The Dr. Hyman Show - The Next Revolution In Medicine: Scientific Wellness, AI And Disease Reversal with Nathan Price & Lee Hood

Episode Date: September 20, 2023

This episode is brought to you by Rupa Health, Kettle & Fire, LMNT, and Cozy Earth. Recent technological advances are completely changing the way we understand the body. Revolutions are happening on multiple levels–the “omics” revolution, the digitization of data, and the systems biology medicine movement. Today, I’m excited to talk to Drs. Leroy Hood and Nathan Price about the future of personalized healthcare through scientific wellness. Dr. Leroy Hood is the CEO and founder of Phenome Health, a non-profit organization developing a project called Human Phenome Initiative (HPI), based on the science of wellness, which will sequence the genes and generate the longitudinal phenomes of one million people over 10 years. He has co-founded 17 biotech companies. His many national and international awards include the Lasker Prize, the Kyoto Prize, and the National Medal of Science. He is also the Chief Strategy Officer/Professor at the Institute of Systems Biology in Seattle. Dr. Nathan Price is the Chief Scientific Officer of Thorne HealthTech and author of The Age of Scientific Wellness. In 2019, he was named one of the 10 Emerging Leaders in Health and Medicine by the National Academy of Medicine, and in 2021 he was appointed to the Board on Life Sciences of the National Academies of Sciences, Engineering, and Medicine. He is Affiliate Faculty at the University of Washington in Bioengineering and Computer Science and Engineering. This episode is brought to you by Rupa Health, Kettle & Fire, LMNT, and Cozy Earth. Access more than 3,000 specialty lab tests with Rupa Health. Check out a free, live demo with a Q&A or create an account at RupaHealth.com. Head over to kettleandfire.com/Hyman today to see all of their products and use code HYMAN to save 20% off your entire order. LMNT is offering my listeners a free sample pack with any purchase at DrinkLMNT.com/hyman. Get 40% off your Cozy Earth sheets at cozyearth.com and use code DRHYMAN. Here are more details from our interview (audio version / Apple Subscriber version): Systems biology and scientific wellness (5:41 / 4:25)  Three components of the human phenome (20:07 / 18:30)  How big-data analytics and AI can be used to optimize health (24:30 / 22:30) The majority of health and wellness happens outside the doctor’s office (41:28 / 37:47) Educating the public about the future of medicine (43:23 / 39:21)  Training AI machine learning models (52:47 / 49:11) Drs. Hood and Price’s daily health routines (1:13:49 / 1:10:12)  Get a copy of The Age of Scientific Wellness: Why the Future of Medicine Is Personalized, Predictive, Data-Rich, and in Your Hands.

Coming up on this episode of The Doctor's Pharmacy. And you can actually forecast the likely amount of time that you have with a healthy brain given your current state. Hi everyone, it's Dr. Mark. As a functional medicine doctor looking at hormones, organic acids, nutrient levels, inflammatory factors, gut bacteria, and so many other internal variables, it helps me find the most effective path to health and healing for my patients. But such extensive testing can be very complicated and time-consuming for both the practitioner, somebody like me, and our patients. But lab ordering became very quick and painless since I started using Group of Health. I can order, track, and get results from

over 35 different lab companies within a few clicks in one lab portal. And this means one invoice for all labs paid online up front. Plus, patients get practitioner pricing and receive full patient support through easier personalized collection instructions, automated follow-up, super bills, and answers to testing questions, and so much more. And best of all, it's free for practitioners. So sign up free today. You can find out more information by going to rupahealth.com.

That's R-U-P-A health.com. What if I told you there was a delicious way to support your immune system, your digestive system, fight inflammation, and get in some collagen and amino acids to support your skin, joints, and bones, and support your sleep and your brain daily? Well, there is. It's called bone broth. And my favorite convenient way to drink bone broth daily is with kettle and fire.

They make super easy to use bone broth that you can get delivered straight to your door to make soups, stews, or just sip on by themselves, which is what I often do. I've tried so many different bone broths and this is the best one. Head over to Kettleandfire.com forward slash Hyman today to see all their products and use the code Hyman to save 20% off your entire order. That's Kettleandfire.com forward slash Hyman. And now let's get back to this week's episode of The Doctor's Pharmacy. Welcome to The Doctor's Pharmacy. I'm Dr. Mark Hyman.

That's pharmacy with an F, a place for conversations that matter. And today's conversation is about the future of healthcare, about an age of scientific wellness, a revolutionary new way of thinking about how we look at our own biology through the lens of what's really emerging as the principal model that we should be using for medicine, which is systems medicine and biology. And we have with us two of the leading proponents, advocates, pioneers in this field. It's a real honor to have them. Dr. Leroy Hood is the CEO and co-founder of Phenome Health, which is a nonprofit developing a project called the Human Phenome Initiative based on the science of wellness, which will sequence genes and generate

longitudinal phenomes of 1 million people over 10 years. A phenome basically is the expression of your genes. So what your medical history is, what disease you have, what biomarkers you have. So it's the expression of your genes. So it's really important not just look at your genes, but actually what all those genes are doing and how it affects your health. And it's going to help us deliver a totally new paradigm in healthcare based on prediction, prevention, personalization, and participation. It's what Leroy Hood calls the P4 model of healthcare. And it's really very aligned with functional medicine. And it addresses some major healthcare challenges. It'll improve

healthcare outcomes, facilitate brain health, make healthcare more cost-effective, reduce the huge burden of chronic disease, promote healthy aging, which we're all interested in, and really lead the way for the U.S. to be, you know, transforming health and health innovation. He's co-founded 17 biotech companies, including Amgen, which you might have heard about. It's a big pharma company, Applied Biosystems, Rosetta, Aravel. He's won so many prizes that, you know, are given to like kind of the equivalent of the Nobel Prize, like the Lasker Prize, the Kyoto Prize, the National Medal of Science. And he is the chief strategy officer and professor at the Institute for Systems Biology, which he founded in Seattle, Washington.

Nathan Price, been a longtime friend. He's the chief scientific officer of Thorne Health Tech and the author of The Age of Scientific Wellness, which actually both Leroy and, or Lee Hood actually, and Nathan both co-wrote. He was previously the CEO of Longevity, an AI health intelligence company that merged with Thorne prior to the IPO. He's named one of the 10 emerging leaders in health and medicine by the National Academy of Medicine. Again, no small feat. In 2021, he was appointed to the board of life sciences and the National Academy of Sciences, engineering and medicine. And he spent a lot of his earlier career as a professor and associate director of the

Institute for System Biology, co-director with the biotech pilot near Lee Hood, who we just introduced. And he's also as affiliate faculty at the University of Washington in bioengineering and computer science. And he's co-authored more than 200 scientific peer-reviewed papers, given over 200 talks and keynotes, including at the Institute for Functional Medicine. And he's served as a chair of the NIH study section on modeling and analysis of biological systems, which is really important because how do we think about the complexity of human

biology? And he's also a fellow of the American Institute for Biological and Medical Engineering. So welcome, Lee and Nathan. Pleasure to be here. Thank you, Mark. Great to be here. Those intros are basically on behalf of the podcast, but it's worth it to let them know who you are. Yeah, I'm thinking about letting the NFL down. So, I mean, what everybody listening should know is that these two men are among the leading

thinkers in a revolution in healthcare right now that we've been working on for decades in functional medicine, but they bring the weight of tremendous scientific credibility to a new way of thinking about health and disease. It isn't based on just diagnosing and treating symptoms and diseases, but on a very important question, what is the science of wellness, right? And how do you create scientific wellness? In other words, what are the biomarkers? What are the metrics? How do we measure health? How do we not just look for disease? And it's a really revolutionary view. And I always say functional medicine isn't the science of treating disease. It's a science of creating health.

So we've seen a real radical shift um in our thinking and and i think most people think of wellness as fluffy as light as spas massages you know whatever but not not hardcore science and you know i think what's what's really important for people listening understand is that systems biology is is a is as big a change in our medical thinking about health and disease as quantum physics was to Newtonian physics. It's a huge paradigm shift. It's a paradigm shift that's equivalent to thinking the earth is flat to the earth is round. And it really hasn't caught up with clinical practice yet. All of medical organizations, medical education, our reimbursement system, the way we code, the way we get bill, is all based on this outdated model. And so Lee and Nathan have been reimagining what healthcare

could look like as we start to apply this new paradigm. So tell us, maybe you can start, Lee, how you guys came up with this idea of scientific wellness, how you began to think about biology differently from this reductionist view where we're all sort of just focusing on the bits and pieces and not the whole and how it all integrates as a network and how our body is a biological network or a network of networks. And to be healthy, we need to create balance in those networks. So can you talk about the origins of this concept of systems biology and scientific wellness? Let's hear from both of you on this. Yeah, I think the essential feature to understand is that humans are incredibly complex. They have complex systems that interact with one another.

They interact with one another at many different levels from an informational point of view and from a organizational point of view. And in thinking about this many, many years ago, it became obvious that there were a number of things that we had to do to deal with complexity. And the most important of it was really what's come to be known now as big data. What is essential in a human being to deciphering their complexity, whether it be a complexity associated with wellness or with disease, information about many different systems, being able to understand what the organism is, what the human is on the outside as well as the inside. And one major principle that we've really formulated is this idea of blood is a window into health and disease. Your blood bathes every organs. They secrete molecules into it. If you can analyze those molecules, you can, in a sense, begin to understand how all those different organs

are with regard to their health state and so forth. I think another thing that's become very important is when you make the measurement on many different blood analytes, proteins and metabolites and clinical chemistries and everything, you get an enormous amount of complex data. And the question is, how do we deal with that data? And that's where systems biology comes in. And the idea is exactly as you expressed it, Mark. The idea is that our body is a multitude of different biological networks that carry out the physiology of a normal individual. And in fact, when you become diseased, those networks also become diseased. So what we have to do with systems biology is take the big data information that we can now gather from your blood and so forth and to place it into those networks and to do

it so in a dynamical way so that over time we know how the networks are changing. And those networks and their change gives us an idea of the slope of your health. Are you transitioning into a disease? Are you heading toward wellness? So the integration then of big data, of systems biology, and I'd say the final initiative is the understanding of how AI is going to be able to deal with this complexity and translate it into meaningful information for physicians. For example, we have the hope in the future that with large language models and digital twins and knowledge graphs, these are all fundamental tools of AI, we'll be able to take the very complex information that comes from your genome and from your phenome and feed it into this system and have it identify your deficiencies.

And for each individual, give us an ordered list of the actionable possibilities that can move us to greater wellness or back from disease to a wellness state and so forth. So those are the fundamental principles. And you enunciated them very clearly when you articulated the introduction. Thank you. Nathan, what are your thoughts on this sort of revolution in scientific wellness?

And how did you kind of come up with this concept? Because it's kind of a beautiful way of expressing, you know, the hard science behind health, which is something we've not really looked at in medicine. Yeah, and that's kind of how we thought about it. Because, you know, Lee and I both come in from a hardcore science background into this. But you mentioned earlier, like, the way that people think about wellness, you know, you tend to think about yoga and you think about foodupuncture, right? Acupuncture, exactly, all these kind of things. And so there's this really interesting nexus between kind of the way we think about, you know, medicine or

healthcare in the West and how it's thought about in the East. And there's this like very interesting intersection about a philosophy of wellness, but taking some of the scientific rigor of the principles of what we have that has defined a lot of Western medicine. We get into this in the beginning of the book. And so, you know, that's where we came up with this, you know, the term for better or worse that we chose scientific wellness was kind of to indicate wellness, which is the orientation towards not disease, but health. But the scientific moniker was supposed to kind of differentiate or give a sense. That's what we're talking about. And so scientific wellness in that sense, then, is really just the same principles that we might think of in precision medicine. That's trying to take a very deep view into into how you leverage all these molecular data and tools.

But our feeling is that that is too narrow because the way that that's getting set up, it's still set up around this paradigm of wait till you have some horrible symptom, get diagnosed with a disease, and you get this drug. And we're trying to give those drugs more precisely. But scientific wellness says, no, that's not enough. We want to shift the whole orientation so that we're still being precise and deep, but do it early and focus on let's extend your health span as long as possible, reverse disease in its earliest transitions if it arises, and try to never get into those later states to the degree that that's possible. And then the effort around scientific wellness is really to just drive how do we have as deep of a scientific enterprise underneath the wellness

paradigm that we've developed under the disease paradigm. It's amazing. It reminds me of a patient I had years ago that came in and this blood sugar, I think it was 120 or something. And I said, has your doctor seen this? And have you gotten any advice from your doctor about what to do? And he says, well, yeah, my doctor said my blood sugar is going off, but wait till I get in the diabetic range and then he'll give me a medication. It's sort of the opposite of what we're talking about. It's like, well, if your blood sugar is 120, you're already screwed. If, you know, when you look at the data, anything over 85, which, you know, a hundred is considered now normal. It used to be 110. But if you're 85 to 100, you're still having an increasing risk in

a linear way for cardiovascular disease and other bad events. And, you know, when you think about what you're talking about as a doctor, you know, what I learned to do was take a medical history, what I could remember to ask, you know, do a physical exam, look for things that I could see crudely that were wrong, maybe get some imaging, a few blood tests, not that money, maybe 20, 30, 40 analytes in your basic chem screen, CBC, and then, you know, assume that I could kind of figure things out. And, you know, when things go really bad, you know, those things are off, right? When you're kind of in the hospital at the end stage of these processes, you get to see abnormalities, but most of the time you don't see much. And it's like, it's kind of a joke because there's billions and billions of chemical reactions every second. And what you are both talking about

is really a revolution where we're not just taking, you know, a few physical signs and symptoms, a few lab tests. We're talking about literally billions and billions of data points that are going on in your body from your genes to your microbiome, to your metabolome, to your transcriptome, to your proteome, all these things that we're looking at in the omic revolution and biometrics that we're now going to be able to put in through wearables, you know, and we're going to be doing, you know, analytes of things that we haven't been able to measure before. And so we're all of a sudden able to have enormous amounts of data, but there's no way a doctor can make sense of that because they would have one brain and it's kind of not AI, but it's pretty good eye, but it's not able

to sort of measure and track and interpret and analyze a list. And, you know, you've talked before about these dense dynamic data clouds. You've gave a talk at Cleveland Clinic for Grand Rounds today that was really great. And you talked about the future of this and shared what you've been learning through some of the work you've done. And so rather than just taking a simple view, you're taking this complex view and mapping out where are people in the continuum of health and wellness. So you've done a number of projects, a Pioneer 100 group. You're now trying to do a much bigger one with a million people. And you, you know, you've, you've created Aeroval, which was an attempt to kind of create a clinical model for this.

Can you talk about your learnings from the Pioneer 100, which is where you, you've tried to collect all this data, make sense of it for people and then, and then, you know, give them a plan that's as you, as you call it, P4P or P4, P4, which is personalized, it's preventive, it's predictive, and it's participatory, meaning the patient has to do some of the work. Well, I think the Pioneer 100, which occurred around 2014, was a study in which we put together essentially 108 of our friends, and we carried out a whole genome analysis. We did the blood analytes, and we used a Fitbit, and we analyzed the gut microbiome, and all of these data were integrated together. And it was done in the context of people who understood medicine.

So from these data, we identified 3,500 statistical associations and took the most interesting of those associations to the medical literature, and they led us to actionable possibilities, to something concrete the individual that had that particular perturbation could do either to improve their wellness and or let them avoid disease. And during the course of this program, we came up with hundreds of actionable possibilities, and it was obvious with a larger study we'd end up coming up with thousands of these kinds of things. What we did learn that was very important was that the fourth P, participatory, the need for the patient to take their own health was absolutely critical. And in this pilot study, we had coaches who actually could take these actionable possibilities, prioritize them, and discuss them with each patient, encouraging them

to move on and carry these things out. And we found that the coaching was enormously beneficial in one, the retainment of these people for the full year that we did it, or nine months that we did it. And two, in causing people to actually carry out these actions and so forth. And that was foundation for us moving to AirVille, a program that lasted for four years, did exactly the same thing with the same general approach, but generated an enormous amount of data that gave us deep insights into scientific wellness, into healthy aging, into our ability to detect transitions years before the actual disease showed up clinically with the hope that we'll be able to use prevention and or therapy to reverse it at that early and very simple stage. And that's where we stand today.

We have from these two demonstrations, one of 108 and one of about 5,000, an enormously compelling picture of what we can do for an individual if we analyze the genome and the phenome. And I just add that the phenome really turns out to be three interesting things. It's one, your personal behavior and the choices you make. And two, it's your environment and how they impinge upon yourself. And I think a really apt analogy for doing this is a composer writes a tune, right? And it's the player that takes the tune and gives it life and puts passion in it and changes it. And different players change it in different ways. It's exactly the same with the genome and the phenome. The genome is your basic construction kit for how a human develops,

but the phenome is the artist and that's your behavior and your environment that play on this genome. And the three of those things together give you your phenotype at any given point in time. And essentially, these measurements are attempting to determine the influence your environment and your behavior have had in making what you are, and more important, in being able to take you to where we want to go to superb wellness. And I'll just say one more thing. Most people who are well don't realize they've probably exerted only 20 or 30 percent of their potential for wellness. They can do much, much more in many different ways. And it comes back to how do we persuade patients to actively participate in this process and commit themselves to a future where your health span will equal your lifespan.

And we think we can move it out into the 90s or 100s, where we can give you an extra 20 or 30 years of healthy life. And of course, the fascinating question is, what are you going to do with it? Exactly. Well, we know what you're doing with it, Ellie. You're 85 and going strong and just building new companies and businesses and writing new books. It's very inspiring. Hey, everyone. Dr. Mark here. Scientists have long known that electrolytes are important in the body. So many daily ailments like headaches, cramps, and fatigue can be caused by electrolyte imbalances. Sports drink companies

know this and they've responded by peddling electrolyte drinks that are full of sugar, food coloring, and other junk that should not be eaten or drinking. But this is what makes LMNT or Element different. Their tasty electrolyte drink mix has everything you need and nothing you don't. It contains a science-backed ratio of sodium, potassium, and magnesium to keep your electrolytes balanced. And there's no sugar, coloring, artificial ingredients, gluten, or fillers. Element is used by everyone from NBA players and Navy SEALs to busy moms and exercise enthusiasts, including me. It's also perfectly suited to anyone following a keto, low-carb, or paleo diet. Right now, Element is offering my listeners a free sample pack with any purchase.

That's eight single serving packs free with any Element order. It's a great way to try all eight flavors or share Element with a friend. Get yours at drinklmnt.com forward slash Hyman. It's a great way to try all eight flavors or share Element with a friend. Get yours at drinklmnt.com forward slash hyman. That's drinklmnt.com forward slash hyman and get it today. Getting quality sleep is incredibly important to me. Sleep is really one of the pillars of good health. So you can imagine my frustration when I used to lie down at night but couldn't fall asleep because I was just too hot. But those sleepless nights are behind me now thanks to Cozy Earth. The bed sheets are made from temperature-regulating fabric that keeps you comfortable all night long. I naturally run hot, but with Cozy Earth's breathable sheets, I cool off and get right to sleep and stay asleep much faster.

Cozy Earth offers a variety of luxury pillows, sheets, blankets, and more. And their durable weave fabric won't pill for 10 years, guaranteed. Plus, they pride themselves on the ethical production of all their products, so you can feel good about your purchase knowing you're supporting a truly responsible company. And right now, Cozy Earth is providing an exclusive offer for my listeners. You can get 40% off site-wide when you use the code DrHyman. Just go to CozyEarth.com and use the code DrHyman. That's D-R-H-Y-M-A-N. And now let's get back to this week's episode of The Doctor's Pharmacy. Nathan, I think when you looked at the Pioneer 100 study, it was very early on in this sort of space.

And it was using lots of data information. It was mostly filtered through the human mind to come up with a set of sort of recommendations and guidelines. But now we're talking about, you know, something that's even beyond that. So how do you see this progressing where we use these big data analytics and AI machine learning behind the scenes to actually make sense of this enormous amount of data? And how, you know, kind of what's the next iteration of the, you know, the phenome study or the Pioneer 100? Because, you know, as a physician who's been doing this for so long, I see all the patterns in the data that I recognize.

And I can be very good at it because I've had, you know, tens of thousands of hours of experience, seen millions and millions of data points. And I'm sort of, you know, 30 years in. But it's kind of locked in my head. I can't really share it with anybody easily. And I know I'm missing probably 90% or 99% of what actually really is true also, even though I probably see more than most. So, you know, I know that there's so much in there and I've seen patterns in when I do these, you know, really extensive phenotyping of people through all the diagnostic testing. And I can see these patterns that are emerging that I've never seen described. For example, I see someone with heavy metal toxicity and I can guess that they have it because I see

mitochondrial dysfunction on organic acids. I see, you know, for example, methylation problems, low glutathione, low zinc, low amino acids, oxidative stress. And it gives me a clue that there's something damaging the, you know, these various pathways and it's likely heavy metals. So I can kind of infer that, but I've never seen that written up in a paper. And I'm sure that's just like the iceberg. So how do we take the sort of insights that now we're gleaning from this phenotype

and these dense dynamic data clouds of all these biomarkers and actually make sense of it and create a predictive model for people to create a personalized program that optimizes their health and not just as treating disease. It's a great question, Mark. So at the very beginning, you're exactly right. There was, you know, just pinpricks of information relative to now that you could really deal with. But over the last several years, you know, and maybe we'll come back to this a little bit.

We learned a tremendous amount about the data, published a ton of papers, insights, things we can talk about. We can come back to that in a minute. But I want to address your forward question of what do we do with all these different kinds of data? And this is where, you know, as we talk about in the age of scientific wellness, the reason we think this is so ripe for pushing now is because of these two big features that are happening. There's this massive growth in the amount that you can measure. But at the same time, there's massive increase in how you can interpret those data and deliver it back to people. So, for example, one of the things that we've done recently is to get into digital twins. And so a digital twin is a representation of your body's physiology.

And we've done this first for brain health. And so what we can actually do in this case is, and we're going to release a test on this, you this, a product based on this next year. But basically what you can do is you can monitor for a number of these blood measures, your genetics, cognitive assessments, and so forth. And you can then run a simulation based on your particular biology. And it's based around understanding from a physiologic and molecular level what's driving brain health. And you can actually forecast the likely amount of time that you have with a healthy brain given your current state. More importantly, you can go to personalized recommendations for different kinds of things that people can do, some of which are exercise to keep your oxygenation in your brain high. You can get into things like phosphatidylcholine. It turns out that

that becomes rate limiting under low oxygen conditions. Latest people are developing dementia, hugely important. Vitamin D, very simple one. We could talk a lot more about that one. Turns out to be very important. There's many, many of these. But the point is that what you can actually do with the digital twins is you can get a representation of a person's individual risk profile and then tailor the precise recommendations. These recommendations are very different person to person. Once you get to four recommendations, only 1% of people actually benefit from what's the best thing, the best for in the population. We just did those simulations. It's very interesting when you do that. And so you get this intense personalization and you can get into the physiology and you can start to make sense of this because you have to take the

complexity of all these measures. You can't place that on a person. You have to put that into the algorithms and deliver back simple, actionable information. And then the other side of the coin, which I'll just mention here briefly, is the chat GPT and all these things that have shocked the world over the last year. The ability now to deliver personalized insights that give you a lot of context and that you can have a back and forth with and you can get access to a dialogue even with what your digital twin is saying or what you're learning about your body. The capability for us to develop personalization on that front is just radically better than any of us thought it was going to be a couple of years ago. And so those things together are really pushing us into this new world of where we're going to be able to harness so much more of this complexity than we could have even thought

about before. I mean, I mean, this chat GBT there, like now, for example, I put in all my symptoms, I enter in all my lab data and I hit, you know, tell me what's wrong and what to do about it. Would it give me anything useful at this point or is it still far off? So I've played with this a lot. Maybe I'll jump in on that. But it's pretty much what I do in my free time. I don't do anything else. You're on a contract.

You put it on your symptoms. My stomach hurts. I got a headache. Yeah. So it's partially there if you use like earlier versions like the gpt 3.5 for example you'll get lots of hallucinations it's sometimes useful sometimes not gpt4 is pretty good except anyway there's this weird trend it's not as good as it used to be and there's a lot of chatter around that on it it doesn't let you go as deep

as it used to i don't know if it's legal or they're not really probably put guardrails on it. It doesn't let you go as deep as it used to. I don't know if it's legal or they're not really talking about it. They put guardrails on it. Yeah. They put guardrails and various kinds on it and so forth. But as long as your, if your question is reasonably well dealt with in available text that it's generating from, it can be quite good. And I've had, and I've used it, you know, not just on medical issues, but, you know, explain statistical analysis of this kind of data or something like that and it's it actually gives back really reasonable kinds of information now it's not fully to where it wants to oh and i did see a survey maybe you saw this as well they polled doctors and apparently 60 of doctors are using gpt today right now in the background on things that they do so i said if you saw that survey

but it was actually not totally ready for prime time but just to say that yeah go ahead well no i was i was at this big medical conference in lake nona and they had this guy from microsoft with i think prometheus which was kind of a new version of like chat gbt that was like you know for doctors and they had a case report that they were sharing and they were entering in this case study and it got it totally wrong. And I guessed it immediately. Like I wouldn't guess it. I just knew what it was because I listened to the story. But, you know, it was basically a patient who had, you know, frequent urination, fever, chills um you know had had i think maybe i had had a history of rheumatoid of strep long ago or something like that or had a murmur maybe had a murmur as a sort of part of the

exam and it was just a murmur and i'm like oh this guy has endocarditis this guy has bacterial endocarditis and the the chat the prometheus thing oh, he's got a, you know, kidney infection. And I'm like, no, he's not having a kidney infection. And it was wrong. And it was like in front of like 500 people. So, you know, I kind of wonder, but I do think that, you know, the things are changing. So as you've gotten into sort of looking at these sort of enormous amounts of data through the phenotyping of people, you know, when that goes into these machine learning AI models, like, you know, where is the next step in this in medicine? Are we all kind of moving towards this? Are doctors going to become in some ways obsolete? Or are they just going to be helping to kind of, you know,

implement some of the decision support that these tools give. Because personally, I would love to be able to put all the data for my patients in and instead of spending hours and hours muddling over and thinking about it, trying to remember every study I ever read and what to do and my medical school training, like this is going to give me kind of a roadmap to start with and then implement it. How far are we away from that? Well, I'll make a couple of comments. I think a really important thing about these large language models, which is what GPT and the other things we've talked about are, is that they have to be educated properly. So if you take a large language model and you

expose it to the internet, you expose it to the conspiracy theories and the lying and all of those other things, you have an enormous susceptibility in that device. And my argument is for health, we ought to have a GPT that has only been educated with biomedical data. And we're actually collaborating with a group that has one of those. And what our hope is, is we'll, and part of the education has been to put PubMed into the device, which gives you an enormous amount of data. Now, some is right and some is wrong. You'll still have to make judgments. But what we plan to do is we have access, for example, to Google's knowledge graph. And this is a graph that connected roughly 50 different features from the literature so it's assembled from the pub med literature all of the relationships

between genes and proteins and diseases and drugs and on and on and on pub med for those listening is just the entire body of uh peer-reviewed published medical biological information yeah it's a lot it's millions of millions of studies. Well, this knowledge graph has 50 million nodes and 850 million edges, which means an enormous number of relationships. So we're going to put this knowledge graph in this medically educated GTP. And we're going to put in, we're building now a knowledge graph for the kidney. We'd certainly like to put in the knowledge graph for brain health. All of the knowledge graphs and digital twins that we have should go into educating this thing. And then my hope is the following. We'll be able to take the data, genome and phenome from each individual, enormously more complicated than what we did in AeroVale, maybe 10 times as much data as we had initially, and put it in there and ask it to

generate from tens of thousands of actionable possibilities the ordered priority of actionable possibilities that you as an individual can use to optimize your health or avoid disease or whatever. And what the AI will actually do is send this information to a doctor, and there'll be two things the information will have to do. One, clearly explain the actionable possibility and what the doctor and the patient will be expected to do. But two, it's to give the physician the medical evidence for this actionable possibility to assure him or her it's bona fide. And the dramatic result of this is you will be able to take a family practitioner and make him a domain expert in virtually every field of medicine.

It gives you this global reach that you were talking about and the capacity to handle virtually anything. And that democratizes medicine in an incredible way. And I'll argue, well, never, ever get rid of the physician because they're in the end still an integrative factor that we're a long ways from being able to replicate and so forth. But he will have the tools to become a world expert in every field of medicine. Really quite a remarkable promise for the future. And what it promises for patients, that is the optimization of this wellness and prevention Nathan and I have talked about, I think is really dramatic. So how far away from this are we so i think we'll begin to see the effects of this within the next year or so as as these things get i mean we won't have them in the full glory

for you know who knows maybe 10 years is way too long to say, because look what, I mean, that 60% of the doctors would use a tool like this. I would have said there's no way in the world that that conservative group of people would ever go into AI like this. And yet. So they're putting their patient's history in there and saying, hey, what's wrong? Is that what they're doing? Yeah. That's amazing. I know.

We should probably not over, over us it means they use it to some degree because you know the thing about like replacing doctors the line that i really like i think it's eric topol's which is um uh you know ai won't replace doctors but doctors who use ai will replace doctors who don't and i think that is a really good way to put it because it it is a tool. And I think it's like today, it's already a super useful tool. Like if you're trying to remember something or if you want to delve into the literature, it's so you can and especially with these particular GPTs that are based around PubMed

and things like that, they're already an assist, right? So it's just already a function of how strongly that assist can be made. And I think the doctor is still going to be the quarterback, but your ability to block and tackle and just solve lots of issues with the AIs is incredible. And it's not just the LLMs. I mean, one of the really biggest uses that's straightforward right off the bat is getting rid of as many medical errors as possible, right? Because a doctor who's tired, it's easy to, you got a long, complicated name, and there's two of them that look almost exactly the same. It's pretty easy to accidentally check

the wrong box. But if the AI actually knows, well, you said your patient has diabetes, and that's a drug. Did you actually mean this drug for multiple sclerosis? And that's already happening today. Hospital systems have saved millions of lives already by just implementing some of those really simple things, the kind of mistake that's easy to make as a human and a computer won't make. Now, vice versa, computers will make the kind of, and AIs will make errors that a human never would because they don't understand causality. They don't understand the context. They don't, you know, there's all kinds of stuff like the case study that you got right that the AI didn't. Like there's things that it doesn't know. So a hybrid or what we call Centaur AI in the book, a hybrid approach really

makes a lot of sense. So you can cover your bases because those two kinds of intelligence, human intelligence and AI actually operate quite differently. And the kind of errors you make are very different. So combining them is powerful. What you're talking about is definitely going to help transform the expertise of physicians and allow them to practice medicine that's more up to date, that reflects the scientific literature, that is based on understanding a wide network of biological factors that they haven't been able to consider before. And that's going to be fantastic. But the truth is that wellness, health, does not happen in a doctor's office, right? And so 80 to 90% of the things that determine your health actually don't require a doctor and are things that you can learn about yourself and fix without a doctor's help.

And so in a way, this is also going to help, I think, disintermediate people from the healthcare system and from doctors because we don't really have a healthcare system. We have a sick care system. And so what you're talking about is actually a new kind of healthcare system where people are going to be empowered with their own health data guided by these big, dense data clouds of their own biological information from all their, their omics to their blood panels, the things we don't even measure now that we're going to measure to their wearables and biometrics. I mean, I have a Garmin watch. I mean, I know everything about myself, my pulse ox, my heart rate ability, how much I slept, how much deep sleep, how much light sleep, how much training, how much time I need to recover. I mean, it's

pretty impressive. And, and all that is just sitting out there ready to be kind of harvested and used. And so individuals, I think, are in this moment where they can become more empowered to be the actors in determining their own degree of wellness and health and then know when to go to the doctor. Like, oh, well, gee, you know, your creatinine is like five. You better get your ass over to the nephrologist tomorrow. So that's going to for sure be still there. But a lot of the stuff that actually requires a physician isn't really needed. It's really diet, lifestyle, behavioral changes, supplements, and other practices that they have access to. So how do you see this kind of being a tool that the individuals and patients and

consumers can use in a way that is really going to disrupt healthcare? You know, Mark, I think you made a really excellent point, and that is the importance of education for the consumer, if you will. And we're doing a number of things in that regard. For example, this past year, an educational team at the Institute for Systems Biology that I initiated 20 years ago to deal with K-12 science education problems has put together a four-module, one-year course based on two chapters. Several of us wrote in the systems biology and systems medicine book, one on systems medicine, one on P4 healthcare. And the essence of this module is to give them the picture that is portrayed in our book of what health care is

going to be in the future and to clearly explain the responsibilities they'll have for their own education. And it makes very strongly the point the core of your health is going to be diet, exercise, sleep, stress, et cetera. And these are things you can do about it. And these are tools and devices you can use to measure it. And oh, by the way, there is this more sophisticated medicine of assaying your blood and your gut microbiome that can tell us. And by the time students will get done with that year course, I'll guarantee they'll know more about what I think, what we think the future of medicine is than 95% of the physicians out there. I mean, this revolution in transforming healthcare from

a disease orientation to an orientation of wellness and prevention, I can't stress how important that's going to be in doing two things. One, improving the quality of health for every single individual that practices even partially. And two, it's going to lead to enormous cost savings in the health care system by avoiding what costs 86 percent of our health care dollars today, namely chronic diseases. And Mark, I'd love to kind of weigh in on that question as well that, you know, that you asked, because I think it's such an important thing because you're exactly right, because the more and more of what we can call, you know, put under healthcare, especially if we start talking about wellness care, right, we like to say scientific wellness should be the front door of the healthcare system. Most of that effort should really be on, you know, this maintenance of health, and then you get referred back into the health care system. Most of that effort should really be on this maintenance

of health, and then you get referred back into the disease care system when, hopefully early enough, that really make a difference, but with some advanced warning. But the ability for us to deliver this really efficiently and low cost, I totally agree with you, is pushing this more and more to the home remotely, making it easier. So some of the things that we've done, you know, for example, you know, we've spent the last few years developing a essentially painless, you know, at-home blood collection device. It used to be called the OneDraw, now called the NanoDrop. You know, but that's like one feature of it. You're not going to go to jail like Elizabeth Holmes with this, are you are you not at all yes exactly that was my objection to the name change honestly

sounds like very familiar the nanotainer yeah i read the book i watched the documentary like 12 times. I watched the dramatization where they did it. It's a fascinating story in many ways. But you can move to home, right? Microbiome testing, right? You can do that in your home. You can get access to this with AIs.

We developed something called the microbiome wipe to make that as easy as possible for people and so forth. But the whole idea is that we should be able to deliver health information to people in ways that are much more efficient, much more user-friendly, not nearly as expensive, and that people can have a real control over their health and be informed by really deep data. You know, I think that's really the key. Oh, and on the, you know, coming back to, you know, some of these, you know, like small measurements, you know, you brought up Elizabeth Holmes and so forth. One of the things that's important is that a lot of people have failed in trying to take traditional measures and

miniaturizing them, you know, at, you know, at least doing a lot of them at the same time. But the kind of things that we're talking about in terms of omics, like a metabolome, where you can make thousands of measures, which we're going to do on this device, a protein proteome that you can do right again, you know, thousands of measurements. Those are only ever done on small amounts of blood. So, you know, if we, and I are running something on that in our lab or any of the top labs in the world, you only ever run those things on time. If you gave them a huge vat of blood, all they would do is take a tiny amount out of it and run it on the mass spec. There's no such thing as running this through it. So you're talking about technologies that are

miniaturized already. That's the way that they work. And so there isn't actually a technological breakthrough of any kind that's needed to use this small amount of blood to get those many measurements. The breakthrough is you have to understand how to read the information. But in the modern world, I'd much rather have an information challenge than a technology challenge, because the information challenge can actually be overcome you know by getting access to samples the ai is the long term and i'll give one interesting example so uh think about what happened in genomics so in the genome initially one of the traits that we couldn't predict from the genome was height now we all know height is heritable right if you have tall parents you have tall kids if you have tall kids. If you have short, you know, if you're short, like, it depends on what you're eating. It depends part of what you're eating. There's some other factors, but by and large, it's fairly heritable, right? to now and height is now the number one trait that we can predict with the highest accuracy you can capture over 60 percent of the variants in height by a genome prediction but that genome prediction requires over 180 000 genetic variants so it's it's distributed across this long tail

so one of the things that we don't know yet is how much... You mean SNPs? You mean, are you talking about SNPs? SNPs, yeah. It's like one, it's single and nucleotide polymorphism, which in English means you substitute out one nucleotide in that gene sequence that changes the function of the gene. So you need 180,000 of these slight little spelling variations in order to actually predict what's going on. That's impressive. Butredict high. But you could see that there was a really interesting paper. And one of the people they included was Sean Bradley. If you remember him, he was a basketball player. He was 7'6", huge outlier. And you look at this and you get a distribution. And he's a massive outlier. Like if you looked at his genome at birth, you could have predicted that he was

going to be crazy tall. And so you can do this in the NBA, you can do it in all these different groups. And so coming back to the blood, the thing that we don't know yet is it might be possible once we're able to make, say, tens of thousands of measurements out of the blood instead of the handful that we do in medicine, we might find that there's a lot of information in that long tail. It's a little harder because it's not as digital as the genome, but it might be there. And so it's an open question, but these are some of the things that are really fascinating as we go forward because there might be a ton of signal that will let us optimize health in many ways and look for early

warning signs or clear them and so forth. And there is just an incredible amount of data you can pull out of blood that we haven't harnessed yet. Yeah, and I think it's really important. I think people, you know, what were we going to say, Lee? I was going to say one really nice example of polygenic scores and how they can be, they can apply to improving people's health is we were able to look at the polygenic score, that is a multiplicity of SNPs that explain a fraction of why you have high LDL, which is a proxy for heart disease and so forth. And we were able to show that people in the upper fraction of those things, could only bring down their LDL cholesterol with statins and

other chemistry, whereas people in the lower 40% or so beautifully brought down high LDL with just exercise or diet. So I would argue for all of the 150 or so polygenic traits we have, many toward disease, we're going to want to treat low-risk people differently from high-risk people. And it's going to be important for everybody to know those risks. Well, that's the personalization aspect. And everyone's doctors to know those risks. Yeah. Not like one size fits all right now.

You've got a high LDL, you get a statin, boom. It's not very nuanced. It's very rudimentary. You know, one of the things that actually concerns me is, you know, how these AI machine learning models will be trained. Because, you know, when I was at Cleveland Clinic, I met this guy who developed Watson, which is the IBM AI supercomputer. And, you know, the big thing was Watson went to medical

school. I read all the medical textbooks about all the medical literature. And in my mind, I'm like, I said, I went up and said to this, to the guy, I said, listen, you know, this is great, but you're going to be just doing the same things better. It's like, you know, you're going to be basically having a better mousetrap for the same kind of medicine, which is disease-based, organ-based, you know, ICD-10 disease classification system diseases, which isn't actually a true reflection of how biology is organized, right? We're an ecosystem, we're a network of biological networks. It's not the typical diseases that we think of that we should be looking at. It's what's underneath the mechanisms and the root causes and the things that go wrong, like the hallmarks of

aging are much more approximate than understanding of what's really going on in the body. And so I'm like, well, this is great, but it's going to help, you know, diagnose conventional problems better and have a better application of conventional approaches, which to me is like, you know, you know, kind of just doing kind of a better approach to sort of, I don't know, the earth is flat kind of thing. It's not actually changing. So I wonder, my question is, how do we avoid that? And how do we train these models and AI in the systems biology, systems medicine,

functional medicine approach to actually know what to do with the data? Because I see the same data as traditional doctors, but I see very different things when I look at them. I think the really important point is with phenomics, we're going to give billions of features of the individual to the AI, and it's going to sort through a dimensionality of information that's staggering. And reading textbooks is one thing. That's metadata that's descriptions at very high levels. Your data is the core of what you are. And AI is going to be able to extract that essence and translate it into the actionable possibilities that'll actually benefit you enormously. And the other point is you'll have to train the AI properly.

And it isn't just reading medical textbooks or not. It's using knowledge graphs. It's using digital twins. It's using all of these kinds of things. Yeah. I mean, let me give you an example. Maybe we can play off this. Because, you know, for example, let's say a patient comes in with psoriatic arthritis.

And from a traditional point of view, in the diagnosis, they have these kinds of lesions. You can diagnose it with AI interpretation of skin pictures based on their medical history, joint exams, et cetera, et cetera, certain blood tests. And it'll say, okay, this is what you've got. Psoriatic arthritis is an autoimmune disease. And here's the catalog of drugs you get to choose from and the therapies, steroids, creams, you know, biologics, whatever. And you're going to get that recommendation.

Now, when I see that patient i think of different things like what is the cause of their inflammation and and in psoriatic arthritis after decades of doing this i've learned that it's a few things that aren't typically considered one it could be uh in environmental toxins like heavy metals and i've seen completely clear up with just getting rid of heavy metals in the body i've've seen it be from, for example, gluten sensitivity, which is maybe diagnosed or undiagnosed celiac or non-celiac gluten sensitivity, and removing that helps. I've seen it be the result of an overgrowth of bad bacteria or fungus in the gut, SIBO or SIFO, and severe leaky gut and a disruption in that barrier that drives these symptoms. And my approach would be very, very different depending on which of those problems a person had. And so what I always say

is just because you know the name of the disease doesn't mean you know what's wrong with you, right? And so how is this new framework going to be, you know, drawing on that kind of knowledge? And I guess, you know, some of this knowledge around toxins or leaky gut or gluten are there in the literature, but they're things that are completely ignored by traditional doctors in healthcare because they don't fit in the paradigm. It's like, it's an outlier. So it's like, we don't want to do that. And so it's like, let's just stick with our lane. And so what I'm wondering is how do we kind of use this new phenotyping to kind of give us the right information and the right plan for the person, instead of saying, oh, you have psoriatic arthritis, take this drug? You know, the really key point is all of those things will be reflected in the

phenome, and you'll be able to read those things. And even in a simple way with AeroVale, we had people that had extremely high mercury levels. And we were wondering where that came from. And the most common cause turned out to be people who ate a lot of tuna sushi. And those are simple kinds of correlations that the observation in the blood says you've got high mercury. And there'll be a whole series of conclusions you can draw. And so, too, having having parasites, having having all sorts of different environmental exposures or your own self-choices. Those will all be reflected in your phenome, and those will be read by an instrument that will, you know,

in time become increasingly sophisticated. I'm not saying they'll start out that way, but they'll take in more and more data as these things are learned. So you're saying basically the AI machine learning itself will sort out what's true and will help to sort of distinguish an earth is flat world from an earth is round world. And even though... It'll give you the major symptoms, diagnoses, and it'll make hypotheses, but someone like you, that's why we need the physician as a part of the system. And the physician himself will be training AI as you say, no, wait a minute, here are three other

explanations I've come across. Yeah, but those three other explanations are not things that traditional medicine now even considers. They're things that functional medicine, systems medicine folks are doing. No, but functional medicine can feed into AI just as certain as traditional medicine. