#255 Eric Topol: Why AI is the Most Powerful Tool in Healthcare Now

AGNTCY - Unlock agents at scale with an open Internet of Agents. Visit https://agntcy.org/ and add your support. What if AI could predict exactly when you'd get sick—and help you prevent it? In this episode of Eye on AI, Dr. Eric Topol, world-renowned cardiologist, author, and AI health pioneer, joins us to unveil the future of preventive medicine. We dive deep into the themes of his new book Super Agers, which lays out a groundbreaking blueprint for extending healthspan—not just lifespan—through the power of multimodal AI and deep biological data. Dr. Topol explains how AI models can now analyze a full-stack of human data—genomics, proteomics, metabolomics, microbiome, and more—to forecast age-related diseases like cancer, Alzheimer's, and heart disease decades before symptoms appear. This isn't science fiction. It's here now. If you're interested in the intersection of AI, longevity, and the future of medicine, this is a must-listen. Where AI Works tackles the big questions shaping AI's role in business today, cutting through the hype to deliver actionable insights for leaders. Brought to you by the Wharton School, in collaboration with Accenture, this podcast combines cutting-edge research with real-world case studies to uncover how top companies are using AI to upskill workforces, enhance customer experiences, boost productivity, and streamline operations. Check it out: https://link.cohostpodcasting.com/f5e223b4-da0c-4fc8-bbf3-5f24c15f8fd2?d=sxo9xhJN2 Stay Updated: Craig Smith on X:https://x.com/craigss Eye on A. I. on X: https://x.com/EyeOn_AI (00:00) The Power of Precision Medical Forecasting (01:53) Eric Topol's Journey into Digital & AI Medicine (03:27) Using AI to Prevent Aging-Related Diseases (05:25) The Challenge of Health Data Privacy & Ownership (09:05) Genetic Risk to Deep Data Insights (11:20) Personalized Prevention Through Lifestyle & Biomarkers (13:59) Why Anti-Aging Drugs Are Still Years Away (16:18) What are Organ Clocks (19:34) The Longevity Industry's Flawed Use of AI (21:59) Top AI Pioneers Endorse "Super Agers" (24:21) Which Longevity Startups Are Getting It Right? (26:27) Why Topol Refuses to Join Longevity Startups (28:57) Topol's Own Health Data & Lessons Learned (30:25) How Accurate Is AI at Predicting Disease Timing? (31:47) The Truth About Genetic Risk and Cancer Detection (33:33) AI-Driven Cancer Detection: A Smarter Approach (38:51) How Precision Medicine Has Evolved (41:02) The Risky Reality of Anti-Aging Interventions (44:39) Why Healthspan Matters More Than Lifespan

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Speaker 00

  Now things are different. First of all, you have all these different layers that are orthogonal that back up each one, you know, from another, looking to the same try to forecast. I call it precision medical forecast, like the weather forecasting, AI is completely revamping that, uh, making it at accuracy levels that are hard to fathom how great it will be. The same thing is true here. So basically the difference is you've got all these additional layers of data we didn't have. And what's really noteworthy is you can give a person's projection in time when this is going to be an issue if they don't do anything about it. About the science of aging, it's not about the drug. It's about being able to, you know, clock a person, a person and their organ systems, including their immune system. We never had that before. That's what's different right now.

• 0:45Speaker 01

  AI is everywhere right now, but with all the buzz, how do you cut through the noise and focus on what really matters? If you're looking to dive deep into the big questions shaping AI's role in business today, you need to tune in to Where AI Works: Conversations at the Intersection of AI and Industry. Brought to you by the Wharton School in collaboration with Accenture. Each episode cuts through the hype, blending cutting-edge research from Wharton professors with real-world case studies. You will discover how leading companies are leveraging AI to upskill their teams, boost productivity and streamline operations. And you will hear directly from executives and industry pioneers who are implementing AI in their businesses today. No fluff, just practical insights.

• 1:29Speaker 01

  Listen to Where AI Works now on your favorite podcast app and get the strategies that matter most for today's business leaders.

• 1:39Craig S. Smith?

  Introduce yourself to listeners. Obviously you're a doctor, but how you got so deeply involved in the tech space and what your book is about? And then we'll talk about that.

• 1:52Speaker 00

  Well, I'm Dr. Eric Topol. I am a professor and EVP at Scripps Research in La Jolla, California. Uh, I've been involved, uh, from the earliest days of digital medicine, uh, back in the nineties with biosensors, um, with smartphones connected to the internet, even before there was a real digital infrastructure. So back, you know, many years ago, I wrote a book called The Creative Destruction of Medicine, which was about going digital in medicine. And then most recently, uh, about to be published as a book called Super Ager's. It's actually about using AI to promote health span.

• 2:35Speaker 00

  It has not been previously laid out like that. It's a blueprint for how we can go forward. And we couldn't do it without the current types of models with AI. And that's what makes it especially exciting.

• 2:49Craig S. Smith?

  Yeah, I just saw Bill Gates had an interview talking about how someday soon, within the next decade, we're all going to be accessing medical information through agents, AI agents.

