The Peter Attia Drive - #91 – Eric Topol, M.D.: Can AI empower physicians and revolutionize patient care?

Episode Date: February 3, 2020

In this episode, Dr. Eric Topol, founder and director of the Scripps Research Translational Institute, shares how artificial intelligence and deep learning is currently impacting medicine and how it could transform the healthcare industry, not only in terms of the technological advancements, but also in restoring the patient-doctor relationship for better patient outcomes and experiences. We also discuss Eric’s rich and fascinating career in cardiology as well as his involvement as one of the first outspoken researchers to question the cardiovascular safety of Vioxx. We discuss: Eric’s background and his source of interest in cardiology [3:15]; The US medical field’s resistance to technological change and learning from other healthcare models [11:15]; Eric’s mission at the Cleveland Clinic [20:15]; How Eric helped to elucidate the issues with Vioxx (and why he came to regret it) [29:45]; How Eric came to found one of the most influential research centers in the world [47:30]; How AI and deep learning is currently impacting medicine, and the future possibilities [56:30]; Gut microbiome—Its role in health, impact on glycemic response and fuel partitioning, and how deep learning could improve our research and treatment [1:17:45]; Why machines combined with human doctors is superior to one without the other [1:32:00]; How AI and machines can reinstate medicine as an attractive career (and alleviate physician burnout) [1:36:45]; Eric’s dream experiment [1:47:15] and; More. Learn more: https://peterattiamd.com/ Show notes page for this episode: https://peterattiamd.com/erictopol Subscribe to receive exclusive subscriber-only content: https://peterattiamd.com/subscribe/ Sign up to receive Peter's email newsletter: https://peterattiamd.com/newsletter/ Connect with Peter on Facebook | Twitter | Instagram.

Hey everyone, welcome to the Drive Podcast. I'm your host, Peter Atia. This podcast, my website, and my weekly newsletter, all focus on the goal of translating the science of longevity into something accessible for everyone. Our goal is to provide the best content in health and wellness, full stop, and we've assembled a great team of analysts to make this happen. If you enjoy this podcast, we've created a membership program that brings you far more in-depth content if you want to take your knowledge of this space to the next level. At the end of this episode, I'll explain what those benefits are, or if you want to learn

more now, head over to peteratia MD dot com forward slash subscribe. Now without further delay, here's today's episode. I guess this week is Dr. Kirk Topel. Eric is a very famous cardiologist, geneticist, and digital medicine researcher slash pioneer. He's the founder and director of the script's research translation institute TSI. In part coming to scripts he served as the chairman of cardiovascular medicine at the Cleveland clinic, a post he held for about 15 years. We actually start the interview by talking about the story that led to him leaving the Cleveland clinic. And actually we spend quite a bit of time on this story which is something that I certainly remember following during its

unfolding in the early part of the 2000s. He's also the editor-in-chief of Medscape and in 2012 he published a book called the Creative Destruction of Medicine. What we talk about today, though, is his, I believe his third book, but it could be his fourth, called Deep Medicine. And this is something I've been wanting to talk with Eric about for some time, because it really goes into in a non-sci-fi way, the application of artificial intelligence, deep learning, machine learning in medicine, which is, as you probably

realize, a field that is at times upsettingly slow to adopt to technical change. We talk about a lot of things in this episode, and in a surprisingly brief period of time for one of my podcasts, actually, we talk a lot about the gut biome, and I actually have a great, and spirited discussion about it, because as some of you may know, I'm kind of a skeptic of this whole gut biome is going to be the answer to all of our, all of our woes. But I think in the end, Eric and I really kind of end up being much more closely aligned in our views of the utility of this tool as a way to provide

predictive insights. In fact, there are a number of things that I came out of this episode with some follow-up notes for myself as far as people I want to connect with, researchers that I want to connect with to better understand how I can utilize that information for some of my own clinical interests. I think what comes across in the end of this discussion is that doctors aren't going anywhere. And in fact, Eric has a slightly contrarian view of what the impact of AI and medicine will be.

He argues that it's not at all that doctors are going to go away. It's just that doctors are going to change their focus and frankly focus on the one thing that doctors and humans in general can do far better than machines. So with that said, I hope you enjoy my conversation with Dr. Eric Topo. Eric, thanks so much for coming over on a Friday afternoon. Great to be with you, Peter. This is kind of funny because we've both Lipton San Diego for over 10 years and your name comes up all the time. I have everybody says to me, you must know Eric Topo and I say, well, of course I know of him,

but no, I don't know him. And where it really comes up is every time I'm at Dexcom. And obviously you're on the board there, and I know Kevin, say, are very well, and I met several folks on the team. So it's hard to believe this is the first time we're meeting. It is. I've heard a lot about you over the years, Peter.

Now, you mentioned Dexcom. I've been on their board for nine years, and I've watched this early medical, wireless world of sensors be transformed. So that's been really a privilege. Whereas most people think about steps as a wearable sensor, not glucose. So, you know, it's been a great company that started nine years ago, at least when I started with them, It's been a great company that started nine years ago, at least when I started with them, they were really having a rough time to get people with type 1 diabetes to use continuous glucose, and that's really changed a lot. Yeah, Kevin and I met about four years ago on an airplane. I still refer to it as certainly one of the top two luckiest seating assignments I ever had

to be sitting next to Kevin and immediately clicked and never taking the sensor off sends. You can see I'm wearing my G6 rail. And I agree. I mean, it's sort of comical when people think about the number of steps one taking as a quote-unquote wearable or a valuable insight when you think about what could be measured in the interstitial fluid. And glucose, of course, is just the thin end of the wedge on that. Exactly. I think a lot of people haven't realized how where this is headed. The more concern of course is using in the right people. That's like for example the Apple Watch for heart rhythm where so many people are using it and it's a recipe for false positives. But if you use these sort of things, these more advanced

sensors properly, they could be really a big different. You're one of the earliest adopters of mobile telemetry and mobile devices or outside of hospital devices, ambulatory devices, to be able to measure heart rhythm. I wasn't even planning to ask you about that, but I can't resist at this moment. Give people a little bit of background about you. Obviously you're a cardiologist. We're going to talk about what you've done at the Cleveland Clinic and what you've done here at Scripps, but what interest did you in cardiology in the first place?

Well, it wasn't really cardiology that got me into medicine. It was the interest in endocrinology. My father had been a type one diabetic and had every complication you can imagine was blind by age 49. So I decided that since that seemed to be such a primitive area as far as no prevention and lack of treatments outside of insulin that maybe that would be the way to go. And so when I went to UC San Francisco for my residency, it was really to get geared up to be a diabetologist.

And what happened there was I was completely transfixed by what was going on in cardiology, particularly kind of chateurgy who's been a medical hero of mine, had a big influence in really changing the path. It was also a very remarkable time in that it was the first balloon angioplasty, the coronary arteries, the first clot dissolving therapy for heart attack, and so many other things that it was captivating. So I've never regretted that change, but it wasn't what I had initially in mind. The field of cardiology today is so specialized. It's, I mean, to say that one would do a residency in medicine, followed by a fellowship in cardiology, would be as broad as doing a residency in general surgery today, where the field has maybe stayed in another way. An interventional cardiologist versus a lipidologist would have virtually nothing in common outside

of their foundational training in cardiology. I mean, I don't know that many people actually appreciate that outside of medicine. You know, you're really right, Peter. There's the sub-specialties. It could be a heart failure or a prevention or the plumbers, interventional or the electrician and electrophysiology and on and on. So it's a very broad discipline. The field has matured so much in the last decade or two. There are obvious benefits to that.

What do you think are the limitations of that stratification? Well, the major limitation is that you get this ice-pick view of the patient. You know, when you see a patient as an interventional cardiologist, you're thinking about what arteries can I fix, and the electricians are thinking about the person as having an arrhythmia. So the general cardiologist, which is the group of people that would be the advocates to prevent unnecessary procedures, they don't get enough respect, it's just like, you know, primary care, internal medicine doctors.

And so, we really want to boost them up because they are the ones that are really caring for patients and looking out for their overall cardiovascular health. How long ago did you sort of get the sense that we didn't have to be in the hospital with a 12 lead EKG on a patient to appreciate what was happening in the conduction system of their heart? And in fact, I feel like I even remember seeing you on TV 10 years ago on CNN or Good Morning America for all I know.

I honestly can't even remember. But you were in a clinic and you were sort of saying, look, there's going to be a day when a patient at home is going to wear a device and it's going to send me a warning sign that something is going on. Right. Well, it's interesting you bring that up because it was kind of a serendipitous connection to San Diego. So it was, I think, 1999.

I had gotten to know the folks at Cliner Perkins pretty well, and this guy broke buyers contacted me. And he said, you know, we're looking at this company called CardioNet. We don't really understand this thing about being able to do electric cardigan monitoring over the internet. Could you look at this thing? I'm going to send you the slide deck.

So it was, you know, 1999, 20 years ago, I looked at this thing and said, whoa, this is an eye opener. And it was a San Diego-based company. And you were still in Cleveland at the time? Yes, yes. And the whole idea was things were starting to really converge of the idea, at least, of medicine and the internet.

But the sense that you could monitor people remotely, continuously, for multiple leads of their cardi-gram was really exciting because up until that time, the only way we could do that was to put on one of these bulky, halter monitors. That's a Norman halter from the 1950 version. We still talk about his name. There's still, still using it. And you know, that is, you can't exercise really. You can't take a shower.

You know, it's, you can't wear this too long. And it isn't real time. You then send it in and you know, you get, or you go back to the clinic and take it off. And so it's so antiquated when you think about it. So the idea that we could transcend that era with this mobile, continuous monitoring. And by the way, there are people who have been on a halter who died suddenly. And the halter, of course, serves no purpose other than to tell you what arrhythmia killed

them. Exactly. So now it's a whole different world, and then you start to wait, wait a minute. Why don't we just do everything? Not just a card. We could do all the vital signs. We could get rid of hospitals or at least those hospital patients who are not in an intensive care unit. And I think that's where we're headed. That is 20 years ago was kind of the entry point where we just first dedicated wireless company card unit, and it's just where we're going to build on to ultimately eradicate the need for most hospital rooms, which is

a pretty big deal. And it's probably the most transformative aspect of where we're headed because that's the number one item for healthcare costs. It's not just the facilities, but the personnel. And so they account for a third of our $3.6 trillion annual healthcare budget. Medicine seems to always take longer to adopt things. I mean, I think in general, as people we tend to have optimism that exceeds the pace at which, you know, technology moves forward. I mean, in some ways, engineering examples get overused. We talk about the Manhattan

project, which is kind of remarkable when you really stop to think about it. That in such a short period of time, they could go from a proof of concept in the early 40s to a finished product in 44. Even the space race is kind of remarkable in terms of the accuracy with which they were able to sort of project and map out the steps. It doesn't seem that healthcare follows that curve. It doesn't just follow a straight Moore's law. Well, it actually defines Moore's law. If you plot that out, you look at, wow, the cost of chips is gone.

So incredibly low over the, of course, 50 plus years, and healthcare costs are going the opposite direction. So they're at lack of embracement of the digital era, and also the lack of it having the impact of lowering costs is notable. It's palpable. It's a general resistance. You know, I liken it to a sclerotic or ossified nature of the medical community very resistant to change. The only time you see lack of resistance when

it is tied to markedly improved reimbursement, for example, the adoption of robots like Da Vinci or something like that. But otherwise there's just no real incentive to change. And of course we want to be careful because we don't want to adopt a significant change when it isn't validated or proven. But when we see things that are unquestionably advances and still unwillingness to move in that direction, that's disconcerting. Yeah, it is. And there are a few problems I've contemplated where no matter how much time and energy I put

into it, I really can't even see the direction of the solution. I think there are some problems, even the political system, when you think about how broken our political system is. I don't think you have to be a student of political science to appreciate that. But I think most people who spend a lot of time thinking about it, if given a magic wand, would know how to move in the right direction. Right? If you stop cherrymandering, if you maybe discarded the

electrical college, there were like five things that you could do structurally that would bring politics back into a sort of more civilized era. But if you said to me, wave a magic wand, how do you fix medicine? The only idea I've ever had is one that involves changing behaviors directly, which of course becomes a bit of a totology. But it seems to be that the disconnect between the driver of demand and the one who pays the bill is the biggest problem.

