one, since I read your book. So I think there is that. So thank you for writing it. But two, since I really recognized that when I became a solo or a primary few practitioner in my own realm, I needed to force amplify the work that I was doing.

**[0:17:42] Umair Shah:** And when I look back and I continue to stay in touch with my colleagues in the field of public health, what they're also struggling with is that you have an epidemiologist who's got a mound of information, data, statistics, et cetera, that they are going through. and they're doing everything in their power to get that processed and analyzed. AI can take 80 % of that and do it, and that epidemiologist can now turn to more of an overseer and a gatekeeper and to really recognize the patterns and let AI be able to do the grunt work.

**[0:18:17] Umair Shah:** And similarly, as you know, measles with the outbreaks that we've seen, especially in Texas But elsewhere, you've got an opportunity where our communications people who are saying, look, we're about to have or we know we're about to announce that there's a measles outbreak in our community or our state or what have you, our region. And they can have AI go through different press briefings and or press releases and say, give me the state of the art on how I should communicate this message to the community.

**[0:18:51] Umair Shah:** And bam, you can do that. And now you can oversee that work as well. And then the third example is that we are always looking at how do we find ways to have a deeper connection with those who come to our websites or come to our engagement tools with chat bots and things like that. AI can really accelerate that work as well. So there's so many use cases that AI has for population health or public health.

**[0:19:17] Umair Shah:** But I think the challenge is that we just don't have enough adoption because they're One, we've had funding cuts, but two is that there is this real hesitation on what is it that we can do. And I argue, the last thing I'll say about this, Peter, is that I argue that AI is happening right now. The discussions, the technology advancements, the work, the policy work, all that's happening right now. Now, if public health practitioners are not at the table, if they're not part of the what does this look like, how does it work in our field, guess what?

**[0:19:52] Umair Shah:** It's going to be done to us and for us rather than with us. And if we do not get with that and get to the table, then unfortunately, it may not be exactly what we want it to be at the end of the day.

**[0:20:04] Peter Lee:** I find it really interesting that you are using the terms public health and population health pretty much interchangeably here. And I think that that's something that I think touches on an assumption that was both implicit and explicit in the book that we wrote, which is we were making some predictions that our ability to extract insights and knowledge from population health data would be enhanced through the use of AI. And I think that it looks to me like that has been more challenging and has come along more slowly over the past two years.

**[0:20:47] Peter Lee:** But what is your view?

**[0:20:49] Umair Shah:** Yeah, I think part of, and I think you and I have had this conversation, you know, in bits and pieces. I think one of the real challenges is that when even tech companies, and you can name all of them, when they look at what they're doing in the AI space, they gravitate towards healthcare delivery. Yes. Right?

**[0:21:13] Peter Lee:** And in fact, it's not even delivery. I think techies, I did this too, tend to gravitate specifically to diagnosis.

**[0:21:22] Umair Shah:** Yes, that's right. That's right. You know, I think that's a really good point. And, you know, when you look at sepsis or you look at pneumonia or try to figure out ways that, you know, radiologists or x-rays or CT scans can be read. I mean, there are so many use cases that are within the healthcare sector. And I think that gets back to this inequity that we have when we look at population health or this broad swath of land that is oftentimes left behind or unexplored, and you have healthcare delivery.

**[0:21:56] Umair Shah:** Now, healthcare delivery, we know, gets $0.95 or $0.96 of every dollar. So it makes sense. Why? Right? But we also know that at the end of the day, we're looking at value-based outcomes. And you cannot be successful in the healthcare delivery system unless we are truly looking at prevention and what's happening in the community and the population. And that's why I use it interchangeably. But I know that public health has got a very specific term and population health is a different set of ways of looking at the world.

**[0:22:29] Umair Shah:** The reason that people try to shy away from pop health, in essence, is that you could talk about population health as being my population of patients in a clinic. It could be my health system's population. It could be an insurance company saying these are the lives covered, right? So it becomes what is population? When we think of public health, we think of the entirety of the population, right? In the state of Washington, 8 million people. Harris County, 5 million people.

**[0:22:54] Umair Shah:** Or in the U.S., you know, 300. Whatever the number of millions of people that we think of, the entire population, and what is it that actually impacts the health and well-being of that population is really what that's about. Yet here's the challenge. When we then talk to those of our partners and our colleagues in the tech field, there are two things happening. One is there's a motivation because of the amount of dollars that are in healthcare sector.

**[0:23:21] Umair Shah:** And number two is because it's more familiar, right? And so there are very few practitioners similar to me that are out there that are in the pop health who kind of know healthcare delivery because they've also seen patients, but they're also – they've worked at that federal, state, local level, community level. They've done various different kinds of environments, and they say, look, I've got a perspective to really help this tech company or somebody see the rest of it.

**[0:23:49] Umair Shah:** But you have to have both partners coming together to see that. And I think that's one of the real challenges that we have.

**[0:23:56] Peter Lee:** Yeah. And so now I'm going to want to go into specific problems. And maybe COVID is a good thing to focus on the breadth of problems that had to get solved in the pandemic response and where the gaps between healthcare delivery and public health were really exposed. And so the first problem that I remember really keenly that just seems so vexing was understanding where the PPE was, the personal protective equipment, and where it needed to be.

**[0:24:34] Peter Lee:** Yes. forward to solve, but that turned out to be an extremely difficult problem. But how did it look from where you were sitting? Because you were sitting at the helm having to deal with these

**[0:25:16] Umair Shah:** problems. Yeah, we were constantly chasing data and information. And oftentimes, you know, because a lot of these data systems in the public health sector have been underinvested in over the decades, then, you know, you had our biggest emergency crisis of our time. And a lot of public health agencies were either getting, you know, thrown a whole host of resources or had to create things on the fly. And whether that was at Harris County or in the state of Washington, I will tell you that what I saw was that, you know, a lot of agencies across the country were still using fax machines, you know, to get data that were coming in.

**[0:25:58] Umair Shah:** And I remember actually, it's kind of a funny story. There was a fax machine that was highlighted down in our agency in Texas. And we actually had this fax machine, had mounds of, you know, data, you know, sorry, papers that were next to faxes that were coming in and all these things. And you would have, you know, Mr. Peter Lee listed as a patient. And then the next, you know, transmission would have Pete Lee. And then the next transmission would have Peter Lee, but instead of L-E -E, it was L-E -A-H or something or L-I or something, right?

**[0:26:42] Umair Shah:** It was just, and you, or you had a date of birth missing, or you had, you know, an address that was off. And what we realized is that over time, a lot of the data that were coming in were just incomplete data. And being able to chase that was really hard. And so I think AI has that potential to really organize it and to stratify it and to especially get you to a point of at least cleaning it up.

**[0:27:12] Umair Shah:** And so I don't think it's just that AI, AI doesn't just save time, it saves lives. Truly used. That's, I think, where we're talking here. And so when you have PPE and things of that nature, as you talk about here in the state of Washington, or what we were trying to do to get vaccines out, or everything we're doing to try to get communication messages to the public. And we did a fantastic job of that, although not ideal.

**[0:27:37] Umair Shah:** I mean, there are so many things that I could point to that we could have done better, all of us in the field of public health and healthcare delivery alike, I will tell you that the one thing that stays with me is that if we had those tools then, and we had them in place then, and we had invested in them at that time in advance of, I think there was a real opportunity for us to be able to move ahead and even be better at how we affected the health outcomes of the very populations that we were trying to get to.

**[0:28:13] Umair Shah:** And I think AI allows us to shift from reactive to proactive systems, catching health issues before they escalate, and allow us to really communicate with empathy at scale. And when we can do those things, whether it's opioids or whether it's something that's happening related to an infectious disease or even the new agenda with Make America Healthy Again, which, by the way, as you know, we had a Be Well Washington very much that was about looking at physical health and nutritional health and emotional well-being and social connectedness, that there is a real opportunity for us to address the very drivers of ill health.

**[0:28:59] Umair Shah:** And when we can do that and AI can help us accelerate that, I think we truly have the ability to drive down costs and increase the value that's returned to all of us.

**[0:29:10] Peter Lee:** What is your assessment of public health agencies' readiness to use technology like AI? Because if there's one thing AI is good at, it's predicting things. Are they in a better position to predict things now?

**[0:29:27] Umair Shah:** You know, I think it's a tale of two cities. I think on the one hand, we're better because we have the tools. On the other hand, we've lost the capacity to be able to utilize those tools. So, you know, it's a plus and a minus. Many, many years ago, there was the buzzword of what we called syndromic surveillance. And Peter, you know this term well. It was like you would have a whole host of accumulation of data points in, let's say, a hospital setting or an emergency department where you have runny nose, you'd have cough, you'd have a fever.

**[0:30:01] Umair Shah:** and you would take that, what was happening in people presenting to the emergency department with what was happening in the area of pharmacies where people were going to get Kleenexes and tissues and buying over-the-counter medication and things of that, and your Tylenol, etc. And you would say, you would put those two things together and you would come up with a quote-unquote syndrome. And you would say, our ability to say there is an alert to that syndrome allows us to say something uh-oh is going on in the community and we got uh many uh many uh advancements related to wastewater surveillance over the last several years well also yeah wasn't

**[0:30:38] Peter Lee:** a patient number one in the united states discovered also because of the seattle flu study or at least that sort of syndromic surveillance they weren't even looking for covid they were just taking

**[0:30:48] Umair Shah:** that's right that's right so not samples from people that's right and so that's the kind of thing that you, you know, we underappreciate is, is you have to have a, a, a smart, intelligent, agile practitioner, right? So if I, I think about, uh, down in, uh, Dallas when Ebola was, you know, the, the, the gentleman who was, you know, uh, the, the index case for Ebola was sent out of the emergency department and, and came back, um, several days later.

**[0:31:22] Umair Shah:** And it was the nurse who picked up this time because the practitioner, the provider, the healthcare provider, the doc, missed it. And I wouldn't want to say in a negative way, it was just like not obvious. You aren't thinking of Ebola in the middle of Texas. And it was the nurse who picked up. There's something wrong here. And what AI has the ability to do is to pick up those symptoms or those patterns and be able to recognize the importance of those and be able to then alert the practitioner.