• 3:08Craig S. Smith?

  So super agers, the, yeah, give me the thesis of the book. Is it, is it about how AI is going to spread knowledge? And, and, or is it more about aging strategies or how to combat aging?

• 3:27Speaker 00

  Yeah, so there are the three major age-related diseases. Heart, neurodegenerative Alzheimer's and cancer. They all take 20 years to incubate. They all have common threads of the immune system and inflammation. And now we can tell in any given individual, who is at high risk by a full stack of data depth that we've never had before. That's not including, not just including electronic health records and labs and images, but it's also including the genome, proteins, metabolites, the gut microbiome,

• 4:12Speaker 00

  environmental exposures, social determinants of health. Anyway, for all these different layers of data, the AI will tell us.

• 4:23Speaker 00

  If you are high risk, when, pinpointing when, this will show up if nothing is done. And then that can be used to direct surveillance and prevention strategies. So you never have one of those three age-related diseases, which are the biggest burden of our chronic disease and killers, of course. So this is an exciting time. It's unique. It's momentous in many respects because we didn't have the AI that could could input, ingest all this data. And we didn't have the data to ingest.

• 5:03Craig S. Smith?

  Right.

• 5:04Speaker 00

  So what we have now is a is a just extraordinary time to be able to help each person know, especially at a younger age, what's in store for them. And to do these things that would help prevent, at the very least markedly delay, a condition.

• 5:25Craig S. Smith?

  Yeah, and that data, I mean, there are two issues. One is the the privacy issue that's kept a lot of healthcare data locked up, inaccessible to AI models. But also, personal health data that is not necessarily digitized or or very complete longitudinal. I mean, I've moved around the country. I don't know where all my, not the country, the world, where all my data is, if it exists. How do you tackle those two problems? I mean, first of all, on on just more broadly,

• 6:09Craig S. Smith?

  in order to train models, you you need access to large populations, data of large populations. And I'm talking to people, spoken to people over the years about that. It seems that that's.

• 6:27Craig S. Smith?

  Been addressed to a certain extent, uh, but, but yeah, where does, where do you see that uh, today and how it's going to improve?

• 6:36Speaker 00

  Okay. Well, firstly, the data story uh, that you bring up is that uh, and I've written about extensively, even had a book about it, the patient will see you now. People should have all their data. It's their data. They should own it and it should be uh, kept in a secure platform. Uh, and so other countries do that, just not here in the U S. Um, but that's the ideal scenario because you're not going to put your uh, genome sequencing data or your biosensor data or other layers of data into your electronic health record because we don't protect people fully for things like um, disability insurance

• 7:17Speaker 00

  and life insurance and you know, various things that are not related to health insurance. Uh, and the so-called GINA, you know, discrimination uh, of people about their genetic information. So, we have to come up with a better plan about where all that data sits and that each person is entitled, it's their data, their body, their, that, that's critical. Now, it turns out the A M. Models that we have now um, are very well suited for um, supervised fine tuning for this task. I mean, the fact is they're multimodal, uh, they're now a foundation.

• 7:58Speaker 00

  Um, we can use of course, uh, domain specific agents. But no problem here with respect to the models. That, if you were talking pre-transformer architecture, yes. But in the current environment, we even are getting, you know, these reasoning capabilities. And you know, we're not, it's not like a lot of these things have to be um, outputs in seconds. We can, we can wait uh, minutes, hours, days even for the best output. So, the models are not to hold up, the data uh, ownership is actually uh, an issue that has to be grappled with. In the meantime though, many people have been able to uh, collect all their data,

• 8:42Speaker 00

  curate everything of theirs, uh, particularly engineers and certain people, you know, patients of mine that have everything. Uh, and so they're very well suited to enact this now.

• 8:55Craig S. Smith?

  And is, okay, so that's the personal data. What about this, this more universal data to train the models?

• 9:05Speaker 00

  Yeah, it's surprising that it's not as big a challenge as you would expect because

• 9:13Speaker 00

  a lot of the things in medicine and life science, we would never predicted that the models that already were appearing, like in GPT-4 and Llama and others, really were remarkably well-suited for this, just by having ingested everything known to mankind about medicine and, you know, the whole corpus of knowledge related to this. So that, that, you know, in the work that's been done so far, to look at being able to predict the arc of a person's, let's say, risk for Alzheimer's and when they would get out, we can do that now.

• 9:58Speaker 00

  We don't, you know, we don't need new models, in fact. So the difference now is, Craig, is that up until now, let's say you had a so-called polygenic risk score, where you could go to 23ME or a whole bunch of different companies and tell you, you know, Craig, you have a risk of a tie for, let's say, Alzheimer's disease. And the only problem with that is, well, there are two problems. One is it might not be that accurate. But the bigger problem is, what if it, the risk is when you're 98 rather than 68? They're different. And there was no way to be able to ascribe a time range. Now things are different.

• 10:40Speaker 00

  First of all, you have all these different layers that are orthogonal, that back up each one, you know, from another, looking to the same, try to forecast. I call it precision medical forecasting.

• 10:53Speaker 00

  Like the weather forecasting, AI is completely revamping that. Uh, making it at accuracy levels that are hard to fathom how great it will be. The same thing is true here. So basically the difference is you've got all these additional layers of data we didn't have. And what's really noteworthy is you can give a person's projection in time. When this is going to be an issue, if they don't do anything about it. Now, many of the interventions or preventive tactics. Involve lifestyle changes. And we know a lot of those, but most people don't do any of those. Uh, or you know, change behaviors or, but what we've also learned that when you have specific knowledge about yourself.

• 11:38Speaker 00

  The chances of you taking on some of these changes are much higher. So they could now much more specifically, um, bespoke to your situation. But by the way, it isn't just lifestyle changes that can help prevent these conditions. I mean, obviously there's surveillance, whether it's. Cancer surveillance with multi-cancer early detection blood tests, or whether it's surveillance for neurodegeneration with these new. Uh, P tower two seventeen biomarkers, which was a really big breakthrough. Each of these disease. Uh, age-related diseases has ways we can stay ahead of it.

• 12:18Craig S. Smith?

  Yeah, uh, it just reminds me, it's on the side. So this is really about prediction.

• 12:26Speaker 00

  Yes.

• 12:26Craig S. Smith?

  Uh, I've been talking over the years to Alex Javron, Javronikov. Uh huh. From Insilico, I'm sure you know of him, if you don't.

• 12:36Speaker 00

  Oh, yeah. No, I know him. He, he sends me stuff all the time.

• 12:39Craig S. Smith?

  Yeah. Well, and his, you know, he's all on, uh. You know, anti-aging, uh, and that's kind of his motivation. And he's, you know, he's got a very sophisticated, uh. Process for drug discovery and.

• 12:56Speaker 00

  He does.

• 12:56Craig S. Smith?

  Molecules, yeah. Uh, and there he's working on inflammatory diseases because. Uh, he, he sees that as one of the, the major, uh.

• 13:11Craig S. Smith?

  Manifestations of aging that end up leading to death.

• 13:18Speaker 00

  Yeah, fibrosis.

• 13:20Craig S. Smith?

  Yeah.

• 13:23Craig S. Smith?

  Have you looked at in the book, do you look at using this technology to develop drugs to target specific diseases of that are endemic to aging?

• 13:38Speaker 00

  Yeah, so this is, I do review all the different strategies that are now being pursued. And, you know, everything from partial epigenetic reprogramming to you name, or you know, different repair.

• 13:55Speaker 00

  Like what in silical medicine is on to with pulmonary fibrosis. You know, I review all that, but basically the conclusion is there, these are years away, if ever. You know, things like senolytics to take out arsenic cells in our body, but they can't tell the good senescent cells from the bad senescent cells. And a lot of these things, you know, in induce cancer some in some organisms. So they're risky, they're iffy. They're often time, but today, what we can achieve is using AI tools and rich data, deep data for each person to forecast like we've never been able to do before.

• 14:39Speaker 00

  And so one of the biggest breakthroughs were these so-called organ clocks. So where Alex and I and many others in the age into aging field converge is there have been dramatic advances in the science of aging.

• 14:53Craig S. Smith?

  Yeah.

• 14:54Speaker 00

  And what is an outgrowth of that are these things, these molecular clocks, like epigenetic clocks, like the Horvath clock. We look at methyl groups on the DNA. And there's also organ clocks of from from a tube of blood, you can get eleven thousand plasma proteins and it'll tell you which organ. So it's a Craig, all your organs are great, but it turns out your your heart is, you know, seven years accelerated aging, which tells us right away, you know, that's what we got to zoom in and for you. So we're seeing tools that we never had either breakthrough test about the science of aging. It's not about the drugs. It's about being

• 15:34Speaker 00

  able to, you know, clock a person, a person and their organ systems, including their immune system. We never had that before. That's what's different right now. And with these different proteins and assays, we can say, hmm, we measured it this year. We measured it, you know, this year. Oh, that means for you to be worried about this, it's if you if you don't really go full court press at age, you know, whatever seventy one, this is going to hit you. You're going to start having symptoms. So with that point that we have twenty years to undo the natural history of risk,

• 16:14Speaker 00

  it's it's a, you know, this is a whole different strategy. The book is about a different strategy than the one that these companies are pursuing like Altos Labs and Unity and in Silico, you know, there's fifty of these anti-aging companies, right? I'm saying, good, good luck to them. I hope they're successful. But I have a different plan. That's not risky. Okay, because preventing diseases is a is a dream in medicine that's been a fantasy that's been around for, you know, multiple millennium. Now we have a chance to do something about it.

• 16:54Craig S. Smith?

  Yeah, is how much of this is productized at this point?

• 16:59Speaker 00

  There everything's like, you're right, everything's piecemeal. So you got to go here to get your organ clock. You got to go here to get your your epigenetic clock. You got to go here to get your metabolome. You know, here to go, you get your gut microbiome. So it isn't the package isn't, but you could do it. You can do it. It's just that the the AI tool is separated from each of the layers of data. It's just a matter of time when this comes together.

• 17:31Craig S. Smith?

  Yeah.

• 17:31Speaker 00

  Your point is a good one, Craig.

• 17:33Craig S. Smith?

  Yeah, I just I just wrote a a piece for Forbes about

• 17:40Craig S. Smith?

  MCP.

• 17:43Craig S. Smith?

  I'm not going to remember what it stands for, but this Anthropic developed a standard protocol for connecting AI systems to disparate data sources or tools, sort of thing.

• 17:58Speaker 00

  This one is being cracked every day with multiomic. So in the life science field, which is what this is really converging with, they are already looking at every layer, DNA, RNA, single sequence, a single cell sequence nucleus, and all the other ones I've mentioned. They've already figured out how to do all that.

• 18:17Craig S. Smith?

  Yeah.

• 18:18Speaker 00

  And that's exciting because that's just part of this. All you got to do is, you know, add in a couple of traditional medical pieces like the electronic records, which contain labs and images, and you're there.

• 18:31Craig S. Smith?

  Yeah. In the book, do you go through how somebody could collect all of this data? Because for the layperson, I would, I mean, just the the list that you mentioned, I don't.

• 18:47Craig S. Smith?

  Know anything about, did you say melanome?

• 18:51Speaker 00

  Oh, the metabolome.

• 18:52Craig S. Smith?

  Metabolome, yeah, I mean, I don't know what that is, where it is, how I could find it.

• 18:59Speaker 00

  Yeah, well, there's a company Metablon that does that and other companies as well. I don't go through that step by step. I just basically trying to say, look, folks, we're going to a new era where you're going to know your risk. And I lay out, you know, what, what are the layers of data, how we're going to do this? In the next year or two, we'll see the companies that have the whole package. Right now, there's these companies pitching data for longevity. And I called them out. I wrote a sub stack about that recently. You know, these, these companies that are selling supplements, I mean, these, this is, this is not, it's not high science, but they have the right idea. Okay.

• 19:43Speaker 00

  Because some of them are assembling these different layers of data already. They're not using AI. Sometimes they say on their website, they use AI, but no, they're not.

• 19:53Craig S. Smith?

  Yeah.

• 19:54Speaker 00

  Not real AI. So we're already seeing the bud, budding, you know, there's, there's several companies that this is in their sights right now. And it's not going to take long for them to adapt to the opportunity. Um, which, you know, th- this is very clear path to achieving something we've never been able to do before. Our ability to give a person's risk assessment of a disease has been rudimentary at best. But actually incredibly weak and inaccurate. And it's our most important thing is that we should be knowing well in advance what we have to prevent and how we, how we do it.

• 20:38Craig S. Smith?

  Yeah, and one thing you you said, I was thinking as you're talking, you know, I've looked a lot at ed tech and I've spoken to a couple of companies that have an assembly of algorithms and and one of the things that struck me as most promising is that you can have a knowledge tracing algorithm that that tracks the knowledge of a student as the student studies, provided that they're interacting digitally. And then you can have a prediction algorithm

• 21:17Craig S. Smith?

  that that predicts the student's score in an exam or in a course. And then you can have a recommendation engine that recommends stuff to fill in the knowledge gaps. And when you put it all together, I mean theoretically, the student, if he follows the recommendations, can see his predicted score going up. And that's a huge motivator. It could be the same thing with

• 21:46Speaker 00

  Same exact model type there. I agree.

• 21:49Craig S. Smith?

  More compelling because it's your lifespan that you're increasing, not

• 21:56Speaker 00

  Yeah, exactly. And just to add to it, so you know, the likes of Jeff Hinton, Demis Tsabis, Mustafa Suleyman, all three of them, you know, reviewed the book. And they all thought this is, you know, extraordinary. They they supplied, you know, endorsements, not, you know, because they see that,

• 22:17Speaker 00

  you know, both, actually, both Demis and Jeff have said that the most important ever use of AI will be to improve our health. And this is, I think, unless I don't know, Craig, but I don't think anybody has laid out how we're going to do this yet. This is kind of, that's why I'm excited about it. And they were excited about it. So, you know, we have now a way

• 22:42Speaker 00

  It's very similar to what you just described in education. Of course, it's a totally different application. It's a little more complex, but it's it's ready to go. It's not going to take long to get there.

• 22:57Speaker 03

  Building multi-agent software is hard. Agent to agent and agent to tool communication is still the Wild West. How do you achieve accuracy and consistency in non-deterministic agentic apps? That's where agency comes in. A G N T C Y. The agency is an open source collective building the Internet of Agents. And what's the Internet of Agents? It's a collaboration layer where AI agents can communicate, discover each other, and work across frameworks. For developers, this means standardized agent discovery tools,

• 23:39Speaker 03

  seamless protocols for inter-agent communication, and modular components to compose and scale multi-agent workflows. Build with other engineers who care about high-quality multi-agent software. Build with other engineers who care about high-quality multi-agent software. Visit agntcy.org and add your support. That's A G N T C Y dot O R G.

• 24:11Craig S. Smith?

  Yeah. What can, are you free to mention companies that you think are on the right track in coming out with an application?

• 24:21Speaker 00

  Uh, well, I reviewed all of them that are out there. Um, and, you know, there, I'll just pull up the chart I made from the ground truths that I did. Uh, one sec here, if you can bear with me.

• 24:36Craig S. Smith?

  Sure.

• 24:38Speaker 00

  Uh, yeah, I just put it out a week ago. I called it the business, the business of promoting longevity and health span. Basically, the twelve companies, um, there was one that started this years ago, a decade ago called Human Longevity. They get total body MRI and genome sequence. This was before there was any AI. Uh, got all these labs and whatnot. That company is just basically not, almost nonexistent now. Charging twenty five thousand dollars to come and have all these things done. That's, that's a no brainer, not gonna work. Uh, Function Health, they do a hundred lab tests. That's it, you know? So that's not exactly what we're talking about.

• 25:21Craig S. Smith?

  Yeah.

• 25:21Speaker 00

  Um, and of the ones, Life Force is, um, I think on the right track. Um, let's see, uh, going down the list, um, Fountain Life is trying to get a whole lot of tests. Actually, when you look at them, they have the right idea that you need more layers of data, but none of them are getting the right data. I wrote about that in the post, you know? They're not kidding. They, they have this idea that, oh, if I know much more data about a person, I can guide them. They're just not getting the right data and they, they, they don't, none of these companies have a, a significant AI effort yet. But some of them have raised immense capital, like for example,

• 26:05Speaker 00

  uh, Function has, has a valuation of two and a half billion dollars already. It has, uh, fifty thousand members on a waitlist. Uh, Neko Health has a hundred thousand people on a waitlist. So people want this.

• 26:19Craig S. Smith?

  Yeah.

• 26:20Speaker 00

  Okay, uh, but they, they're not, they're a little clueless about they're not getting what they should get.

• 26:25Craig S. Smith?

  Yeah. Uh, are you advising? I mean, you obviously are deep in this.

• 26:30Speaker 00

  Not advising any of them. I don't want to be conflicted.

• 26:34Craig S. Smith?

  Well, wh- why you, you have a deep knowledge of AI and you have a deep knowledge of medicine? Uh, have you thought about doing exactly what we're talking about?

• 26:47Speaker 00

  I, I, okay, so the Function Health, the one that has this massive valuation, uh, one of the principals is a doctor named Mark Hyman. He flew here, right? He was sitting in my office and he offered me to, you know, be part of the company and, you know, get all sorts of financial incentives. I told him, Mark, I just can't do that. I, I, because if I do that, then people will read this book or see me as, you know, I'm doing this for financial gain, just like they sell supplement, which I don't agree with. That's another reason I wouldn't do it, right? Uh, so basically I can't, uh, for me, it's much more important to put out the ideas and not have any profit motive whatsoever. Yeah.

• 27:30Craig S. Smith?

  Yeah. Yeah, well, I didn't mean it so much as, as profit motive. I mean, obviously you're you've had a financially lucrative career. Uh, but just as you, you see the problem, you see the solution, you have the knowledge. Uh, and certainly the context to pull together a team that, that could solve the problem.

• 27:54Speaker 00

  Uh, well, I, I just wanted to get it done. And like I have done in the other previous books, I gave a lot of people the ideas. I, I so many people have written me or come to visit me and tell me, you know, I built my company because of what you wrote. And that's kind of what I'm hoping is other people can execute. Uh, here's the, here's the recipe, here's the blueprint, whatever you want to call it. And that's, I think, how it's going to get done. Now, the reason I mentioned these companies, they already have a head start. They have revenue, they have, you know, some, some of them have pretty strong participation, memberships, whatever. So I, I, I'm perfectly happy to see them pivot, do this right, get there where we eventually all will be.

• 28:38Speaker 00

  I don't want this to be a thing just for the affluent either.

• 28:41Craig S. Smith?

  Yeah.

• 28:41Speaker 00

  This, in fact, the people who need this the most are the ones who can't access or afford it.

• 28:47Craig S. Smith?

  Yeah. Uh, how much of this, I mean, you, you understand the relevant data, how to get the relevant data? How much of that have you done yourself?

• 28:56Speaker 00

  Uh, most of it. So in the book, I got, uh, an immunome, the beginning of an immunome from a company, Infinity Bio. Uh, John's Hopkins spinoff, which is a, another essential part of the layers of data. Uh, I've had most of the other layers of data, uh, you know, uh, so. I have done this and the only risk of this big three that I'm facing is the cardiovascular risk. And so now I know what I gotta do. I'm gonna get my LDL down to the lowest level and, you know, ten other things that I gotta do. But there are things that, you know, turning to much better sleep health, getting much

• 29:39Speaker 00

  better deep sleep, and many other things that we can do. Once we know, you know, what we're after now, if you if you find that you don't have a risk for one of these big three diseases, well, you're lucky, right? Doesn't mean you should go out and go into self-destruct mode, but you're lucky. The point is, most people, one of them, if not more than one, have vulnerability. And the question is the cutoff. You know, top five percent, top 10 percent, that's something that, you know, is still gonna be debatable for years to come. What is the risk, right?

• 30:15Craig S. Smith?

  Well, and and you were talking about the timing, predicting the timing of risk. How accurate do you think that can be? I mean.

• 30:25Speaker 00

  Yeah, I think it can be. It's hard to get it on one shot. But if you have a person that you see is at high risk, by the time you do a second assessment, then you have it. So if you have just two points on the curve, you'll know what's about the brain amyloid accumulation, what about microscopic cancer showing up, what about atherosclerosis forming in arteries? So, yeah, it doesn't take, it's hard to do it on a single point basis, but two data points separated in time by six months or a year and you nail it. The key is that first baseline.

• 31:04Craig S. Smith?

  Yeah.

• 31:05Speaker 00

  To determine the risk and then use the second point to determine the timing.

• 31:09Craig S. Smith?

  Yeah. And for the timing, for example.

• 31:17Craig S. Smith?

  Let's pick one, cancer.

• 31:19Speaker 00

  Yeah, yeah.

• 31:20Craig S. Smith?

  Uh, you know, you look at your family history, you look at presumably different biomarkers. Uh, maybe your, your personal genome. Uh, wh- what would, what would the prediction be that, that in three years, in fifteen, twenty years, you, you have an, uh, you know, a ninety-five percent chance? I mean, what does the prediction look like?

• 31:47Speaker 00

  Okay, well, the ninety-five percent, that's what we were talking about earlier, top five percent. That would be ninety-five percent, uh, or very high risk, that is, um, you know, somewhere. I'm thinking, you know, most people, if they're not in the top five or ten percent, they, they're not gonna really. It's, that's really where you draw the threshold. That's where some medical health systems, like, for example, Mass General Brigham has drawn the threshold for genetic risk. So let's just say we're talking about top five or ten percent. We're not likely to get out a readout that, you know, this is gonna happen in eighteen years. But certainly, you know, when it's more proximal, like three to five years, that would be the way it show up. Now, how do we get this? Well,

• 32:30Speaker 00

  it turns out, and I make a really important point early in the book. We have overestimated the family history genetic story. Okay. Now, for cancer, it's more of an issue than it is for the other two, because if you have any of these, uh, cancer predisposition genes, I'm not just talking about BRCA genes, but other genes. That puts you in a different strata of risk. But the point being here is that there are many other factors, like the level of your body inflammation, that those organ clocks, again, the, the, uh, your total body aging clock. If you're seeing things that are out of kilter,

• 33:13Speaker 00

  and then you get a multi-cancer early detection test, the chance of that being abnormal. See, today, what's amazing, these tests are advocated for people age fifty, period. Now, talk about a, a, a senseless way to use a test. You know, out of a thousand people that get the test now, nine hundred and ninety-five are negative. Okay, but when you use that test, when you have these other things that are suggesting increased risk, then the yield is so much higher. I mean, this is Bayes' theorem, you know. So that's how we get the risk of cancer nailed down. And then, of course, if there's an organ clock that's already showing up, you can start to, and you can get images,

• 33:58Speaker 00

  of course, like that total body MRI, if you really, but the multi-center cancer detection test already with AI can tell you which organ is lighting up most of the time, very accurate, actually. So the cancer story, I think, is not that hard to see through. As long as you don't say it's just the genes, that's our biggest problem is we think we have this kind of over emphasis about our family history and this kind of dooms, impending doom thing that we live our whole life. My father had a heart attack when he was 50, and you think about that like all the time. We got to get that out of our system because that just

• 34:42Speaker 00

  doesn't really play out. We did a so-called Welderly study, we called it here. 1,400 people lived through past age 85, never sick, none of these diseases. We sequenced whole genome, all of them. And what did we find? Very little, almost nothing. So the secret in the genes thing is not so, there's not that much to it. There's a little, but not much.

• 35:11Craig S. Smith?

  Yeah. The, um, let me think, where do we go with this? The conclusion of, of the book then is that there's this promising technology that's here, and there's ways to get the data to make the technology useful. What, what are you, this is, I would presume not only for

• 35:49Craig S. Smith?

  AI technicians, but for general readers, what what is the what is the recommendation? I mean, what is the the? What is the book telling us to do?

• 36:04Speaker 00

  Well, there's a whole chapter on these lifestyle things that, you know, it'd be great if we adopted all those now. Right? Because you you don't without even knowing your risk for a particular condition. It'd be good, but I I review all the data, you know, everything from, you know, protein and ultra processed foods and environmental hazards, microplastics, I mean, all this stuff, each of us have at least some potential to affect. Right? And then I get into this, what I call, you know, brimming with optimism. That we have a much more, you know, exciting way to go forward in medicine. To be able to be informative early in a person's life, and I mean, it's never too late, but

• 36:50Speaker 00

  for people of our age, but even better is, you know, somebody in their 40s or 50s.

• 36:56Craig S. Smith?

  Yeah.

• 36:56Speaker 00

  Or younger even, but the point here is that there's a new path forward that I think is transformative in medicine. We couldn't do it without multimodal AI models that exist today and are keep getting better. And we couldn't do it without the layers of data that were discovered largely through the science of aging. But a lot of people are using that, you know, course for companies to come up with drugs.

• 37:23Craig S. Smith?

  Yeah.

• 37:24Speaker 00

  And I'm saying, no, no, no, we got it for a different purpose now. And let's stamp out age related diseases. Let's do it. So that the book leaves the lay reader, I hope, with an optimistic view in otherwise pretty dark times for life science right now, when, you know, our funding is getting gutted every day. People are getting, you know, laid off from NIH, FDA, CDC. So on the one hand, the world isn't doing too well right now. But here's something that's hopefully, you know, exciting to. Read about, know where we're headed. I mean, each of the books I've written, this is my fourth book, probably my last book,

• 38:02Speaker 00

  is about the future of medicine. And this one is the most exciting yet. This one, I think, is something we can really make a huge difference in the future.

• 38:14Craig S. Smith?

  Yeah. I, on, you know, there's a lot of talk about personalized medicine and with, with, you know, the ability now to,

• 38:27Craig S. Smith?

  edit the genome and

• 38:32Craig S. Smith?

  create novel proteins. What's your view just generally? I know this is not what your book's about, but about the promise of

• 38:45Craig S. Smith?

  precision personalized medicine becoming widely available?

• 38:51Speaker 00

  Yeah, I'm really glad you asked that, Craig, because this is the nuts of it right here. We haven't really done it. You know, here and there, we did a little with, oh, well, you have this mutation and cancer, we're going to treat you with this drug or, you know, but precision medicine largely has been a disappointment. It's been talked about a lot, but we haven't achieved it.

• 39:17Speaker 00

  This is our segue, this is our, our, our way to get there because we didn't have the depth of data. So when we talk about precision individualized medicine, we couldn't really define that person well. We're still missing the immunome data, which is one of the most, if not the most important layer, but there are companies that are pursuing that, you know, intensely right now. And I tried one of them and there's a couple others. A group at Stanford that plans to spin out of a company that does B and T cell sequencing that looks really exciting. So we just didn't have the goods to do it. And it was all talk and no action largely. Now we have the goods and I hope we have the action.

• 40:02Craig S. Smith?

  I don't want to keep you too much longer, but you know, you also mentioned epigenetic research or strategies. And I had Sebastiano Vittorio, Vittorio says Sebastiano on the podcast years ago, who works on using Yamanaka factors to

• 40:29Speaker 00

  Yeah, yeah.

• 40:31Craig S. Smith?

  To roll back the aging of cells. And you mentioned the risk is that a lot of this leads to cancer. But do you is, what do you feel about that? And you mentioned organ specific, or I don't remember the word they use, but treating, you know, specific groups of cells epigenetically, senescent cells.

• 41:03Speaker 00

  Yeah, so, yeah. So, yeah, so the first one you mentioned is, you know, huge bets have been put on this. Many companies are pursuing the Yamanaka factors.

• 41:15Craig S. Smith?

  Right.

• 41:16Speaker 00

  And, you know, you brief exposure to them and you can turn an old mouse into a young mouse. I mean, it's like, wow, you know. But the problem is, is that you can't just give these, you know, a shot to somebody with

• 41:30Craig S. Smith?

  Yeah.

• 41:31Speaker 00

  Unless you

• 41:32Craig S. Smith?

  Excuse me.

• 41:33Speaker 00

  But you give, then you have a real risk of tumor. So what's fascinating is these companies have figured out, you just can't give it like you can give it to a mouse. So what they're trying to do is figure out, how can you do a human trial? So one of the companies is thinking about going in the knee for people who have horrible knee arthritis and otherwise need a knee replacement. Another company's putting it in the eye, you know, so they're not achieving the fountain of youth here. They're going to try to do in a limited compartment test zone, if you will, right? It's gonna be dicey because we've already learned that the exposure to those powerful

• 42:14Speaker 00

  factors, the yamanaka transcription factors, well, that's a really risky strategy. It's like the reward's really high, but you know, putting that on a human, we're gonna, it's gonna take a long time before we see a whole human get exposure to those, you know, intravenously or whatever systemic pathway. The other companies, like I mentioned, that these senescent cells that are thought to be bad actors because they secrete very noxious proteins and they rev up inflammation in the body. The problem is some of them are really good and we don't have a way to say just go after the bad actors.

• 42:56Speaker 00

  Leave the good ones that are promoting healing and doing lots of good things and, you know. So, we don't have smart ways to eradicate the bad cells. And if you go through each of these, and there's at least 10 different ideas, which I go through in the book, they all carry significant risk. They're all some years away and I hope that they're successful, but they're not here and now.

• 43:24Craig S. Smith?

  Yeah.

• 43:25Speaker 00

  What we've been talking about in this conversation is a kind of here and now thing, right? It can be done today or imminently. Those are years off and maybe never. I, I hope they're successful. Each one of them has some good ideas, but we'll see.

• 43:42Craig S. Smith?

  Yeah. Another thing about sort of the aging debate that you hear people talk about, and I'm just curious what your view is. Of course, I wanna live much longer than I'm slated to live. I tell my wife, gosh, I wish I had 40 years instead of 20 years or, you know.

• 44:08Craig S. Smith?

  But if if everybody added five years to their lifespan, the demand for resources would quickly be overwhelming. I mean, how do you balance, you know, a human desire with with

• 44:32Speaker 00

  Yeah, well, first say the desire really isn't for lifespan, it's for health span, right? I mean,

• 44:39Craig S. Smith?

  Yeah, that's right.

• 44:40Speaker 00

  If they're demented, they don't really want to live longer.

• 44:43Craig S. Smith?

  Yeah.

• 44:43Speaker 00

  So you're right. I mean, it's hard to meet a person when you talk about would you like to live healthier, you know, long life and, you know, rarely would you say no.

• 44:54Craig S. Smith?

  Yeah.

• 44:55Speaker 00

  You hear someone say no. So you're the demand will be high. And, you know, what we're talking about here is largely it's software because these tests, they get you those additional layers, they can be done inexpensively. You know, every one of these is, you know, it's below a hundred dollars, fifty dollars, you know. So even if you take the whole package, it's it's not like putting somebody in a total body MRI, which now you're getting into the thousands. So the interesting thing is, it may get done in other countries before the US.

• 45:28Craig S. Smith?

  Hmm.

• 45:29Speaker 00

  Because we have terrible perverse incentives here. We have these insurance companies that they don't think they're going to have you next year. So they only care about immediate gratification, right?

• 45:39Craig S. Smith?

  Yeah.

• 45:39Speaker 00

  Whereas if you're in other countries, like, you know, I was asked to review the National Health Service in the UK, they're representative of most other rich countries, which is they take care of all their people.

• 45:54Craig S. Smith?

  Yeah.

• 45:54Speaker 00

  For life. So they're going to be the countries that make these, you know, basically implement. And here it will be more likely to be, you know, if you're affluent and you, you know, the demand, I do think the demand will ultimately be high, you know, some years out from now when this is widely available. But we're not in a good position in this country to make it equitable or accessible relative to other countries because they can see a small investment can lead to a huge downstream reductions of cost, no less healthier lives.

• 46:33Craig S. Smith?

  Yeah, yeah. Okay, well, this is just fascinating and I'm going to go buy the book right now on Amazon. It's, it's coming out May.

• 46:46Speaker 00

  I could send you the PDF if you like instead.

• 46:49Craig S. Smith?

  I don't mind pre-ordering.

• 46:52Speaker 00

  I'm waiting to get the actual hard copy tomorrow or Thursday, finally.

• 46:56Craig S. Smith?

  Yeah.

• 46:57Speaker 00

  And I think it was Stephen Morrow that got us together. Is that right?

• 47:03Craig S. Smith?

  I, I'd have to go back and check.

• 47:06Speaker 00

  Yeah, I thought maybe he was the one that, um, he said, you got to talk to Craig. I don't know.

• 47:10Craig S. Smith?

  Well, maybe he will have been, yeah.

• 47:13Speaker 00

  Anyway, it's been a joy, Craig. I really enjoy. You asked a lot of great questions that, um, I, you know, I think are really spot on.

• 47:22Craig S. Smith?

  Yeah, well, I'm probably all, once I get the book, um, uh, well, how about this? How about you send me the PDF and I promise to buy it. I just, my wife writes and I always think you should, people, if they're interested in a book, they should buy it, not, not get a free copy. But, but if you could send me the PDF, uh, I'll, I'll, I'll write something. I'm a contributor at Forbes, not that that gets a lot of traction, but, uh.

• 47:53Speaker 00

  Oh, great. Darren, can you send me your email address?

• 47:56Craig S. Smith?

  Yeah, I'll do it right after this.

• 47:58Speaker 00

  Excellent. All right. We'll get it off to you and it's been a pleasure to talk with you.

• 48:03Speaker 01

  AI is everywhere right now, but with all the buzz, how do you cut through the noise and focus on what really matters? If you're looking to dive deep into the big questions shaping AI's role in business today, you need to tune in to Where AI Works, conversations at the intersection of AI and industry. Brought to you by the Wharton School in collaboration with Accenture. Each episode cuts through the hype, blending cutting-edge research from Wharton professors with real-world case studies. You'll discover how leading companies are leveraging AI to upskill their teams, boost productivity, and streamline operations. And you will hear directly from executives and industry pioneers who are implementing AI in their businesses today. No fluff, just practical insights.

• 48:47Speaker 01

  Listen to Where AI Works now on your favorite podcast app and get the strategies that matter most for today's business leaders.