Does that kind of resonate with you? In other words, in this system, which is not a budget-driven healthcare system like it is in the UK, it's a demand-driven system. So the system will rise to the cost of the demand. The demand is mostly driven by the patient in the physician, the patient requiring the care, the physician ordering the treatment. But they bear less than, I mean, they bear maybe, I think the last thing I saw said about 11% of the total cost is born by those driving demand, which is sort of like you walking into a car dealership,

and knowing you only have to pay 11% of the car price. It's going to completely uncouple any reality. To me, that seems like the elephant in the room, and that's why I think the problem is, as you stated, which is why are hospitals so expensive? Well, if people actually saw the bill of, you know, a hospital stay and realized what the, you know, the gauze and the pillowcase were being charged for, I mean, they'd scream, but of course, they don't have to pay it directly. They're only paying it indirectly. Right. It's a really messed up system in so many respects. You touched on one big one, but the basis is absurd healthcare charges.

It's just unfathomable. And all the things that have been done to date, like Obamacare and the debate now about Medicare for All or whatever, doesn't get to the root of the problem, which is the cost. That's right. It's politically invoked to deal with access, which is an important problem, absolutely. But if you expand access without reducing costs, you trade one bad problem for another bad problem. That was so educational for me, because over the past year and a half,

I worked with the NHS to review their health system, in particular, the impact of technology, AI, digital medicine, genomics. And as you already mentioned, Peter, they have a system which can be changed like a light switch. They don't have a single pair and they have far better outcomes than we do at about a third of the cost per person. And what's interesting is they have the will to make these changes. They're adopting things at a rate that is, there's no comparison to the US. Like, for example, they already have places in the UK where they've gotten rid of keyboard instead of doctors typing and being data clerks, but they're also interested in making things more efficient

than they already are more efficient than we are. But the difference is the incentives, just as you outlined, this is not employer-based healthcare, this is not copay-related, this is healthcare for everyone, and we're going to make it as good as we can and as least expensive as we can.

So that country is, in many respects, a different model, Canada is like it, and many countries in Europe are similar. And we're so remotely disparate, it's just unfortunate. You know, I grew up in Canada, so I have sort of mixed feelings about the discussion of a single pair system because I've seen the advantages of it and you've outlined them. I don't know as much about the NHS, which may be better than in Canada, it's not national,

it's done by each province, but it's still universal coverage within each province. But that said, my whole family is still in Canada and I will say the following, when they get care, it seems to be pretty good. But boy, is it hard for them to get care sometimes? It depends what you need, right? If you need a coronary artery bypass and you have critical stenosis, you'll get excellent care in Toronto.

It'll be no worse than it would be in the best hospital in New York or San Francisco. But if you have a torn ACL, it might take you six months to get that MRI. Now, we could debate whether or not in the long run that matters as much. But I've always found it interesting that at least a country like Canada, and again, you can speak to the UK for me,

there's great resistance to have a second layer of private insurance on top of the public that would allow that, which to me seems like the best hybrid solution, which is you have to have a safety net that provides universal coverage for everyone. But if an individual decides, look, I'm willing to pay an extra $10,000 a year, which by the way is still a fraction of what I pay to ensure my family, you now have a separate queue that you can go into. It's like Disneyland, right? It's like in Disneyland, you can do the special pass where you don't have to wait in line, you pay an extra, whatever it is.

Why do you think that places like Canada for sure, but maybe even the UK have resistance to secondary insurance? Well, they have secondary insurance. People, I have that. In many respect, it works like you just described. I see. So the so the NHS has a second tier that one can buy privately. Yes. The main difference is there's a philosophy that if you're a citizen, as you said, healthcare is a right. It's right not a privilege. Yeah. Yeah. And then there are people that have this added insurance. It does separate a small fraction of people into this other class of getting access to more rapidly to

perhaps a different queue as you outlined it. But for the most part, it's a small proportion of the people in the UK and I think it's somewhat similar in Canada. But I think the difference really is that there's two big poles of problems. If you look at in the US, there's the indigent who either don't have access or if they do, they're just not getting the kind of cure that you would like to see. And then there's the affluent who get too much, they get overcooked, they get executive physicals and they get all this stuff that shouldn't be done. And the outgrowth of that is bad outcomes. They get incidental omnis. You don't see that in the UK and in a lot of other countries.

So we have this problem at both ends and most of the recognition has been on the end of the underrepresented and indigent, not on the people who are getting overcooked, and that's a problem. I interviewed Marty McAree a little while ago, and he's written very eloquently about this problem, specifically with respect to pharmacotherapy. You know, you mentioned executive physical while you're all the moderate, of course, is one of the places that, you know, certainly has to be regarded as one of the finest hospital centers in the United States and then by extension the world. And I feel like I've had half a dozen patients come back from their

executive physicals there or more so ask me if they should go and get it. So when did you, when did you get to Cleveland early 90s? Yeah, you have to 91. And what was the Cleveland clinic in 91? It wasn't as well known as it is now. It was particularly well known for bypass surgery. It was the place where Renee Favallaro essentially invented bypass surgery. And also Floyd Loop had really brought in the internal memory artery, which was a big advance.

It also had some other traditions. I mean, Mason's song had been there, discovered coronary angiography. Was it considered at that time ahead of Minnesota, which was also arguably one of the earliest pioneers? You know, Stanford and Minnesota were really these huge pioneers in earlier cardiovascular medicine. Well, I think in Cardiovascular, that was its signature contribution. I mean, obviously there were others, but it was...

Lilahayat, of course, was, you know, some way in Lilahayat were kind of these gods. Exactly. I think the main, you know, for coronary disease, because there had been so many, a cluster of remarkable innovations. That's where it had its biggest footprint. And when I went there, there was my far more bypass surgery done in Cleveland Clinic than anywhere in the world.

And you had gone after UCSF training, you went to University of Michigan? Well, there was one stop in between. That was at Johns Hopkins where I did cardiology. Oh, I don't think I knew that. Yeah, so we have this one overlap in our backgrounds. Yeah, and then I went to, I was seven years at University of Michigan

my first job, my second job at Cleveland Clinic. It was almost 14 years, but when I went there in 1991, it wasn't a really strong academic center. It was, in fact, I'll never forget my chief of medicine at Michigan when I told him I'm going to Cleveland Clinic, he said, well, that's the end of your academic career. It was viewed as almost going into private practice. It was viewed as well high volume, factory medicine,

high quality, but you know. Did you have a strong residency fellowship system underneath you where you're gonna be heavily involved in training? There was a medicine fellowship system, but I don't know that I would qualify it as strong academically, large, lots of them, but they weren't know that I would qualify it as strong academically. You know, large, lots of them, but they weren't doing cutting-edge research and there wasn't that kind of scholarly environment. So my mission when I went there to refute the Yamada's view that it was the end of

a career was actually to do just the opposite and and liven it and wake up the curiosity and the innovations. So that's what we did. And you know, it was a big transformation because it involved a whole new team, you know, bringing it was like an exchange transfusion because they were, they hadn't written a paper in the cardiology division in a couple of years. Really? Yeah. It was, it was very much dominated by cardiac surgery and it was just limited by

productivity in academic side. So it really comes down to incentives again I mean today we see the opposite problem of course where we have the proliferation of total nonsense journals and Absolute horrible things that don't pass for science being written constantly because of course the pendulum on the incentive is you have to publish. Right. And so presumably at Cleveland, that was simply not the pendulum was the exact opposite, where you were probably compensated based on clinical productivity and nothing more. Yeah, I mean, I think the cardiologist, when I talked to them, when I was interviewing, and then when I got there, beached in, they said, you know, we're the handmaidins of the surgeons.

And they were so busy taking care of the patients because the surgeons didn't really see the patients outside of the operating room and they needed, off the, at this high volume of patients, needed a lot of care. And there weren't that many cardiologists. So the cardiologists would run the critical care and they stepped on units and everything. Everything. Wow. So they really were giving great care, but they were consumed by that. So they didn't really have the time. Nor did a lot of them since it was highly inbred then, really have the knack of asking questions and chasing them down and whatnot.

So we brought in a whole group. I mean, I started. There were 30 cardiologists when I left. There were over 90. Where you brought in is the chairman of cardiology? Right. No, I was age 35. Actually, it was really funny, Peter,

when you think about it, Bill Bellicek and I started the same day. Bill Bellicek was the youngest football coach in NFL history, I had coach, and I was the youngest chairman in the history of Cleveland Clinic. So we got to know each other a little bit. It was a very different era for Bill Bellicek.

Who's my favorite coach, by the way? Is that all right, hasn't it? Oh, I mean, I'm obsessed with Bill Balecheck. I'm that Tony Gonzalez recently. Oh wow. And he told the absolute funniest story about his experience with Bill Balecheck at the Pro Bowl one year, which I won't restate now,

but in the show notes, we'll link to a video of Tony telling that story along with an article that was written up about it, at some point, but I'm fundamentally just obsessed with Bell Check. Well, he's a really easy guy. He's a bucket list for me to meet him at some point. Wow, I know he's a kind of fascinating figure for many reasons.

Actually, one of the most memorable things that happened regarding Bill Bell Check was he benched Bernie Cozar that didn't go over well. And Art Modell who was the chairman of the board of Cleveland Clinic, we were good friends and we even though we're for dinner at our house, this had all happened and it wasn't up for, you know, with the dog pound and everything. So Art and Pat were over and they said, you know, well, he had to put a sign in front of our house. Bill Belichick doesn't live here. But you know, there was as much fear of what was happening then is when Art Moldell moved

the browns to Baltimore. Yeah, so during those almost 14 years, it was great to see this kind of renaissance of it. And you were supported. Yeah, I mean, presumably you would not have left Michigan without an explicit understanding that you were not coming to implement the status quo, you were coming to rattle it. Exactly.

And you know, it was really because of Floyd, as we knew him, Fred Loop. He was a very progressive CEO of Cleveland Clinic. He, even though he'd been a cardiac surgeon throughout his career, and in fact, in the early years, was still operating. He wanted to see cardiology thrive. He saw...

He's not alive anymore, is he? No, no, unfortunately he died of a rare cancer a few years back. But at a young age, because it was a surprise, he had such longevity in his family. He said, Eric, I want you to come in and just completely get this place. Supercharged, make cardiology the greatest anywhere. And I'll back you 100%. And not like that, but in 2000. And year 2000 when I was thinking about leaving, actually go to Stanford. He said, why do you want to go to Stanford medical school?

It's just start one here. And so that gave me the green light to work with Case Western to get a new medical school and there hadn't been one in Cleveland or in the country for 26 years. So that was the show of loop to be a great leader. I mean, he wasn't threatened by cardiology. He wasn't threatened by making it a far more academic environment. He actually saw those odds pluses. He was, you know, an extraordinary leader.

We would have had that second overlap if you'd come to Stanford because I graduated from Stanford, Mexico on 01. Oh, wow. When I was looking here to be the dean, it was just after the divorce. It was like a low time morale. It was. So, so what was his name on blank? And there was a dermatologist who was the dean.

Yeah. Eugene Bauer. Exactly. He was the one. He was the one that I think basically in the failure of that merger it made sense that there was going to be a regime change. I don't know if Phyllis Gardner was ever in the running for it, but I always liked her. She was top drawer.

I was super impressed by her. But a pediatrician. Yes, from Boston and he was there for a number of years. And I know who you're talking about. Yeah, last name begins with the P.I. don't recall it. Yeah, P.O. P.O. Yeah, yeah. Yeah, he had been at Boston in infectious disease, pediatrics, and he was kind of opposite of the Stanford way. He was anti- entrepreneurial, anti- in many respects, innovation. So it was an interesting C. How that worked out. But in many respects, innovation. So it was an interesting see how that worked out. But before I had decided I didn't want to go there mainly.

So that job you were potentially going to take as Stanford was to be the dean, not to be the division chief or a medicine or cardiology. Yeah, no. And I was at the time I thought it was a dream job. I thought Stanford, even though it was coming at a tough time in the wake of this UCSF Stanford breakup. I thought, hey, it's unilateral.

It can only get better. Absolutely, but of course, knowing what I know, the little bit that I know about what it means to be the dean of a hospital, it seems like that would have not allowed you to thrive in the way that you ended up really finding a second home. That's an astute point. You have to know what you're good at, and that might not have been a good fit in retrospect. But I was restless. I was looking for a change.

And in fact, working on getting the new medical school at Cleveland, which we basically got in 2002, and the first class came in 2004, that kept me busy. I always need a kind of big project to know something that's a reach to keep me going. So that was important that it actually was a four-year run on top of the other things I was doing is to get that new med school off the ground. There's something else that happened in the twilight of your career at Cleveland Clinic that I want to talk about because it's on a personal level, it was very near and dear to me, which was your involvement in the uncovering or elucidation of the challenges

with a medication called Biox. This is such an interesting example of, it's a case study in so many things, right? Because I'll state for you at the outset in my bias in this entire story and then I wanna go into the story in detail. If I could go back in time and be bizarre for a month or a day or a year, I would have put a black box warning on viox. I would have left it on the market for most

people who could have tolerated it and made sure that it was very transparent that this is going to increase the risk of a subset of the population. And everybody's happy. Unfortunately, that's not what happened. Merck, I think in the in the hubris of wanting to deny that there was any potential patient subset that could be harmed by this drug ended up spending by my calculation at least four years, probably concealing data. You'll tell us the story and it may be longer. And in the end, a lot of people lost what I still considered should be probably the best Cox II inhibitor that was ever out there. So that's my bias. I could be wrong.

I agree with everything you said. Totally. And we never discussed it. We never met before. No, no. So now let's talk about the story. So tell people what a Cox II inhibitor was and why was it such a big deal when these rugs came out in the late 90s? Well, this was at that time viewed as the most important blockbuster in medicine, biox and telomerex. They were competing with each other. They, I think, introduced right around 99,

and it was a race because this multi-billion is a dollars for each drug. The promise was, instead of the Advil and a leave and other non-steroidal that they would replace, they would spare the stomach, they would be more potent to relieve pain and better in ion flammatories. That was how they were built. And the reason because they were selective, so these cyclowoxygenase enzymes that the

alieves of the world indiscriminately block them, and one of the problems is, yes, you get the anti-inflammation that relieves your pain, but you also rip apart the gastric lining and a whole bunch of other things in the wake. And of course, as you said, celibrex and vox came along and said, we're going to selectively target just cycle oxygenase two, which almost seemed too good to be true, by the way. In medicine, it doesn't often work that that happens, that you can selectively hit one of these two enzymes, but nevertheless that was... Yeah, I mean, they did have some selectivity, but not as much as advertised.

But nonetheless, I wasn't really paying attention to this because... Right, you're not a rheumatologist or an orthopedist, this is not your wheelhouse. No, and I'm not even into drug safety. That was not the kind of thing I was into. And in fact, it was only because this remarkable fellow of ours, Deb Mukherjee, who now is a chief of cardiology in Texas. But at that time, he came to me and said, Dr. Topel, I'm looking at this data from the FDA. And what they're saying is that viox is really not at all causing any heart problems. It's actually that the comparator,

and then an approximate was the one that is decreasing a benefit. That was that was the argument. And I said, well, you know, damn this FDA, they approved this drug. You know, it was a year plus after they approved it. And I said, how did you get this data? Because back then, she get into the bowels of the FDA website wasn't so easy, but he did it on his own. So I give him credit. And I looked at it. First, I didn't believe it, but then we spent quite a bit of time. Now, do you remember the numbers? Because I remember that it was Neproxon.

But do you remember what the absolute risk difference was between Neproxon and Vioxon in that first cohort? Yeah, I don't. There was this trial-called vigor. I don't remember the exact numbers, but it was something like an excess of heart attacks in the Viox arm, Rofacoxid, that was not trivial. If you look at it per hundred people. My recollection, I get it wrong, and we will link to all of this in great detail, so it'll be for those of you listening, this will be completely accurate in the show notes. I want to say it was like 15 deaths per 10,000,

but I don't remember what the baseline, I don't remember what the naproxen number was. Yeah, I think it was 15 per thousand. 15 per thousand or up to 20 per thousand, depending on how you interpret the data, but there was a definite gap. And so first I was questioning Deb, and then we raked over the data,

I said, you know what, you're onto something here. But at that time, Eric, did you think that Niproxin provided cardio protection? No, actually, I said, where did that come from? Okay, so in other words, you sort of questioned the premise. Very peculiar, because there was no data to really support that.

And it seemed like a very odd explanation for this excess of heart attacks. We went over the data and I said, you know what, we've got to publish this because this is really important. And so we put together a paper and went to JAMA. It was published. This was 01.

01. No, it was published in 01. In fact, it was, I think, August 30th, 01. You know what, I remember it so well. I remember where I was reading it. Yeah. It was the summer of 01. It was on the front pages of Wall Street Journal

It was on a lot of other front pages, but there quoted me as saying we could be facing a public health disaster Now did I ever know that that would be the case? Did I ever know that it would be three years later to the date? September 1 that Merck had this abrupt withdrawal. And in the process, by the way, Peter, before we published in JAMA, Merck came out to try to intimidate us to withdraw the paper. Once they heard it, how did they know that the reviewers give it to them for comment?

The reviewers apparently communicated to them that there was this hatchet job on Viox coming, you know. And so they came to us and tried to intimidate us And they also then what I learned from the editor then editor They tried to intimidate her that they would sue jama and it was unfounded and as soon as we published the paper and That was they actually say to you guys well, they said that you know, we did data dredging They they had all the lines. They basically said that we were hacks and didn't have data dredging. Yeah. I mean, all

we did was basically review the data that was filed on the FDA. And by the way, some of the things that didn't get out in the public, there were other small studies that never really got in the spotlight that also showed excess of heart attack. So the signal,, did your jamma study include a meta analysis of those smaller ones as well as the original FDA as the bigger trial? Exactly. And we saw this consistent signal. You saw this pattern. It wasn't a question. And we also saw a lesser signal for shellabrex. It was in the paper. But the one that was just so consistent and you couldn't deny it was with viax. And that was not just compared to an't deny it was with viox. And that was not just compared to naproxon, it was compared to other things.

And you're feeling placebo. And so you're feeling at that point was the naproxon comparison is a red herring. And whether you're doing this against a placebo or ad-vill, and by the way, was there a belief at the time that just general ibuprofen had slight prevention or was neutral? Neutral. Neutral at best. There wasn't any hint that naproxen afforded benefit of protection. So that whole premise was off base. And so we were talking about a difference of one in a hundred and absolute rest. Who went a hundred? Two and a hundred. So one in 50 additional. And at that point in time,

because I think later on, we knew more, but in 01, did you have a sense of which patients were the ones that were at risk? No, I think that we still don't know that. Who was at risk? We do know that 80 million people took viox, which is a lot of people. Yeah, but it wasn't necessarily those with hypertension or those with dyslipidemia. I mean, were we able to sort of stratify it at all? No, in fact, that's the hardest thing is that when there were all these lawsuits of people that had heart attacks,

Merck defended it, saying, well, it could have been their hyperlipidemia and their high blood pressure. And it's very hard, an individual person to ascribe the hit to viox. That's difficult because most people that have severe osteoarthritis are also having comorbidities

that would put them at risk for heart attack. The signal would kept showing up though. Like when Kaiser looked at their patient base, database, they saw it everywhere. It looked, it was a heart attack problem and stroke problem, by the way, but heart attacks especially. And the strokes were hypercoagulable strokes? As best we can tell. Yeah. In fact, when I did the 60-minute segment, it brings me to that idea about we talked about it was right after ViEx withdrawal, and I was upset because Merck was claiming they did everything right, and I knew much better that it wasn't true. In fact, we had called this three years before and they still never took it seriously.

And as you said, they could have just admitted there was a problem. It was in all their emails. It was clearly they knew about it. Wait, there's evidence they knew before your paper. Oh, absolutely. Oh, I don't think I realized. Yeah, I thought it was your paper came out in 01. That was the shot across the bow.

Then they just completely denied it, concealed data that until it became undeniable by 04. I didn't realize prior to 01 internally, they had seen the same signal. Absolutely. No, they had emails they recovered from the, all the way back to, from 99 when FDA approved the drug 2000 well before our paper. Because they did make the argument in 99 that Naproxon was risk lowering, and that's why there was no signal.

But, yeah. Yeah, in fact, the term signal was used at the head scientific officer, and all the people involved in the Vios development, said, well, let's flip it to, the communications experts showed up and, yeah. Yeah, no, the whole thing was just so incredibly contrived and it was all clear that they were in this race

with Pfizer, with celibrex, they didn't want to lose it. $5 billion was on the line and whatnot. But when I went to 60 minutes to discuss this right after the turbulence of the withdrawal, the interviewer, he had just had a stroke on Viox. He never revealed it on the show. I said, well, why don't you, you know, in the, just like we're talking before we actually went on the air, I said, why didn't you tell people that? He says, well, I'm not part of the story. I said, well,

you had a stroke. I mean, that's kind of a big deal. Ed Bradley, you know, I think there was a lot of hits out there. It's a shame because up until that time, Merck had been seen the finally sunk the ship in 04. Well, when they withdrew the drug, there was another new trial. And this one, again, the same exact signal. This was a phase 4. This was a... Actually, I think it was phase 3 for an expanded indication. Whereas the early one was in one condition.

This was in another. It was a large trial. The heart attack thing was right there again. And they just couldn't deny it anymore, especially on top of everything they've been trying to suppress for years. So they just pulled a plug on it. But was there any ramification? No, that's actually when you mention it.

You know, why I never should have been involved with this. I regret it because you do regret it. Oh, absolutely. Because nothing ever happened. I mean, no one at Mother Woods ever believed that had you not written the paper in 01. They still would have withdrawn it in 04. They might have because after we wrote the paper and published it, others started to come alive like Kaiser and others about this signal.

So it was getting more and more undeniable. So I don't know that our paper even though it was the first one and it was in a high profile journal, I think they still would have had a hard time keeping that drug. Well, they might have done what you suggested, Peter, which is put on a warning and keep marking, which is what they should have done. It was a good drug. But the problem was that the doses that they were recommending certain people

were getting exposed. And you say, well, two out of 100's not a lot, but when you have 10 to millions of people, so it's a lot. Yeah, one out of 50 absolute increase in risk for a hard outcome, like mortality is a huge deal, especially if you can't know who that patient is. So this is where, again, because I never, you know, I was in the middle of my residency,

when this was going on and I was a surgeon, so it's not like this was top of mind. I just had a personal interest because I remember using viox and finding it so efficacious and finding it to be personally much better than celebrex and much better than, you know, single day dose thing. I think it took 50 milligrams once a day. I mean, it was like, you know, and I had just had a horrible back injury in 2001, which is actually another story where they'd operated

on the wrong side and I had multiple trips to the OR. So I was really debilitated and in the midst of a surgical residency, Viox was the saving grace for me. But my recollection was, oh, but there's a subset of patients in whom you could sort of carve out to not take it. And that would have been the interesting question.

That would have been the clinical question, which is, like, for example, like if you look at drugs that cause birth defects, something like avid art or de-tasteride or something like that, like don't take it if there's a pregnant woman nearby kind of thing becomes a very clear and obvious way Not that that causes birth defects, but that interferes with the endrogens. I don't know So it's interesting to hear you say that that basically I don't want to put words in your mouth But it almost sounds like you said if you go back in time you wouldn't have done it No, because it wound up being a horrible phase in my career the true nature

Not only during that time after the withdrawal whether threats from whether it's Merck or Friends of Merck, calling up saying, if you don't stop talking about this, this is a bad thing is going to happen to you. I'm never being out of town one night, and my wife got a call like that. You better stop. You better tell your husband to stop saying things about Merck or you're going to regret it. It's hard for people to believe what you're saying, right?