**[0:31:51] Umair Shah:** So what I, we call it artificial intelligence. It almost becomes artificial wisdom.

**[0:31:59] Peter Lee:** Yeah, interesting. So that actually reminds me of my next question, which is another thing that I watched you and public health officials do is try to play what if games. So for example, I think one decision you were involved in had to do with, you know, what would be the impact if we put a ban on large gatherings like concerts or movie theaters or imposed an 8 p.m curfew on restaurants and you were trying to play what if games like what would be the impact on the spread of the pandemic there um so now again today with ai would that aspect of what you did play out

**[0:32:45] Umair Shah:** differently than it did during the pandemic? As you know, COVID was the most studied condition on the planet at one point. And it was, you know, things that were usually we would learn over years or months, we were learning in weeks or days or hours. And I remember in Houston, I would say something in the morning, and I would always try to give the caveat, this is the best information we know right now, because it kept changing, whether it was around masks or whether it was around, you know, the way the virus was operating, the way it was around.

**[0:33:17] Umair Shah:** I remember even I was just watching something recently where I was asked to comment about whether spiders could transmit COVID-19. You know, just questions that were just evolving, evolving, evolving. And the information was evolving. By morning, you would say something. By evening, it would change. And why I say that is that it would have been great in the pandemic if we could have said, if you could give us all the information that's happening across the globe, synthesize that information and be able to help us forecast the right decisions that we should be making and help us model that information so we could decide if you did a curfew or if you did, you know, a mask or if you

**[0:33:58] Umair Shah:** could, you know, change something else related to policy, what are the impacts of it? What we found constantly in public health was that we were weighing decisions in incomplete data, incomplete information. So great now that everybody can armchair quarterback looking back three to five years ago and say, I would have done it this way, or I would have done it that way. Gosh, I would have as well. But guess what? We didn't have that information at that time.

**[0:34:25] Umair Shah:** And so you had to make the best decisions you could with incomplete data. But what AI has the potential to do is to help complete the incomplete data. Now, it's not going to get 100%. And I think, Peter, the one thing we've got to be really mindful is phantom information or information where it sort of makes up things or may somehow get you incomplete information or skews it a certain way. This is why we can't take the person out of it yet.

**[0:34:55] Umair Shah:** Now, maybe one day we can. I'm not one of those Pollyannish that people will never be replaced. I actually believe that those people who are skilled with AI and the tools will eventually have a competitive advantage over those who are not. Just like if I had a physician who knows how to use their smartphone or knows how to use a word processor or knows how to do a PowerPoint presentation is going to replace the ones that use Scantrons or the ones that write it on pieces of paper that eventually it makes it more efficient and effective.

**[0:35:29] Umair Shah:** But we're not there yet, but I think the potential is absolutely there. So I have one more question, and you can

**[0:35:37] Peter Lee:** kind of tell I'm trying to expand people's understanding of just the incredible breadth of what goes on in public health, you know, all of these sorts of different issues. And again, just sticking to COVID, but this is a much broader issue. Another thing you had to cope with were significant rise of misinformation. Yes. And maybe going along with that, very, very significant inequities in outcomes in the COVID response. And when you think about AI there, I think you can argue it both ways, that it both exacerbates the problem, but also gives you new tools to mitigate the problems.

**[0:36:25] Peter Lee:** What is your view?

**[0:36:26] Umair Shah:** I think you hit, I don't even have to say it, I think you hit on it, is that, you know, it really is two sides of one coin. On the one hand, it has the power of really advancing and allowing us to move forward in a way that incredibly accelerates and accentuates. But on the other hand, in the case of inequities, right, so if you have inequitable information data that's already out in the literature are already out in the media or what have you about a certain population or people or certain kinds of ideas or thoughts, et cetera, then AI will tend to accumulate that.

**[0:37:02] Umair Shah:** You're going to take that information thinking that's the best out there, but it may have missed out on information and now you go with it. And that's a potential problem. And I think it's the same thing on information, is that when we have people that are able to classify or misclassify information, I think it really becomes hard because it can accelerate the inequities of trust or inequities of trusted sources of information. It can also close the gap.

**[0:37:35] Umair Shah:** So I think it's really up to us in this responsible AI to really think about how we can go about doing this in a way that's going to allow us to further the advancements, but also be careful of those, you know, those kind of places where we're going to step into that are not going to be well received or successful. You know, the one thing that's really fascinating about this whole conversation is that this is why we've got to be at the table, Peter.

**[0:38:03] Umair Shah:** Yeah. Because if we're not at the table, Well, you know, what's the – or if tech companies that are out there doing this work and aren't even seeing a field of practitioners that are actually wrestling with the same problems but just cannot actually get to the solutions, we're just going to continue to accentuate the problems. And that's why I'm a firm proponent of we've got to be at the table. And so even when we've seen in, and this is going to be a little controversial, but governmental spaces where policymakers have said, look, we are not going to let you do certain things.

**[0:38:45] Umair Shah:** or they say to public health practitioners or even healthcare delivery practitioners in certain spaces, you cannot even play with this. You cannot have it on your phones. You can't do any, you know, what I really believe it does is that it takes a almost like we put our head in the sand type of approach rather than saying, what is it that we can do to help improve AI and make it work for all of us, what we're doing is we're essentially saying we're going to let the tech companies and all the other developers come up with the solutions, but it's not going to be informed by the people in the field.

**[0:39:22] Umair Shah:** And that's dangerous. We have to do both. We have to be

**[0:39:25] Peter Lee:** working together. Umaira, that's really so well said, and I think a great way to wrap things up. I certainly learned a lot from this conversation, so thank you again.

**[0:39:37] Umair Shah:** It's been a pleasure to be with you this morning. Thank you so much for the time, and I'm looking forward to further conversations.

**[0:39:51] Peter Lee:** I live in the state of Washington, and because of it, I've been able to watch Umair in action as our state's former Secretary of Health. And some of that action was pretty intense, to say the least, because his tenure as Secretary of Health spanned the period of the COVID pandemic. Now, as a dyed-in-the-wool techie, I have to admit that at the beginning, I don't think I really understood the scope and importance of the field of public health.

**[0:40:20] Peter Lee:** But as the conversation with Umair showed, it's really important, and it is arguably both an underfunded and underappreciated part of our healthcare system. Now, public health is also very much an area that's ripe for advancement and transformation through AI. As Umair explained in our discussion, the core of public health is the idea of population health, the idea of extracting new health insights from signals from population-scale data. and already we're starting to see AI making a difference.

**[0:40:55] Peter Lee:** Now, here's my interview with Dr. Gianrico Farrugia. Gianrico, it's really great to have you here today.

**[0:41:09] Gianrico Farrugia:** Peter, thanks for having me. Thanks for making me part of your podcast.

**[0:41:13] Peter Lee:** You know, what I'd like to do in these conversations is, we'll definitely want to talk about the overall healthcare system, the state of healthcare, and what AI could or might do to help or even hurt all of that. But I always like to start with a sharper focus just on you specifically. And my first question always is, I think people imagine what a hospital or a health system president and CEO does, but not really. And so how would you explain to your mother what you do every day?

**[0:41:54] Gianrico Farrugia:** So Peter, my mother's 88 years old. She lives in Malta and she's visiting at the moment. Oh, wow. Wow. That is amazing. I'm proud that she's still proud of me. So she does ask. I'll I tell her the scope of Mayo Clinic. We serve patients across the globe. We have about 83 ,000 staff members that work with us and we're very proud of the work we do in research, education and practice. Mayo Clinic is built to serve people with serious disease.

**[0:42:23] Gianrico Farrugia:** So what I tell my mother is that here we are, we're a healthcare organization that knows what it needs to do, keep patients as the North Star, the needs of the patient come first. We have 83 ,000 people who want to do that, several thousand physicians and scientists. My job is to look slightly ahead and then share what I'm seeing and then sort of smooth the way for others to make sure Mayo remains true to its mission, but also true to the fact that at the moment we are in a category of one.

**[0:42:54] Gianrico Farrugia:** We need to remain there, not just from an ego standpoint, but really from a good to the world standpoint. And at that point, invariably, my mother will tell me that I'm working too hard. And then, of course, I change the subject and I ask her what she cooked today, because my mother is 88, cooks for the whole family of Malta. And there are usually four generations eating around the table. So I tell her what she does for the family is what I do for the male family.

**[0:43:23] Peter Lee:** Oh, that's a great way to put it. And it sounds like you actually have a good chance to have some good genes if she's still that active at age 88.

**[0:43:33] Gianrico Farrugia:** I think I chose a little more stressful job that may limit. I will tell you very briefly is that one of the AI algorithms we have estimates biological age from an ectocardogram. My biological age jumped by 3.7 years when I became CEO. I'm hoping it will reverse on the other side.

**[0:43:52] Peter Lee:** To stick with you just for one more moment here. The second question I ask is about your origin story with respect to AI. And typically, for most people, there is AI before chat GPT and generative AI, and then after the generative AI revolution. So can you share a little bit about this? Because it must be the case that you've been thinking about this long time since you've really led Mayo Clinic to be so tucked forward in this way.

**[0:44:29] Gianrico Farrugia:** Well, I've been, as you said, a physician for way too long. I got my MD degree in 87. So that sort of dates me. But it also means that I saw a lot of the promise for AI that never seemed to pan out for decades and decades and decades like you did. Yeah. Around 10 years ago, Mayo could sense that it was something different, that something was changing that we actually, at that time, predictive AI could make a big difference.

**[0:44:57] Gianrico Farrugia:** And I think that's the moment where I and others jumped in and said, Mayo Clinic needs to be involved. And then about six years ago, when I, six and a half years ago, I became CEO, it was clear that there was the right confluence of data, knowledge, tech expertise, that we could deal with what was increasingly bothering me, which is that we knew what was coming from a technology standpoint. And we knew the current healthcare system could not deliver on what patients need and want within that current system.

**[0:45:31] Gianrico Farrugia:** And so the answer is, how could a place like Mayo Clinic, with our reputation, not jump in and say there has to be a better way of doing things? I always said that it is impossible for me to understand that every single government employee is incompetent. Every physician is greedy. Something is wrong here. And that wrong was the architecture was wrong. And we knew that we could incorporate AI and make it better. So for me, that journey was one of wait, wait, wait.

**[0:45:56] Gianrico Farrugia:** 10 years ago, begin to jump in. Six years ago, really jump in with our platform. And then, of course, in November 2022, things changed again.

**[0:46:05] Peter Lee:** Yeah. When did this idea of a data platform, what you now call the Mayo Clinic platform, by the way, I refer to this as MCP, which I always spark a little bit because, of course, for those of us in computer science research and the AI research, MCP, has also become quite a hot topic because of the model context protocol version of this. But for Mayo's MCP, when did that become a serious defined initiative?

**[0:46:42] Gianrico Farrugia:** So around the end of 2018, beginning of 2019. At that point, we knew that we were going to do something differently. we came up with a strategic plan as I took on the job, that we needed to cure more patients. There are just not enough cures in the world. There's too much suffering. And that we had all these chronic diseases that people have accepted are chronic, but really the only reason a disease is chronic is you haven't cured it.

**[0:47:09] Gianrico Farrugia:** And physicians have been afraid to talk about cure because, of course, eventually everybody passes away. But I really pushed hard to say, no it's okay to talk about cure it's okay to aspire to cure the second was connect connecting people with data to create new knowledge and that's where it became clear that data were not currently in a format that were particularly useful by the way you'll hear me talk about data on the singular and the plural i'm old school i talk about data as plural but i know that most younger people now use data singular and i apologize if i'll go through that and then the third was transform.

**[0:47:48] Gianrico Farrugia:** Let's use Mayo's resources to transform healthcare for ourselves and for others. And that's the concept of if we are able to use data in a different way, let's create a different architecture. And that architecture had to be very closely linked to using artificial intelligence in order to create better outcomes for patients. So patients can live not only longer lives, but healthier lives. And that's the genesis of MCP, Mayo Clinic Platform. So I'll timestamp that as end of 2018, beginning of 2019.

**[0:48:23] Gianrico Farrugia:** So I'm really wanting to delve in, in this episode,

**[0:48:28] Peter Lee:** in this conversation, you know, the mindset of a health system or hospital CEO. And so you're obviously thinking about, I guess, machine learning and predictive analytics and so on. What were the kind of, like in 2018, what were the outcomes that you were dreaming about from this? So if you had this thing, what were the things that you were hoping to be able to show or

**[0:48:59] Gianrico Farrugia:** kind of produce as results? So first of all, I think all of us who work at Mayo Clinic, and this tends to be a bit sugary, but it's true, strongly feel that we have a responsibility to leave the place better than when we started. And so the Mayo brothers, when they started, did two really important things. The first was that they created the first integrated healthcare system. And the second, they created the first unified record. And that record was of course paper at that point.

**[0:49:32] Gianrico Farrugia:** Part of that is to say, okay, what does it look like now versus how can we improve what we have if it'd be blasphemy to say, let's think of ourselves as the Mayo brothers, but let's think of ourselves as reasonably smart people at Mayo Clinic, really lucky to be surrounded by very smart people with resources. What will we do? And so we said, let's not aim for the low-hanging fruit. Let's aim to get at whatever you want to call it, the intractable knot, the hardest problem, and that is clinical care.

**[0:50:05] Gianrico Farrugia:** Let's improve clinical care. Yes, we can deal with burnout. Yes, we can deal with administrative burden, but let's not focus on that. Let's really create an architecture that allows us to tackle better clinical outcomes. and by starting there then everything flows from that that it's not really worth doing unless at the end of the day people are experiencing better health and so uh i i know

**[0:50:37] Peter Lee:** a very good colleague and friend of mine john halamka you ended up hiring i thought he was a very interesting choice because he is of course in terms of technology quite deep and very expert But he's, I think, first and foremost, a doctor. And so I assume you must have had to decide what type of person you would bring in and what kinds of people you would bring in to try to create such a thing. What was your thinking around the choice of someone like John?

**[0:51:07] Gianrico Farrugia:** It was one of the harder decisions. First of all, physician myself, we tend to want to maintain some control. So now I am the CEO and I have to give this baby to somebody else. That's very hard. Second is Mayo Clinic is really good because it is flat. And we run a lot by committee. But it also means that, therefore, you have to work really hard at change and you cannot change by fiat. You have to change by convincing people.

**[0:51:44] Gianrico Farrugia:** So I've always made the point that the right change agent is a servant leader, because that's how change becomes embedded. But it also means you've got to have that personality, the male personality. And it became clear when we interviewed, there were some people that were really hardcore tech, others that were passionate about social issues. but John really fit that of being as you said deep in IT but also himself very aligned with the Mayo Clinic values it's as if he was a Mayo Clinic physician even though he wasn't and that came together and I felt we felt that as we were hiring that we could do it and then we did something interestingly we paired John with a we created

**[0:52:33] Gianrico Farrugia:** the role of a chief medical officer for the platform, which was a long-standing Mayo Clinic physician. And so we brought them together so we could get the past and the present and the future working together.

**[0:52:44] Peter Lee:** So I'm going to ask you about what has come out of this. But before that, let's get back to this origin story. So now all of that is being set up starting around 2018. But then, you know, in 2022, there is generative AI. Now you are already experimenting with transformers and starting with BERT out of Google there. So maybe that's a couple of years earlier, but still there has to

**[0:53:13] Gianrico Farrugia:** come a point where things are feeling very disrupted. Yeah. So, you know, it really wasn't. it to me was a relief because it gave this we were feeling pretty good about what we're doing we were feeling a little impatient but in true mayo fashion we're willing to sort of do everything take its time take it to the right committees get the right approvals and get it done and so when geroncf ai came for us it's like i wouldn't say we told you so but it's like ah there you go here's another tooth this is what we've been talking about now we can do it even better now we can move even faster now we can do more for our patients

**[0:53:58] Gianrico Farrugia:** it truly never was disruptive it truly immediately became enabling which is strange right because something as disruptive as that instantly became enabling at Mayo Clinic and I'll take um as I as I think about it with you and take a moment to think and reflect on it, I think there were a couple of decisions we made earlier on that really helped us. We made the decision against the advice of any consulting firm to completely decentralize AI at Mayo Clinic six years ago.

**[0:54:30] Gianrico Farrugia:** And we told our clinical department, you need to own this. You need to hire basic scientists and AI. We'll help you by creating the infrastructure. We'll help you by doing all the rest. We'll have the compute. We'll have the partners. You need to do this on your own. you need to treat this the same way as if a new radiological technique happened or a new surgical technique happened and so there was a lot of expertise already present in a very diffuse way that then we were able to layer on gerundive ai uh onto that and we found a very willingness to embrace it in fact i would argue initially a bit too willing because as you know we haven't quite

**[0:55:09] Gianrico Farrugia:** figured out what's legitimate use what's not use we all learned together uh but but it was mostly energy which is really interesting it was mostly energy wow and um you know it's it's an

**[0:55:23] Peter Lee:** amazing thing to hear because um one common theme that we hear is that the initial reaction is oftentimes one of skepticism in fact i've been very open that even i initially had some skepticism was that not present in your mind or in your team's mind at all at the beginning so you're

**[0:55:43] Gianrico Farrugia:** asking a physician if they are skeptical about something yeah i wonder what the answer to that is we absolutely the first hallucination the first wrong reference can you imagine if you write the grunt and the wrong reference comes as you know earlier on when some references were being made up And so massive amounts of skepticism, but the energy was such there that the people were skeptical were also at the same time saying, let's do a rag to clean up those references.

**[0:56:18] Gianrico Farrugia:** Let's create, we were experimenting with discharge summaries, but let's use AI to police AI and let's see what's going on. So there was more massive skepticism, but the energy was pushing that skepticism into a positive versus into a negative frame. Now, I say that summarizing in hindsight. Day to day, much more complicated than that. But overall, if you just, and remember, I had been at the World Economic Forum many years ago and had said healthcare needs to run towards AI.

**[0:56:54] Gianrico Farrugia:** If healthcare was perfect, we would wait. Healthcare is not perfect by any means. Therefore, let's run and embrace AI. And sort of that mentality was part of who we were because at the same time, we were also saying the other thing, that we need to be ones to lead validation. We need to be ones that set the rules. We need to be participating in the creation of CHI. We need to be participating in the National Academy of Medicine.

**[0:57:18] Gianrico Farrugia:** So people did feel that Mayo was being fairly responsible about it, but that urge to the needs of the patient come first was the driver that kept people wanting to say, not ready yet, but let's make it ready. And we now have 320 algorithms in the practice and they run and we constantly are looking and seeing what else we can do to improve. But as you well know, things evolve and change. And we're also looking and seeing which ones work and which ones don't and which ones we have to work together on to make better.

**[0:57:53] Peter Lee:** Yeah. You know, of course, Mayo has such a, you know, such a reputation and is so influential. But in the world of healthcare, let's just focus on the United States to start. How common is this experience? You know, so if you are at a meeting with fellow CEOs of hospitals and health systems, What is the attitude? How common is the approach to all of this?

**[0:58:24] Gianrico Farrugia:** I think it's more common now, but going back a few years, I think it's fair to say that it was scary for people to know how it's going to change things. Healthcare runs on very narrow margins. it's very expensive and so your expenses and your revenue are both massive and they are very close to each other so anything that changes that balance is really scary because it's not like you have the opportunity to erode into a margin or get it right the second time so i think that is what drove a lot of what drove a lot of the initial hesitancy was one is lack of knowledge and two, understanding that you didn't have a lot of room to make

**[0:59:09] Gianrico Farrugia:** a mistake.

**[0:59:10] Peter Lee:** On the economics of this, when you are embarking on what I suspect is a very expensive initiative like Mayo Clinic Platform, how on earth do you justify that early on?

**[0:59:26] Gianrico Farrugia:** So again, I'm trying hard to try and remember how things were versus how I think about them now. So it goes back to our history. Mayo has always invested in what it thinks is the right thing that is coming. And that's how we've stayed where we are. So the investment really was having an open discussion. Is this worth it for our patients? And once that discussion was over, then the board was saying, go, go, go. Now, we are lucky in that we have the size that we're able to hire and absorb.

**[1:00:04] Gianrico Farrugia:** We're lucky in that the people who came before us have been financially astute, and one of our values is stewardship. And we're lucky that we had a lot of patients at Mayo Clinic who were able to listen, be inspired by, and be willing to help support. And so that gave us the ability to build what we're doing, not only into the long-range plan, but actually into the yearly plan. And so we built it into the yearly plan.

**[1:00:38] Gianrico Farrugia:** We set up a center for digital health. We set up a platform. And then we set up the budgets to be able to do that. And the budgets came from assets we've had, assets that we would get as the year came by, and then from philanthropy. We also had a really powerful calling card. And that's one advantage I had. And I've been very open when I was speaking to other CEOs that I would use it, is that right at that very beginning, really, really in 2019, our cardiologists, both the researchers and the clinicians that come together and had used electrocardiograms to create an AI algorithm.

**[1:01:25] Gianrico Farrugia:** The first one was for diagnosing from an electrocardiogram, which is very cheap, very easy to do, left ventricular dysfunction. That's how hard the left part of the heart contracts. If it doesn't do well, you get heart failure. And they were able to show that that algorithm was already making nurses better than the physician without the algorithm. And after that went on to show that you could do it from a single strip, really with an area under the curve for that single strip on a watch that was as good as mammograms or pap smears.

**[1:02:01] Gianrico Farrugia:** And so we already had that proof. That quickly then came into Mayo. We put it into it so that any patient now can benefit from it. And now there are, I think, 14 algorithms just from that same one. So we had a proof of concept, thanks to those really far-seeing cardiologists, that enabled things to happen a little faster. And also, as I talked to other CEOs, enabled me to say, this actually works. This is the path forward.

**[1:02:31] Gianrico Farrugia:** I've recently been vocal about also saying, we are at a point now where I believe that for some medical conditions, it is not right to not use AI to help treat them.

**[1:02:43] Peter Lee:** Oh, that's so interesting. So I think I want to get into another topic here, which is when you think about the use of AI and data, what are some of the results that maybe are top of mind for you or you think are particularly important? And if you don't mind, I'd like to see if we can think about this, not only in terms of results, in terms of patient outcomes, but in your other activities, core activities like research in the education mission, and then even in the broader impacts on the healthcare system.

**[1:03:22] Peter Lee:** But maybe we start with patient outcomes.

**[1:03:25] Gianrico Farrugia:** Yeah, they're all linked, right? They're part of the same ecosystem. We think of ourselves as three shields, research, education, and the practice, and that one goes into the other. So, as I said, we have about 320 AI algorithms from the practice. Some run on every patient, some run on some patients, and we have good evidence for what they do. So, some specific examples, and then I'll get into the transformer part of this. we have a program called CEDAR, and like most other people, like acronyms for things.

**[1:04:02] Gianrico Farrugia:** But what it is in our hospitals, with patient consent, we monitor vitals, we monitor in the patient room, not in the ICUs, in the patient room, we monitor all sorts of things. But there's a camera in the room, and we have a team of intensivists, nurses and physicians who do not have any patient responsibilities, but are just monitoring the algorithms. And when the algorithms are predicting decompensation, they're able to get into the room. And what we've shown, for example, with that algorithm is we've shown we've decreased length of stay in the hospital, decreased transfers into the intensive care units, and interestingly, decreased mortality and morbidity, which is not easy to show.

**[1:04:51] Gianrico Farrugia:** I talked about the electrocardiogram as a good example. Of course, everybody knows about the radiology things. We've created, taken part of this and said, if we can do this in the hospital, why cannot we do it in patients' homes? So being very active in looking after patients that would come to the ED emergency room would normally be admitted and we say no here are the things we can give you go home if you want to and we take we will safely look after at your home and we recently have been looking at the last two years of data i've been able to show that we're also successfully able to give intravenous chemotherapy in patients homes because we can monitor we

**[1:05:33] Gianrico Farrugia:** can do all the things that we can do. Now, with Gerative AI, that gave us many other opportunities. One biggest opportunity for me has always been digital pathology. When we see how pathologies currently run with a glass slide, not much has changed in many, many, many years, right? And so really, we have made a massive push to digitize pathology, not just for us, but for others, but talking about ourselves. We started by saying, it has to be very cheap to digitize.

**[1:06:04] Gianrico Farrugia:** So work, and created a company with partners called Pramana that allows us to digitize slides relatively cheaply using AI algorithms that take away the dirt, the fingerprint. And so we end up with 21 million of our slides digitized and that gives you now a massive opportunity. We worked with another company called Agnostics to create what we call Atlas, which is an LLM that allows us to then build upon it. And we, I think 120 years ago, invented frozen sections at Mayo Clinic.

**[1:06:46] Gianrico Farrugia:** So what that is, is that while the patient's still on the table, you can take a piece of tissue, look at it, and tell the surgeon the margins of what you're trying to resect are clear or not. But as a result of that, because you have to hurry, you get no information as a surgeon about is it an invasive cancer, non-invasive cancer, other things. So we've just found a way to digitize our frozen section practice and we'll completely go across the enterprise with AI-enabled digitized frozen sections, which then enables us to then do it for anybody across the globe if we need to.

**[1:07:22] Gianrico Farrugia:** And then in the genomic space we're working to create a true exomic transformer that is short range and we originally started doing it to see if we can test it against the fact that 40% of people with rheumatoid arthritis don't respond to the first line therapy right but you have to wait six months to find out and we found that we can actually do that but it has much greater uses of course and then we're working with you i don't know how much you want to get into this peter or you want to talk about it yourself, Myra too, which is really exciting about how taking a simple problem, can you create a transformer that is able to detect

**[1:08:02] Gianrico Farrugia:** lines in the chest or the right place, breathing tubes in the right place, and then do it in a way that then can be used for many, many other things. And then you, Peter, because you asked about education and research, imagine what this does now to the education system, right? And so we've got to train our physicians differently. We now have an AI curriculum for all our medical students. We offer masters and PhDs in AI. We think it's essential for the people who want to be able to truly become experts the same way I became an expert in my area of research.

**[1:08:36] Gianrico Farrugia:** And then from a research standpoint, when you think about all the registries that exist in people's labs, all the spatial genomics, all the epigenomics, all the omics that exist, and if you are able to coalesce them into one big, what we call an atlas, how that could really spur research at a scale that we haven't thought of before. And so that is our aim at the moment. From a research standpoint, we are with Vijay Shah, who's our Dean of Research, is to say, let's make the effort of making sure all the data are available to be able to use and enable for us to take advantage of AI.

**[1:09:21] Gianrico Farrugia:** And that is not easy because, of course, people have collected the data. They tend to want to embrace it. So there have to be the right incentives, the right privacy, and the right ways of doing it. And we think we're on the way there. And we're already seeing some advantages from doing it this way.

**[1:09:39] Peter Lee:** So we're running short of time. And so I always like to end with one or two more provocative questions. And, you know, it's attempting to ask you the provocative question of whether you think AI will ever replace human doctors. But I don't want to go there with you. In fact, as I thought about our discussion, I was reflecting, we were at a conference together once and I was on stage in the fireside chat. And then, you know, after the fireside chat, there were audience questions.

**[1:10:07] Peter Lee:** And I don't remember any of the questions from the audience except yours. And just to remind you, you know, I think when I was on stage, we were talking about a lot of practical uses of AI to, let's say, reduce administrative burdens and so on in health care. but you got up and you've, I won't say you scolded me, but you more or less said, is it the right idea to use AI to optimize today's somewhat broken healthcare system, or should we be thinking more boldly about, you know, a more fundamental transformation?

**[1:10:47] Peter Lee:** And so what I thought I would try to close with here is to hear what was really behind that question? What were you trying to get me to think about when you asked that question?

**[1:11:03] Gianrico Farrugia:** First of all, darn your great memory. Belated apologies. It was by far

**[1:11:14] Peter Lee:** the best and most sophisticated and I think thought-provoking question of all of the ones that came out of the audience.

**[1:11:20] Gianrico Farrugia:** What I was trying to get to is actually trying to clarify it in my own head and then ahead of others is that we do not need to have a linear path to get to where we want to get to. And we seem to be on a linear path, which is let's try and reduce administrative burden. Let's try and truly be a companion to a physician or other provider. Let's make their problems better, make them feel better about providing healthcare.

**[1:11:48] Gianrico Farrugia:** And then in the next step, we keep going until we get to, now we can call agenticare, I would ever want to talk about. And my view was no, is that let's start with that aim, the last aim, and do the others because the others will come automatically if you're working on that harder problem. Because to get to that harder problem, you'll find all the other solutions. I was just trying to push that here's this wonderful tool that's been given to us.

**[1:12:19] Gianrico Farrugia:** Let's take advantage of it as quickly as we can. And I think we had gotten a little too sensitized to need to say the right things. Careful, be very careful versus saying massive opportunity, do it right and healthcare will be much better. Go for it.

**[1:12:39] Peter Lee:** Well, I think I understand better now where the vision, insight, and frankly, courage to take on something as ambitious and transformational as the Mayo Clinic platform and really all of your leadership in your tenure as the president and CEO of Mayo Clinic. I think I understand it much better now. So Gianrico, it's just always such a privilege to interact with you and now to have a chance to work with you more closely. So thank you for everything that you do.

**[1:13:15] Peter Lee:** And thank you for joining us today.

**[1:13:17] Gianrico Farrugia:** Thank you for making it so easy. And thanks for giving us this opportunity to do good for the world.

**[1:13:32] Peter Lee:** Gianrico leads what is arguably the crown jewel of the world's healthcare systems. And so I feel it's such a privilege to be able to talk and sometimes even brainstorm with him. Our conversation, I think, exposed just how tech forward Gianrico is, as he charts the strategies for healthcare delivery well into the future. And as I've interacted with many others, what I've learned is that this is a common trait among major health system CEOs. Roughly speaking, like we've seen in previous episodes where doctors and med students are polymath clinician technologists, the same thing is true of health system CEOs and other leaders.

**[1:14:14] Peter Lee:** AI, in the mind of a health system CEO today, is not only a technology that can transform diagnosis and treatment, but it's also something that can have a huge impact on the business of healthcare delivery, the connection of healthcare to medical research, and the journeys that patients go through as they seek better health. These two conversations show that virtually all leaders in health and medicine are confronting head-on the opportunities, challenges, and the reality of AI.

**[1:14:44] Peter Lee:** And they see a future that is potentially very different than what we have today. I'd like to thank Umair and Gianrico again for their time and insights. And to our listeners, thank you for joining us. We hope you'll tune in to our final episode of the series. My co-authors, Carrie and Zach, will be back to examine the takeaways from our most recent conversations. Until next time.