It sounds like the sort of thing you'd see in a mob movie. Yeah. No, it was the worst experience. And then I even had my own institution, unbeknownst to me, the chairman of the board of Cleveland Clinic, a fellow named Malachi, who is a CEO of InvaCare, and Gil Martin, the CEO of Merck, were best friends from Harvard Business School. And so he and the CEO of Cleveland Clinic were basically yanging up to suppress me and gag me and also to turn on me. So I had my own institution, I had Merck against me, it was a nightmare.

I mean, a very terrible nightmare. But without redemption, when Mer Mark finally pulled the drug, you would think that one, it would sort of give people pause to realize that this was, as you said, probably inevitable. And two, it was the right thing to do. Unfortunately, it was too big a hammer for, you know, like I said, there. I was naive. But they were backed into a corner. No, they were, they were in a corner, but you know, to but nobody but nobody came around You know to me it's kind of nowadays. They already talks about truths and and fake and whatnot But to me then was the beginning of seeing that syndrome because here was truth and it was just being basically

turned into fake news by Merck and being basically turned into fake news by Merck, and they had gone years of marketing a drug, mass marketing a drug. You couldn't turn on a TV set without seeing ads for viox. And they never fessed up, and they just, every single patient case that went to court, they basically prevailed eventually, whether it was the original case or the appeals

by this whole inability to prove, for proof in an individual patient. So they didn't pay anything, they were in a institution whatsoever. Nothing that I know that's significant. And most importantly, the executives who oversaw this, who knew exactly what they were doing, they didn't go to jail, they were never indicted, there was never any charge. And no civil suits at all. Nothing. Nothing.

Which is interesting. It tells you something about how difficult it is when the complication is a ubiquitous disease. You see, it's different when you're dealing with, well, and of course, we think of the examples that turned out to be wrong, right? Like the use of silicone, breast implants, and lupus. Well, it turned out to be incorrect, but you at least had a signal to talk about because lupus was so rare or what other connective tissue disorders they were talking about. But as you said, like, how can you possibly look at any individual and make that case, probably holistically, you would need a very large trial to determine that. Oh, yeah, I know. You can't single it out. It's almost impossible. If you had

assays to show that this selectivity of the COX2 inhibitor was pro thrombotic making clot in a person and that person then had a heart attack or stroke, but you know who had that. I mean these were sudden events and no one had a proof in that person that their clotting state has changed from the drug. It seems like that's got to be the most likely mechanism. Oh, yeah, I don't know. The mechanism of how these people went down is not elusive. But what's sad about this, too, Peter, is I had known Roy Vagilus, to some extent. I had the highest regard for this company.

We were doing trials with this company when it happened. And so just to see a company that was reviewed as one of the most ethical minded companies, not just in Pharma, but across all companies, to see it take these tactics of marketing. It's really sad. But of course, that's many years ago. It's 2004, we're 15 years later now. Yeah, but I can hear it in your voice, Eric. It's still quite traumatic. Yeah, it was almost the end of my career. That's what precipitated leaving Cleveland.

And fortunately, coming to San Diego, which was the greatest thing ever, but who would have known for a year or two, it was a question of whether there would be a new position and whether it be suited to things that I would want to do. So how did San Diego, I mean, were you a pariah at the time? Yeah, one of my people who I regarded in extraordinary,

the Pope of Cardiology, Gene Brownwell, he was trying to help me, he said, you know what, Eric, you're radioactive right now. And I was. And I even had people at Cleveland Clinic, by then there was a new CEO and others who were charged to try to nuke me. That is any place I interviewed for a position.

They were calling them and actively trying to take me down. So ultimately over that course of a year when I was looking to move, I started realizing I have to do this in stealth mode because I've got people who are trying to get me and Fortunately a very close friend of mine here in San Diego who I'd known for decades Paul Tierstein Who is it scripts and I had collaborated some with the people at script research and so we started talking They were excited about what I headed vision for and then I was ultimately recruited and

but I had it vision for and then I was ultimately recruited and fall of 2006. And what was the role they brought you into at that time? Because at the time, wasn't scripts, I mean, it wasn't really a clinical powerhouse, it was a research powerhouse. Well, kind of both in some respects, the research is- Was the affiliation with UCSD on the clinical? No, no, purely scripts health.

Purely scripts health, yeah. So scripts, UCSD on the clinical? No, no, purely Scripps Health. Scripps Health, yeah. So Scripps Health was on the move. They had Christian Goerter as the CEO had basically put together, stitched together many different Scripps entities into one called Scripps Health. They were, and are completely different entity than Scripps Research. So TRSI, the translational research institute,

that was totally separate. So totallySI, the translational research institute, that was totally separate. So totally separate, although prior to 2000, near 2000, they were one entity, but it was script clinic then, not this big health system with, you know, multiple hospitals and 30 clinics and whatnot. So what I did was to come in to be a cardiologist at script clinic, but also to develop a new institute that was dedicated to translational research, particularly genomics. That's why I came here. And it was only, you know, within weeks I realized, wait a minute, what about wireless? What about digital? Because you don't want to just rely on a genome,

even though back in 2006, there was tremendous... Now what was Craig Ventner doing at that time? So Craig, had the vendor institute in Maryland He was also working in synthetic biology had a synthetic biology company here and I think he was aiming to develop another vendor institute in San Diego but he as a pioneer of pushing the whole Sequencing project of course in year 2000, announcing it with Francis Collins and Bill Clinton at the White House. But he had moved not just from sequencing, but also to writing the genome with synthetic biology. That was his interest at the time.

I see. Got it. So I came here to try to make human genomics and genetics center stage for the two scripts institutions. Right, and you wanted to translate this as quickly as possible to basically patient care. Yeah, to change practice, which is where's to work on that? But that was a goal. And we basically very quickly, fortunately, we're able to get a big grant called the CTSA grant,

one of the 57 now hubs of that in the country. And with the only one that's not a university or without a medical school. But basically, script research is a storied institution with some of the best life science in the world, ranked number one in nature for innovation and influence above some of the very top known centers. So it has had a phenomenal track record and to work with them, this great brain trust of scientists, and to try to bridge that with this big clinical entity, Schripps House, which is a dominant player in the San Diego region, a big region.

For me, it was perfect. And basically, the big grant we were able to get led to innovation space, you know, just to do whatever you think would be appropriate to make medicine better. And there's no shortage of ways we could do that. And you're also the editor in chief of medscape, is that right? Right. How did you get involved? And I think anybody listening to this who's ever gone onto Google and searched for something

will notice medscape is usually coming up with information. So what is medscape? Yeah, well medscape is the professional side for healthcare professionals of WebMD. The way I got into it was in the mid 90s when the internet was kind of warming up, I started with a couple of friends, the heart.org, which was the first cardiovascular website for cardiologists and anyone working in this space. So we started that and you know, it all about getting great content, getting journalists. And it was for many years a big magnet for not just the information, but also a form for

education and for debates and whatnot. So ultimately, medscape started to cover every specialty and they acquired the heart.org. In that acquisition, being the editor in chief of that, they ultimately asked me, would I be the editor in chief of medscape? So I've done that now for several years. It's been great. How much time does that take? You must, you must have an editorial staff under you because it's such a voluminous,

I mean, it's like an encyclopedia. Yeah, no, they have an amazing crew of medical journalists and they cover everything that moves in medicine. I don't do so much day to day. I set general direction. We have a monthly call to go over features that I usually try to introduce ideas for that. I do a lot of interviews. I try to find, like, you know, this week was the

big Wall Street Journal issue with a Penn Medicine former dean taking on medical education today, saying that it was completely off-base to nurture students on climate change or gun control or any social injustice. And of course, it was a revolt and we're gonna have a lot of that in mid-scape. So I tried to bring up, when I first got involved, the website was much more farm oriented.

And what I've tried to do is round that out with not just devices and medical education, but also the whole genomics and digital medicine, AI, and all those sorts of times. How big is the staff? Oh gosh, there's probably over 30, 35 journalists. Ivan Oransky recently joined as a VP for editorial. He run Retraction Watch, which is really formidable. But, oh, it's a big

staff. It's a for-profit or not-for-profit. Well, it's part of WebMD. It's part of WebMD. WebMD used to be a publicly traded company, but they were acquired about a year ago by a company called Internet Brand, so they're now a private, but for-profit company. I didn't realize that, I should have known that, I suppose, but I didn't realize that I should have known that I suppose, but I didn't realize medscape was under that umbrella. Yeah, and I've always tried to weave in the WebMD side because WebMD has a big reach to consumers. As you pointed out, to kind of go to search for lots of common things in medicine. And we don't do that enough. I'm hoping that over time we'll see better crosstalk

because we may have some really interesting things on the medscape side or the opposite on the WebMD. We don't get enough trying to get that mixed audio. It's funny that it's taken us this long to get to your your most recent book, but I think it was a worthwhile route to get here because I think that the story of Iox alone I think is... well I learned a lot because to get here because I think that the story of Iox alone, I think is, well, I learned a lot because again, I think I knew parts of it, but I don't think I appreciated the severity with which you've paid a price.

Fortunately, past tense and didn't hold, you know. And it sounds like it's worked out for the best, but that's phenomenal. That seems to be one of those experiences that falls in the category of, you're probably better for it, but you never want to redo it. Exactly. You get much stronger, you learn who your friends are and aren't.

Basically, when I got here, it was like being in the witness protection program, and you're starting all over. I remember I had this big lab where we're going to do all the sequencing, and I'm sitting in this big lab, and I'm the only one in the lab, and I got a lot're going to do all the sequencing and you know and I'm sitting in this big lab and I'm the only one in the lab and I got a lot of recruitment to do. Now we have just an R group, you know well over a hundred people. We have one of the largest NIH grants in history to do all of us the big million person participants diverse group that we're doing so much with over the years ahead. So you you know, things are really humming, so it's been great. So your book is called Deep Medicine, and the picture on the front really

points to AI, but the book is about more than that, but I want to start with that. Now, let's assume for a moment that someone listening to this has heard the term AI, and sort of knows from science fiction movies what it kind of means, but that's the limit of the knowledge, right? So they don't make me necessarily know the difference between machine learning and artificial intelligence or those terms synonymous, let alone how would that even factor into medicine and how do you separate out the sci-fi from what's how already happening, right? And to, you know, what you think of how it looks like.

So take that and any order you like. Well, I mean, I think the problem with AI is it's been around the concept since the 50s, 1950s. And it's diffuse. Yes, there's lots of sci-fi and movies and misunderstandings. But what we're talking about now is a specific subtype of AI, which got its birth just over 10 years ago called deep learning. Neural networks that allow for inputs and they could be millions, billions of data points, could be images, could be speech, could be text. And then it goes through these layers of artificial neurons, which are not very much like neurons, but nonetheless, they can distinguish features progressively as they go through

this network. And then you get outputs. And what's remarkable about this era and why it recently won the Turing Prize for Jeffrey Hinden and his colleagues from University of Toronto, but the thing that's so the Turing Prize being basically the Nobel Prize for computer science. Yes, I should have mentioned that exactly. The reason why this is such a big advance in medicine, the biggest advance I've ever seen

as a student of medicine for many decades now. But it's so big because you can take, particularly now, images and you can get accurate definition of the image better than experts, doctors. So whether it's radiologists or dermatologists, pathologists, cardiologists, I mean you go down the list ophthalmologists and you will see studies now to show superiority of accuracy or at least as good to a machine. Now to be clear, this is an initial recognition, not comparison. I mean, I think, this is an area I don't know very much about Eric, but the last time I thought about this and did some reading about this, I came away with the impression that if you took an MRI

of a person and you showed, so this is first time this person's getting an MRI, you get the best radiologist to look at it, you get the best computer to look at it, the computer still struggled for macro context. It still didn't even realize that was the liver, per se. But it could certainly, with greater fidelity and resolution, once told that was the liver, identify, and maybe be more clear about, well, what's assist versus what's a hemangiuma versus what's a hepatoma.

So it had superiority there. It also had superiority when it came to serial studies. So Mrs. Smith had a chest x-ray a year ago. She has a cough now. She has another chest x-ray. Is there a difference? But am I right in my recollection? No, no, actually, I'm really glad you put some angry on that.

Because what we have, deep learning is, in many many respects extraordinary, but it's very narrow. So if I say find me pulmonary nodules in a chest x-ray, that's where I say it can be superior. And clearly the best is the combination, the synergy, the symbiosis of what the machine can quote C versus what the doctor could see. So yes, it's a very narrow thing, but what we're talking about here is there's so many mistakes in medicine because things are missed or are inaccurate. And you know, this extends through pathology

and every different specialty. Yeah, your thesis is not, I mean, many people have said to me when they talk about this sort of loosely that the radiologist is the first doctor on the chopping block. That's not really your thesis. No, I actually think that's completely wrong. Jeffrey Hinton said that once, and I think he ultimately regretted. The point being is that it basically tees it up.

That is, you get a different complimentary read of something. And that helps for speed and accuracy and it could have ultimately lower costs and it could ultimately improve medicine. The thesis of deep medicine is if we lean on machines more, in many respects, we can get into that. But if we do that more, we can free up to have time with patients and we could get the doctor patient relationship

back to where it ought to be, where it was, you know, some 40 years ago. to have time with patients. And we could get the doctor-patient relationship back to where it ought to be, where it was, you know, some 40 years ago. That's the main premise that is unique about the book in which, you know, I really build up to deep empathy with the last chapter. But the real thing that's different now is that we have lots of promise,

lots of potential for AI. We haven't actualized that. We haven't proven it for the most part. One of the only randomized trials to date is in colonoscopy. Because a lot of polyps, particularly of their flat or Cecil or small are missed. And it's very much operator dependent,

how much time they take to do a thorough colonoscopy. And so now there's a Chinese randomized trial that shows, hey, if you use deep learning machine vision, you can pick up pops that are routinely missed. And so then people say, okay, so what? Maybe the ones that are missed are not important. Well, that's where we are today. That's the study is you look at the denominator

of the mist versus the not-mist, the machine-cott versus not,. That's the study is you look at the denominator of the mist versus the not mist, the machine cot versus not, and what's the prevalence. Because if the prevalence of pathology in them is at least the same, you could argue they should be missed. That's what it might be higher if it's Cecil. Yeah, so you're going to have 20% of polyps were picked more, were picked up by machine vision, and then we still don't know how much of that were true disease likely. I've always felt the field, if radiology is the first pit stop on this journey, I've always felt

like the ICU needed to be a very close second. How much is really being done there? Because A, it's the, obviously the most data rich environment after radiology, radiology, also, of course, informing the ICU. But in terms of just raw numbers coming out about a patient, if you think about a patient on a ventilator with CBVHD, and you pick every device strapped up to a patient, it's not the same as a Formula One car, but you're in the ballpark of that much data. Yeah. And you're touching on one of the big deficiencies of AI and deep learning today,

which is multimodal data. So when you have all these inputs of very types, not just their vital signs, but could be machine vision of their facial recognition. It could be so many different parts about that person. No less their priors, electronic record. And we don't do well with that because deep learning today is, as I say, narrow task. It's like, you know, what's in this eye ground for ophthalmologists? Is this a diabetic retinopathy? Is this something else? So the ability to take many layers of data, which would be the ICU story, isn't the early stages, even more so than the image recognition.

Yeah. What realistically, where do you think that is in terms of, again, caviating it with the, it's always going to take longer than we think it is. is this something where, I don't know, in 10 years or in 20 years going to an ICU will afford a patient the luxury of a true supercomputer that's basically assimilating the CVVHD data with the ventilator data, with the Swan gans data, like stuff that as you point out, like it's it's even the most analytical physician can't really recognize the patterns that are deep within all of those data. Well, you just touched on with that statement, the essence of why we need AI support, not just in an ICU patient, but in every patient.

There's more data than we can handle. Especially when you say people are wearing sensors, they're gonna be wearing more, people are gonna have their genome sequence or they already have a genome chip or array, microbiome with a gut. I mean, no less, all their records, not just the one healthcare place

that's happened to be visiting that moment. So this flood of data per person, no less the intensive data collection in an ICU setting, this is overridden human capability. We need machines. We have to fess up that we can't do this. But we also have to acknowledge that we're not there yet. Now, so when are we going to get there? Well, you know, faithily and the group at Stanford has done ICU work, machine vision to see whether it's single machine or

is it integrated? There are studies have been mainly single whereby, for example, they're looking to see risk of extubation so that you don't have to have a nurse in the room all the time that what's going on with that patient that they're going to self-ex debate, or others have looked at, you know, likelihood of sepsis or different pieces of the story, but no one has integrated it all yet today. And I think that's where it's headed. We're seeing these hybrid models of bringing the data together, but, you know, a lot of the problem with this field has been way out of bound type, where it can go. And if I, you know, when I did the research in the book, which we involved a few years

of work, cumulatively, I spoke to a lot of the real gurus in the field. And they made it clear that, you know, we are going to get there eventually, but we're not there yet. That is the challenge, because when you think about other big breakthroughs that we look back on, we don't realize that they were more discoveries than creations. Sometimes, so for example, look at germ theory, right? This is, again, it's something we take for granted today, and it's hard to believe there is a day when you wouldn't wash your hands before operating on a patient or you wouldn't wear sterile gloves. So we acknowledge how that transformed medicine

in a step function manner, but two things are a little bit missed when we contrast it. One is we didn't have to build it, we accepted it and discovered it, and two, it didn't happen overnight. Like there's still a generation that it takes to implement these things. And so that's the best case scenario, right? It doesn't get any better than that. This is something that

has to be built. This is almost, this is, I can't think of an example. Maybe I'm wrong. And if anyone's going to think of it, it's you, but is there an example before when we had the idea and the promise and then we set out to engineer the solution building into it. So for example, I'll give you a failed example, which is the EMR, right? So it's always, like literally the worst thing on the face of the earth.

I heard you once talk about this, and I think it was you actually, but maybe it wasn't, but I'm gonna give you credit for it. But I think you, you best summarize it by saying, look, the EMR was created as a billing solution Not a clinical solution and I couldn't agree with you more But there's an example of okay, we have a problem medical records are so cumbersome so voluminous Although really they're just a two-dimensional problem. It's really not it's three dimensions if you include time

I would say and we now have computers quote unquote so mentions if you include time, I would say. And we now have computers, quote unquote. So computers will solve the problem. Let's build it. Well, one, it took a lot longer than people expected. It took much longer to implement it. And it sucks much more than people could have ever imagined it could suck. When I think of those examples, I keep saying, is there a positive story? Is there a great case study in medicine where the engineering solution lived up to its expectations? I think you nailed it. I don't believe there is one. This is a unique story that's being written as we speak. It's so different than we have a technology and we just want to implement it. This is one that there's a lot of construction

that's still required. We know what the house is likely going to look like when it's built, but we're still in the foundation stage. Do you think that these are problems that are going to be solved by the giants? Is IBM, is Google, I mean, are these the entities that figure this out, or is this going to be solved in more of a pharma model where the early discovery and the early stage, you know, even the stage

one, the safety trials are done by small companies that ultimately get acquired by rolled up into larger companies. I mean, today, like the the merks and the fisers of the world aren't really doing drug discovery anymore. They've decided we're going to outsource that to more nimble companies. And basically the private markets now subsidize that, while the public markets subsidize late-stage drug development. Do you think that's the way this is going to be, or do you think this is going to have

to start and finish within the behemoth companies that have their enormously deep pockets? I think this is a story of innovation from the outside. I think it's very different than what you're seeing now with the consolidation and pharma and outsourcing. Here you see the big Titans like Google and Microsoft, Amazon and the rest of them. They all recognize this is the greatest opportunity for growth and also a noble mission of improving health. So you have that group, you have startups

that there's no shortage of those. And you also have some governments like in China, in the UK, and other places that are nurturing this, that are investing big in this area. So, I think this combined force of multiple entities, is where we're gonna see this really, you know, really take off. It's starting to happen much more in China out of need, that is the implementation is way ahead of what's going on in the U.S. because they have so few...

What are some examples? Well, the radiologists, we're just here, we're just starting to get a bunch of FDA-approved algorithms for reading various types of scans. They already have that white, spread throughout China, they already are doing many things on, well, we hear the only FDA consumer approved or cleared is the Apple Watch for heart, a deep learning algorithm for each of the relations.

So explain how that works. Let's use that example, because that's near and dear to everybody's wrist. And I see you're wearing your Apple Watch there as well. So let's just say you went into the Apple Store So explain how that works. Let's use that example. That's near and dear to everybody's wrist. And I see you're wearing your Apple Watch there as well. So let's just say you went into the Apple Store today for the very first time and you bought an Apple Watch. Okay, so first of all, it's on the back surface of the wrist,

the volar surface of the wrist, and what is it shining through? And I assume it's shining it onto the veins in the back of your arm. Yeah, no, it's picking up optically each heart rate, and you can see the light that it's used. And for the deep learning algorithm, which actually was first clear by a startup, a live core, and then a year later, Apple, which they didn't even acknowledge

that they had been a year after the first. But nonetheless, on their watch, they get heart rate, so at rest, and then when you are active. And then basically for you, it has your data whereby when you have heart rate at rest, that's off track for you, it says, hmm, get a cardiogram, and you get a one lead cardiogram when you press the crown on the, and you get a good quality cardiogram. And press the crown on the EC and you get a good quality cartogram

And then if it has atrial fibrillation, it's all lead. Does it most closely approximate on the 12 lead? It's a lead one you get a cartogram read For atrial fibrillation which I just one thing it's pretty good for that I was about to say not to minimize that but a fib seems like about the easiest thing to pick up because of the irregularity of it, right? Yeah, although there is some false positives and negatives because sometimes the P-ways are that you're looking to be absent, you know, sometimes you can get faked out. And so it's reasonably good. And you know, it's in the 90 plus percent accuracy level. But it's all about the base theorem of for people more information.

Well, for people who are not risk, a lot of people have an Apple watch who are, you know, young and have zero risk of atrial fibrillation and they get a cardigan and get some anxious and they may even get workups by a cardiologist. So this is a problem where we have marketing of an algorithm, the first deep learning algorithm. How long does it take, by the way, to learn a person well enough that it would be willing to make a recommendation like that? Oh, just a matter hours. Wow.

Certainly, by a couple of days, it's got it down. But yeah, I mean, you know your resting heart rate by the accelerometers, it knows that you're not moving. And why did your resting heart rate used to be 60? Why is it 100 something? And then it'll tell you to get a cardigan. And it can't make any other diagnosis, it can't diagnose any ventricular rhythm. Not now.

Or atrial tachycardia or anything else. Ultimately, it should be able to, but those algorithms haven't really been validated yet. But ultimately, no, now I use a six lead cardiagram. It isn't on the watch, but you can just do that with sensors and put it on the leg. Well, how do you do that? That's interesting. Yeah, it's basically half the size of a credit card. Where do you get this? It's an aftermarket product, or? No, it's actually marketed now by a live core, the one that came with this ECG on the watch first. They actually put it on the Apple Watch, but it was their algorithm. They came up with a six lead, which you then put that on your leg, your left leg, and

then you get six all limb lead. And you do this with your patients as well? Yeah, every patient. When I see them, instead of just taking their pulse, I also do a six lead cartogram. It's been remarkably insightful because it's free. It takes a second and Then I can really be much more certain about if they have any rhythmia But also diagnosed conduction system abnormalities. So it's accurate enough that you can measure your intervals perfectly Oh my gosh. It's it's the quality is amazing. Yeah, I mean the six lead now

Can you send them home with the same kit and then can they get a six lead on themself at home and let you see the data? They could, I haven't done that yet, but that's probably where this is headed. The reason why this is actually funny, you mentioned it Peter, you can even do your own stress test with this. Yeah, of course. In fact, you could do a real stress test, which is in the actual environment under which you need to be stressed. Right. Yeah, I did that the other day. I did a rest ECG, and then I got on a bicycle, stationary bicycle, and went really hard, and I just after I got off and did a six lead again. So I said, wow, you can do a stress electrocardiogram, high quality, six lead, and never go near

a couple of times. Where's the output? Where you seeing the output. Oh, on your phone. Okay. And you can make it a the output? Oh, on your phone. Okay. And you can make it a PDF and send it off to your doctor. It makes it automatically, yes. Huh.

Yes, pretty cool. So I mean, that strikes me as proof of concept now. Yeah, well, and that's where we're going to get you alluded to. When are we going to get all the heart rhythm abnormalities diagnosed and the heart conduction, which is a precursor to a rhythmia. So that's where we're headed, because one lead is hard to do that, but when you have all of the limits, in fact, with AI, you could impute all 12 leads. You don't even need to get the other six leads. So pretty soon, we're going to see that six lead become really valuable entry for what's going on in a person's heart.

In fact, Mayo Clinic just published a series of papers on 12 lead cartograms and you could get heart function, you could predict from a cartogram whether they're going to have atrial fibrillation, you can get the potassium level of the blood through that. Wow. I mean, the amount of data that's sitting in this pattern, which we can't see, is amazing. Well, think about the number of times I see this once a month, and my practice is really small. So if I'm seeing this once a month,

let's extrapolate to how many times this happens in the United States. The blood hemelizes slightly on a blood draw and the potassium comes back at 5.5. Oh, yeah, or higher, yeah. And you don't know what to do. Right. Well, imagine you had that. Yeah. And you don't know what to do. Right. Well, imagine you had that EKG.

You wouldn't have to panic because every time that happens, you have to call that patient, send them into the ER, get a blood draw, confirm what you know is likely true, which is the stupid sample hemolyze. Their potassium is really 4.7. But imagine you didn't have to do that. You could just push this button on your watch. That exemplifies what we can't see, but having a machine trained by a million cardogram, what it can see.

And in the book, in Deep Medicine, I have a chapter, it starts out with that story, how did they discover the potassium story? Something we can't, we can tell, the potassium is really high, the tall two ways, but we can't get to the decimal point. Right. We can't distinguish between 4.9, which is do nothing, and 5.6, which is you better be careful. Right. And that's what machines are good for. And we're going to be seeing a lot more of that kind of stuff. That is, the eye opening thing to me is to learn about all the things that we, what humans can't do, that machines can be trained to do, and they're just going to get better over time. So do you wear a Dexcom sensor?

I have. Not regularly. I'm not a dad. But I have, and I've learned a lot from it. I've, you know, I've tried Dexcom and the Libra. I've really found this glucose thing because of how it interacts with what you eat, with your sleep, well, it's physical activity. It's amazing.

Yeah, it really is. People ask me why I still wear it, because I'm not diabetic. And even my patients, so about third of my patients to a half my patients wear this, none of whom have diabetes. And I always ask them for 90 days. If every one of my patients would wear it for 90 days, at least I'd be happy.

And then we could decide. But what invariably happens is people realize, they go through the following cycle, which is, Peter, you've been wearing this thing for four or five years. Haven't you already figured out what to eat and what not to eat? And I say, well, yes and no, but it's more complicated because, like, for example, let me show you this. I have not eaten anything since 4 p.m. yesterday. Wow.

It's 11.30. So I'm coming up on 20 hours of no food. Look at the variability in my glucose for the last 12 hours. It's been as high, it peaked at 118, which was, yeah, peaked at 118, which was right after a workout this morning. And by the way, it was just weight training. It wasn't like high intensity interval training. If it's high intensity interval training, it's going to go much higher. Now it's sitting at 94. And you'd think, well, if knowing that it's 94,

like if I ate a bagel right now, could I predict what it would go to just knowing it's 94, the answer is not a chance. You see, just knowing it's 94 isn't enough to tell me my response to the bagel. I have to know how much glycogen I have. I have to know how much cortisol I have. I have to know how much insulin I have I have. I have to know how much cortisol I have. I have to know how much insulin I have.

Like, there's so many variables, and that's why, four or five years later, there's nothing about this that is boring to me because I'm constantly learning a new physiologic experiment. I mean, if there's anything that's ripe for AI, it would also be CGM coupled with other data. So in other words, I don't think the CGM coupled with other data. So in other words, I don't think the CGM data as the input feed would be sufficient. You would have to constantly be pairing it with your activity and other sensors.

Because if you had the cortisol sensor and the lactate sensor, that starts to become remarkable predictive power. And when you could get to the point where, because this is my dream, I want to know, can I eat that right now or not for my parameters? So this is my pipe dream is, I want to be able to say, go into the algorithm and tell it your desired average glucose, your desired variability. So I want to average glucose that's below 100 milligrams per desoliter or below 110 milligrams per desoliter.

I want a standard deviation that doesn't exceed 15 milligrams per desoliter. And now you tell me what I can eat. Spend the first month watching me eat, learning how my body responds to every different food and go from there. I mean, directionally speaking, how long would it take to get us there? I think we're getting there. I mean, we're chipping away at that. So the gut microbiome is a big part of the story too. And I know you're such a proponent of this. And I am, I call myself a gut skeptic because, well, why would I say that? I certainly don't disregard the importance of that. I think I'm waiting to see a great example of how I can use it outside of like the really

clear clinical ones, like certainly knowing how to change the gut microbiome in the context of C. diff colitis is profound. It seems very likely that something about the gut changes in patients with diabetes who undergo gastric bypass. That seems to really suggest, but it could be as high as the duodenum and the most compelling evidence I've seen is that it's actually the change. It's the duodenal bypass that specifically gives them this incredible remission out of

the gate, more so than the lower GI tract. But I think most of my skepticism comes from the fact that it's not clear to me what to do with all those data, which may be exactly your point, that when I see patients constantly show up to me with their gut sequence and they say, well, look at this pathology state here. And I say, well, first of all,

I don't know that that's a pathology state. And if it is a pathology state, is taking a probiotic the answer? I don't have any evidence that that's the case either. So is it more a readout state or is it a form, is it a malleable state that we directly interfere with? Right. So those are all important questions. I think the real insight here is that up until when Aaron Segal and his group at Wiseman Institute in Israel up until they did what now has to be seen as a classic study. This was the

cell metabolism paper from about a year ago? Well, there was a paper in cell 2015 which was really the seminal work and now there's been several more and it's been replicated by many others. They took now thousands of people healthy like yourself and they went ahead and got microbiome, but they also got the exact same amount of food, the exact same time. They also got all their labs, and you know, every piece of data they could get on these people. And they found that you could predict if they had a bagel, which ones are going to have, and what level of glucose spikes they're going to see. And they found that so many spikes,

even very significant spikes, from when 60, 180, 200 in healthy people, with no sign of diabetes. And how durable do you think the knowledge is from the sequence? So for example, like if you sequenced that patient Monday morning at 9 a.m. How much do we know that Friday at 5 p.m., the data are still relevant, assuming you could even,

because you can't get the data in real time. Right, so they didn't do any DNA sequencing. Of course, that wouldn't change. So we don't know the genome excited of this, but we do know the microbiome, unless you do something significant like that. Oh, no, sorry. I didn't mean their DNA. I meant the DNA of the bacteria.

Okay. Good. Yeah. Yeah. The DNA of the microbiome is pretty darn stable everywhere you look at it, unless you change a radical changing or diet, like change fiber content, or you take antibiotics, but it's very stable from day to day. I see. So you would say that, look, Peter, only if the patient does a course of antibiotics, do we need to recheck them? Yeah. Or make a radical dietary change. But if a person's in quasi-steady state, you could sequence them every quarter and basically

update your pre-test probabilities of what the distribution is. That's right. And another tier of complexity, because it's good that you're a skeptic on this, but early on, these various companies that would do microbiome assessment, they just said, how much you have of this bacteria or that bacteria? It was like a density of bacteria. Turns out that you touched on it. If you sequence the bacteria, the changes in that bacteria species sequence is just as important as the density of the type of bacteria. So this is not easy, it's expensive to do it right. And we've already seen a big fraud on this front quite recently, right?

Yeah, you buy them. They basically are anos of this space. Yeah, well, they were billing people illegitimately and they were only reporting on density of bacteria. I don't know that they're referring. So they weren't object fraud. It was just bad practices. Yeah. I don't think they were doing things wrong with respect to the microbiome density, which is very rudimentary. They didn't do sequencing.

They did basically a bacterial density of... I mean, I found them to be the most useless company on history of civilization because back in 2012, 2011, I was, I mean, at least acting like I was on the forefront of this, trying to understand it and ordering these sequences on myself and all my patients. And I don't understand how this company stayed in business. I mean, they didn't, but they couldn't run a sequence to save their lives. Well, yeah, I think the biggest thing is they were fraudulently billing people, double billing, triple billing, you know, that sort of thing.

That sort of got them into, you know, basically collapse mode. I don't know enough about their sequencing. I mean, I always found Larry's smart stuff to be the most interesting because Larry's doing it at a level that you couldn't do commercially. Yeah, so shotgun sequencing where you do true metagenomics, you know, there are only certain labs like the one I mentioned in Weisman here in San Diego, the night lab does metagenomics. That is K-N-I-G-H-D Robert Knight. So these are the centers that are doing it right that are sequencing each species of every organism that's found. And we now know that sequence is equally as important

as the type of bacteria. So that's the sort of data. Now, the other thing you're bringing up that's really important is we have no idea how to manipulate the gut microbiome. The only thing we know is a fecal transplant in certain people with, you know, pseudomembranus colitis, C-difficial.

Outside of that, we don't have, we have crap souls that are being made, that are being tested. So I think you and I definitely see probably more closely on this than I would have guessed initially, because we agree that at this point, it's an output of data, not an input

to manipulate necessarily. Right, right. So I probably need to go back and look at the Weissman paper again, because I don't think I've looked at it in over a year. And my view was, which is probably incorrect, by the way, that CGM and dietary logging would have been sufficient. So what I really want to do is go back and look at that paper and see what the gut biome added above those things. Which I'm guessing there is something there.

Yeah, you know, there is, and we need more. I mean, basically right now is you could predict if you had all the data and the right algorithms, you could predict which foods you'll spike from. And then this was taken to another level by the group in London, King's College, led by Tim Specter. He brought in all these twins from all over the country, identical twins. So they had their gut microbiome and they also put in a line who avained to get blood samples for triglycerides. And they saw the same thing, which by the way, you could get out of a

sensor. You could ultimately, yeah, we don't have one yet. No, and you know why I mentioned lactate earlier, if you have real-time lactate, you are estimating with really great precision, mitochondrial oxidation. Now you understand fuel partitioning. You see, to me, if you asked me a year ago, how would you want to best estimate fuel partitioning, I'd say, that's tough, because you've got to have somebody basically walk around with a respirator or something that can measure oxygen consumption and CO2 production. But I think lactate's telling you that. I think if you really know how to calibrate

lactate, you can estimate fat oxidation versus glycolysis through to lactate. And so all of a sudden, you now get into this. So the reason that right now, my glucose is 94, but if I ate a bagel, it would go to like 104 is because I'm so glycogen depleted because I have an eaten in 20 hours and I worked out very hard or at least for a long enough duration. Conversely, it's not uncommon after dinner. Let's say you have dinner, you have a glucose spike up to 120 and then it comes back down to 90, 94. you eat that same bagel, you'll go higher. Well, a very important input into predicting that is knowing glycogen stores and insulin sensitivity of the muscle and all those other things. So what I need to better get is how many different phenotypes, macrophenotypes of gut biome, are there that really matter?

Right, the bigger picture though, I agree with all your point, and it'd be nice to see a lactate sensor that's tested at scale and is accurate. It took a while to get that for glucose, and we're at the earliest stages on the lactate, but there's still a lot of naysayers here, and I understand their perspective,

and that is so why? So what if your glucose goes to 180 or your lactate goes to this or your triglycerides go to that? The point is do we know that changing that, that keeping everything nice level keel? You don't think the diabetes literature has made it clear enough that normalizing glucose and insulin is beneficial? Not enough. No. The only way you can get at this, inferentially, yes, but you know what, we've... Oh, oh, you're saying I can tell the story

that a glucose of 120 is better than 180 because I have clinical trial data to demonstrate that all day long. And I can even tell you that how you achieve that matters. But you're saying I don't have the data to tell you that 100 is better than 110.

No, no, another way to put it is, I don't have the data to show that if you wear a sensor for X number of times, 90 days in your case, or forever, or a week, that you're learning about avoidance of glucose spikes changes your prognosis. We don't know that. And the same thing for triglycerides,

which by the way, they don't correlate. And we're learning that each person's individual response throughout their day is so incredibly unique. And we're learning some of the factors, we don't even know, we know all the factors that influence that you've mentioned, of course, glygogen stores and physical activity and microbiome. And cortisol in my experience plays a staggering role.

No question, stress. I mean, just if you get an inner, innervening cold, or less stress in your, in your family, your life, whatever experience. So yeah, this is a really interesting area where learning about ourselves is like, you know, no self sort of thing. We're in the early stages and I see the skeptics. I understand their perspective. I think that we have to prove it. I lean where you are, which is why not have this information. I've learned a lot about

myself, no less the feel from it, but I think we have to admit that we got a ways to go. What do you think's significant blind spot in medicine today at the macro level? At any level? No, I think the biggest blind spot is how poor we are in diagnosis, no less than treatment. I mean, I think that when you really look hard at the data, what's amazing, Peter, is you see all these clinical trials that declare a triumph, and they're helping three out of a hundred people. I mean, a great example of statins, primary prevention of statins, if not the number one, close to the number one, class of drugs that are used today. And you see that out of 1,000 people for primary prevention, 988 derive no benefit for

five years of taking a stat and 12 out of 1,000 get benefit. So whether you look at the diagnosis where, you know, if a doctor... That's another topic I know that we may disagree on. My view on that has always been that because the time course of atherosclerosis is so long, you know, it's a disease that begins in intensity, you certainly know from, you know, the starry stuff of the, you know, the 70s that, you know, basically by the time you're 18 years old, you've, most people have a stage three lesion at that point, that the challenge with studying primary prevention is you could never study it long enough to really see where those curves start to divert.

Well, no, they diverge, but the question is, are they going to keep diverging? And most of the benefits starts to kick in right about 18 months. And yes, they're still slightly diverging after five years. But we don't have any data beyond that. So I should restate that is that we don't have any proof that more, you know, you can suggest that instead of 18 out of a thousand people benefit that it goes to 36. Exactly. But what about the 970 that don't derive it? Yeah, no, no, no, that's fair. I think the point is, do you believe the Mendelian randomizations or do you think that the Mendelian randomizations have artifacts in them, which any Mendelian randomization will have

an artifact if that which changes the variable of interest also changes something else that you don't know. That's always that's the blind spot of the Mendelian randomization. No, there there are a neat way to get a readout, but they're not perfect. You know, I think that whether you look at diagnosis where, you know, if you take people who have died under a doctor's care and you say, why did that person die? What was the cause of death? 40% of doctors say I absolutely know the answer are wrong, 40%.

That's how many autopsy are show a different reason for the death as what was pre-mortem. Wow, that's a big gap. Yeah, if you ask doctors to make a diagnosis, if they don't think about it in the first five minutes, five minutes, 95% accurate, but if they don't, it doesn't come to mind in the first five minutes, it drops down to 24% accuracy.

Basically, what we have is type one system, type one thinking, system one thing I should say, that's kind of into work. And we just are reflexive. We don't reflectively go over anything. We don't have time. We don't simulate all the data we can because it's so much. And so we have to basically the whole, the big hole is acknowledge that we can do far

better. And it can all be through human support. We need help. Do you think there's any area where, I think you've made a compelling case that machine plus human should be better than human? Eventually it will be. I mean, I think even in radiology today, it should be.

Oh yeah. Hopefully critical care would be an amazing place where machine plus human should be better than human. Do you think that there are extremes any other way? Do you think there are places where humans will always be better than machines plus humans? Yes, and that's in being human, which is the bond. You know, just like our conversation, this deep conversation, it really illustrates the human connection. We don't have those kind of conversations in seven minutes or ten minutes with a patient who can't.

You can't get to know a person's life history. That's never going to get really digitized story. Their story. We interrupt patients within 18 seconds. We don't listen. The point being is that machines, what we don't want machines, they don't listen. So the point being is that machines, that's what we don't want machines. They don't have context. They're not going to be able to truly understand all the nonverbal communication and the real issues of a person that are deep. And that's where the humanity

we need to bring it back. I mean, the essence of medicine is that, and it's been lost. It's become this big business. And it's still very... You worry about the, I don't know, well, it's not really a brain drain, but do you worry that the war for talent has shifted and back when you went into medicine, it's probably safe to assume you were one of the best

students in your high school, the best student in college. Like, it would have been skimming at the very, very top of the pyramid of students. Is that still the case today, or has, I mean, you've already alluded to a number of things that I've seen, luckily I don't experience them just on the nature of my practice because it's private, but I mean, these stories you tell, I know so well,

the doctor that gets seven minutes to see a patient and in that seven minutes, six minutes is typing into an EMR. The moral distress and the absolute erosion of a belief in what you're doing is a huge cause of burnout amongst physicians. I don't understand, like, if you're the top student in college and you're interested in life sciences, why you'd pick medicine today, unless you had a profound confidence that you could carve a path distinct from what most are probably going to do. I mean, you have to be an optimist, I think, to pursue medicine today.

Do you worry that it's going to be hard to recruit the most talented kids out of college into medical school. Well, I hope it won't be, but I do hear constantly a friend who are doctors who tell their kids don't go into medicine. Yes, I hear that. And that's really bad, because here is the ultimate profession for sense of really helping people. And then you have the people who are in it saying it's horrible.

And as you know, Peter, the physician burnout, no less all clinician burnout is at peak. And why is that? It's because it becomes data clerks and they're squeezed for the time. They can't care for people when you don't have time. So this is, of course course going back to that main thesis of gift of time, we can get that. But I think we have to restore medicine the way it was in order to attract the talent that you're referring to.

And I think it's doable, it's not gonna be easy, it's gonna require a lot of activism, which we haven't had that much of in medicine. Yeah, this is something doctors are quite ill-equipped to do. We're seeing the light on activism. The gun control, NRA, really brought it out when they said, stand your lane. This is when the AMA said a physician should be asking a patient if they own a gun. It was an American college to physicians.

They published it in the annals, internal medicine last fall. And then an R.A. said, you know, these doctors should stay in their lane. And then you had all the doctors came out, one of them, Judy Melanick saying, this is my fucking lane. And you know, it went everywhere. It went viral. The idea being, if doctors are going to be killed potentially by patients, it's not an unreasonable question to say.

Well, that and caring for all the gunshot victims. Yeah. The murder and the suicide. And the suicide. Which is probably the greatest cause of gun. Yeah. You've got both suicides and homicides and mass killings and AR-15s and all this stuff.

So the fact that this was taboo that doctors didn't warrant a lot of the talk to patients and they warranted a lot of the due research patients and they weren't allowed to do research. I mean, there was no research in this area. So this was a void that now has brought out a lot of the activists and social media and it's this new era of young physicians, a lot of them women,

and we're seeing activism like never before. I wrote about it in the New Yorker recently about this and no, should doctors organize, and this, what we're seeing, it is happening. And the hope is that we're gonna see an organization take hold where all doctors can join as well as ultimately patient advocates and others, and that we will turn this around because this is

the biggest concern I have, Peter, is that we're gonna see AI kick in more and more over the years but what will it do if the administrators who are the overlords who are overrepresented as compared to the people taking care of patients if they keep the squeeze on we're just going to see things get worse so we we have to override that. And the only way we're going to do that and turn inward and get the humanity back in medicine is to have doctors organized and the gravitas of a million doctors in America, all being part of one entity, it could be enormous.

You know, and this gets to another problem within medicine that I alluded to earlier, which is the patients aren't footing the bill based on the system directly and therefore demand in a demand-based system. So if it's not a demand-based system, it doesn't matter. Like in other words, in the NHS or the Canadian system, the patient is not footing the bill, but they're also not driving the demand. The demand is budget set. But in the US where you have this paradox, it also means the patient's voice doesn't matter.

And that's the irony of it, right? So it's the opposite of the DC license plate, which is taxation without representation. It's like no taxation and no representation. And that's why I worry that patients can't be the ones to drive this change, which they should be able to. Like, the patients should demand this change, but because they're not the ones writing

the checks to feed that $3.8 trillion machine directly, they're only doing it indirectly. In other words, they don't get to control it, right? They're paying their taxes and their employers are withholding it But they it's not the same as saying here's my dollar go and do this thing with it Yeah, no, that's why if you get the doctors to come together to start this and the sole purpose is the patient doctor relationship It's not about better reimbursement or all the other Trade-gill activities, but rather it's about we want to fix this relationship and bring the humanity back in medicine. Then we start to see you know the ability for that patient interest to be recognized because now all you have is you got a lot of patient

advocacy groups but they're you know they're just like the doctor organizations they're all vulcanized. We need one entity to stand strong. And I hope we'll get there. Well, that's a good point, right? It should be made up of physicians and patients. Yes. Actually, it really shouldn't be. They shouldn't be separate. No, no. I think, you know, started with the physicians because, you know, there's just a million of them that we can identify and get them together as many as possible. Then you start adding on the page. Are there really a million physicians in the United States? Yeah, the fact checking of the New Yorker is amazing.

I've never experienced that before, but they tracked down everything, and they got to the numbers that I never could get to. Not all of them are practicing. There's about 900, almost 900,000 are actually practicing some respect, but there are a million docs in this country. Have you done the math about how many doctors we would need under this new regime of empathic, intelligent, artificial, this symbiotic relationship? I know it's because there's a bunch of moving pieces, right?

It's radiologists still exist, but now they're there to talk more with patients and interpret the diagnosis as opposed to make the diagnosis, right? radiologists still exist, but now they're there to talk more with patients and interpret the diagnosis as opposed to make the diagnosis, right? And you're still gonna need the internist, but now they have more time with the patient and they don't have to worry about the diagnosis as much as they have to worry about the treatment. Directionally, Eric, do we need the same number of physicians? Are we gonna need more physicians? Are we gonna need less physicians in 30 years on a per patient basis? You know, when I did the UK review, we got into that and we had economists and all sorts of brilliant people modeling on that.

And I think what we'll see is, even though everything now would suggest we need a lot more doctors because of the aging population and all the comorbidities and the complexity. I mean, if you just look at, like for example, how do you care for a patient with cancer today? It's gotten very complex. So, you would project, we're going to need, you know, a steep growth curve, but what we're going to see, I think, is a big blunting of that. Because we are going to be the machine story is not just about doctors relying more on machines getting support. It's also about consumers' patients. And so when you get the outsourcing and the offloading you start to see a pretty big and then when you get rid of the hospital story and just have

surveillance centers, remote monitoring, you start to see a very less need for expansion. So I don't see what we're going to be a decline, but just a difference in the curves as they go forward over the next few decades. And there will also be this, I don't know, for lack of a better word, kind of a growing pain as people transition. I mean, most of the radiologists I know today, you know, for example, have very technical backgrounds. I mean, any of the MRI folks I know today, for example, have very technical backgrounds. Any of the MRI folks I know,

they usually have a great background in physics and things like that. So all of a sudden, there's gonna be a different selection criteria. For example, you may wanna choose radiology independent of how technical your background is in physics or mathematics. And so it's like, it takes a generation

to make these switches. Do you see any other types of changes in how people will select into different specialties? Well, that's hard to know. I think we have theorized, Sara, John, I from Penn Radiology, that there might be a new specialty that would just be radiology and pathology combined, at least the pathologists who work with slides, because it's a very similar interaction with the computer. And they're often very much integrated.

So that might be a whole new specialty over time, but overall, one thing we don't want to forget here is that the empowerment of patients to do doctorless diagnoses of most common conditions, whether that's an ear infection of a child or a urinary tract infection, a skin rash or skin lesion and on and on. The routine things are not gonna have doctor in the loop. Only if you know what treatment is needed perhaps and that's only in the US not in a lot of other countries. So that is gonna to change also specialties, because today you look at pediatrics, you know, it's a wonderful specialty, but a lot of that could be decompressed if you give parents more autonomy for their kids.

So we're going to see lots of changes based on the patient side or the parent side of things, which I think has not been adequately appreciated. If you could conduct any experiment and there were no limits on the resources you had, so you could, and it could be an experiment within the real recesses of basic science, it could be a real translational experiment that takes something from the cutting edge of the bench to the bedside, or it could be the largest clinical trial ever done to test a question that vexes you without any new introduction of a new technology, but just simply asking a question like the Viox one for example and that's easy. Take as much time as you want, but I'd love to know what would be a dream experiment for you if

this is the one shot on goal where you've got billions of dollars and no holds barred. Yeah, no, it's easy. It is. Yeah, for me, I mean, it's a dream. You know, I wrote about this with Kaifu Lee and Nature about a tech last month and it's called, it takes a planet. And basically, it would be to, the experiment would be to develop a planetary digital infrastructure with all the data of each individual and continually being assessed and assimilated

a process input federated AI. So the data never leaves the country, whether it's China or the US or wherever. So it does not have privacy security. But the point being is, when a new person comes in and we want to prevent a condition or better treat it, and we have billions of other people to draw from. And we have these digital twins, if you will, because today we learn from clinical trials and it's really farcical in many respects because those clinical trials are contrived and the benefit

is three per hundred or something like that. What about the other people? Well, not only that, it's often three per hundred because of the heterogeneity of the population. Exactly. It might be thirty per hundred if you knew who to apply it to. Yeah, so my experiment would be just for that, you have pinpoint precision because I know Peter's twins, all of them around the world, and what treatment they got, and what outcomes they got, and how I can prevent their issue that they otherwise had. And so it would be to develop the ultimate learning health system. And the twin you're defining is obviously not just genetic, but it's every layer.

So it's my gut twin, my epigenetic twin, or my approximate genetic twin, my phenotype twin, my metabolic twin. Right. And that's, I think, where we can go in the future. And it involves many different types of AI. And I think we'll get there someday. And it's an experience. Is that a 50 year? I mean, what realistically is, I think it could be done in 20, if we were, if we really were going after it, because it's doable. You know, what realistically is I think it could be done in 20 if we if we really were going after it because it's doable You know, the question is it strikes me as bigger than any one country though, right? No, nobody if you get if you get us in China to start it because of the diverse population in the largeness The US being third in population in the world and you get that going and the rest of them join on you know

You pretty quickly you will have twins. Do you have a sense of how much that could cost per person? It just depends on the layers of data and the analytics. I mean, it's not gonna be trivial, but less than you would think. This is mostly, you know, in silico work, it's not, you know, it's happening anyway. What's, what's, this data all sits in places

that's all fragmented. What's the price of a full exome sequence today? Both, a full genome sequence today. So not a 23 in me, but where they're doing the full sequence. Yeah, well, I had some 400, a full genome, 800, 900. So they're sub-a-thousand. They're going to keep coming down. And at scale, perhaps, you know, that's going to happen even faster

But you start having all these things done at scale and you know, right now we don't have enough The reason why a genome isn't valuable is because we don't have a billion people with a sequence and a phenotype Once we start to get into those big numbers Then we start to do so you so you don't think it's that the genome is not deterministic enough. You think it's too small and N so far? That's a bigger problem. Big part of it, yes.

I mean, the genome will never be fully deterministic. I mean, that's not possible, probabilistic, yes. But the probabilistic side of it is hampered because of inadequate numbers. Yeah, because I got to tell you right now, I find every time my patient sends me their genome, I just roll my eyes and say like, no, there's a limited amount of value.

Yeah, well, you know what I usually say to them, I say, look, anything in here that matters, we already know, you know, if you're a 40 year old, and unless you were adopted, you know, sometimes you figure out, you know, this person has Lynch syndrome or something that you had to know. So there are some numbers on that.

If you look at the Danville, Pennsylvania, Dising or Health System, where they've done over 100,000 people, they have excellent, not full genomes, but the coding elements. And they have 5% that they find something quite important, so called pathogenic. So a like Lynch syndrome or BRCA or sudden death, a rhythmia. Which again, my point is if you're doing your job as a doctor, you should have figured that out in the family history and gone looking for it.

But not with, I mean, in other words, in other words, you should have gone to the genome to be confirming what you suspected, hopefully. Yeah, but you know, a lot of that's missed. Like BRCA is a perfect example. You know, what about BRCA men carriers? Yeah, you know, you just don't know. Thank Braka is a perfect example, you know what about Braka men carriers Yeah, yeah, you know, you just don't know Taking a good family history, don't you? I mean it I guess it depends on how much the patients know about their family too

But picture right no those are those are good examples But when I look at the like how many times do I look at Prometheus and it spits out? Oh, you're at a higher risk for atherosclerosis and a higher risk for diabetes and I'm like This is such nonsense, right? Like if you actually understand how to evaluate lipids and you're at a higher risk for atherosclerosis and a higher risk for diabetes. And I'm like, this is such nonsense, right? Like if you actually understand how to evaluate lipids and you're wearing a CGM, you certainly don't need this thing to tell somebody. No, Prometheus, I mean, I think there's gross deficiencies

of outputs because again, going back to, we don't have one central repository of data. Oh gosh, how small is it? In terms of how many millions of people have had sequence, it's small still. You know, it's in the 10, well, it's in less than 10 million for sure of whole genome sequence. And then of course, how many do we have accurate phenotyping on? Because if the phenotype is not that accurate, then it dilutes the quality of what you're trying to do,

right? That's essential because what phenotype we have is fixed. At the moment, the genome was assessed. Exactly. We don't know what the phenotypes change. So all the studies that we have. So this has to be living breathing and longitudinal. Exactly. And that's why I'm trying to see our way through, like, you know, the all of us study of the million people that we're on to right now is the beginning of something like that where all the layers of data for long-term follow-up, it's still tiny, 100,000, I mean, a million people is tiny, but it's a start. But if we could get the leading countries in the world to get behind this, you know, this is something that should override concerns about competition in countries. This is about, you know, for mankind, humankind.

Then we might be able to really develop something that would promote health of all human beings. That would be far reaching. And, you know, what, I actually think this is going to happen someday. I know it sounds farfetched. I know you think, look, and have me like, I'm a little cool. No, I mean, I look at you. A lot of things seem far fetching the moment. I think it's truthfully, I think it's technologically more capable, it's more possible to me technologically than

it is politically. Okay, that's good to hear. I like that. Because I don't. I think the biggest challenge, I'm doing the back of the envelope math, just I think it's a couple trillion dollars to do this in the United States alone. And it depends on how long, I mean, this is over forever, you know. Exactly.

Which means it's a moonshot. And I don't feel like our political environment is capable of moonshot. Well, we're just trying to live day to day here now. Yeah, so long gone are those days when you could make a bold, we're going to spend the equivalent of a couple trillion dollars over 20 years, long after I'm gone, meaning me, meaning the politician who's going to be the torch bearer of this to make this a reality. I don't know.

Maybe I'm just a jaded skeptical guy when it comes to our political side. Well, it's actually, it's actually healthy to be that, looking at that way. And also, I want to also frame it, Peter, as it is an experiment because you still have to, once you develop it at some scale, you still have to prove that it's helping people. Right. So you'll need to use a bias to an unbiased subset of these. Yeah. So, you know, it's theory. It's intriguing. It's doable. And it's going to get progressively better, you know, what we can put in as input. But it's still a question market.

Will it improve? I just think that our complete reliance on clinical trials is misled. I completely agree. I think the heterogeneity problem and the exposure, the time under the curve, the exposure problem make clinical trials very difficult to extrapolate from.

I mean, here's one of my favorite pet peeve examples is people are so quick to dismiss Zedia as a useful drug. But in reality, it's never once to my knowledge been targeted towards patients that are hyperabsorbers of serials. And yet, you know, so Zedia gets sort of diluted in clinical trials because you're giving it to patients that have normal and abnormal absorption of steriles. And so on balance, it doesn't look like a very interesting drug. It seems to work okay with a statin.

But I'm convinced there are patients out there taking statins who should be taking Zedia, because if you can phenotype this, you can really see people who don't make that much cholesterol, but they absorb it like crazy. It's amazing that never would- It's amazing that they never would- Who's going to do that clinical trial, right? No one's going to do that clinical trial. The lack of interest of the people that manufacture the drug because of dilution of the market. I mean, it's really unfortunate, but you're absolutely right about that.

Eric, this has been a really interesting discussion, And I'm glad it's crazy that it took a decade for us to, I mean, I'm amazed you knew my name, I'm flattered, but I certainly know about you from the day I got to San Diego. And I'm just glad the podcast and your book really became a good excuse to sit down. So thank you. Thank you for your work, most importantly, but also thank you for making the time today.

I know you've talked about this a lot, and I'm sure you didn't necessarily feel like talking about the book Oh, and some of these stories over and over again, but I know that people listening to this are gonna appreciate it Well, thanks Peter. I we talked about things I actually haven't really gotten into in the past But I also, you know, really enjoyed great intellectual Thinking with you. It's fun. I hope we'll have a chance to get together a lot more in the years ahead. Oh, we certainly will, we're almost neighbors, so.

It has to happen. Thanks, Eric. Thank you. Thank you for listening to this week's episode of The Drive. If you're interested in diving deeper into any topics we discuss, we've created a membership program that allows us to bring you more in-depth, exclusive content without relying on paid ads.

It's our goal to ensure members get back much more than the price of this subscription. Now, that end, membership benefits include a bunch of things. One, totally kick-ass comprehensive podcast show notes that detail every topic paper person thing we discuss on each episode. The word on the street is, nobody's show notes rival these. Monthly AMA episodes are asking me anything episodes, hearing these episodes completely. Access to our private podcast feed that allows you to hear everything without having to listen to spills like this. The Qualies, which are a super short podcast, typically less than five minutes that we release every Tuesday through Friday,

highlighting the best questions topics and tactics discussed on previous episodes of the drive. This is a great way to catch up on previous episodes without having to go back and necessarily listen to everyone. Steep discounts on products that I believe in, but for which I'm not getting paid to endorse. And a whole bunch of other benefits that we continue to trickle in as time goes on. If you want to learn more and access these member-only

benefits, you can head over to peteratiamd.com forward slash subscribe. You can find me on Twitter, Instagram, your Facebook, all with the ID, peteratiamd. You can also leave us a review on Apple podcasts or whatever podcast player you listen on. This podcast is for general informational purposes only. It does not constitute the practice

of medicine, nursing, or other professional health care services, including the giving of medical advice. No doctor-patient relationship is formed. The use of this information and the materials linked to this podcast is at the user's own risk. The content on this podcast is not intended to be a substitute for professional medical advice, diagnosis, or treatment. Users should not disregard or delay in obtaining medical advice from any medical condition they have, and they should seek the assistance of their healthcare professionals for any such conditions. Finally, I take conflicts of interest very seriously. For all of my disclosures in the companies I invest in or advise, please visit peteratiamd.com forward slash about where I keep an up-to-date and active

list of such companies. you you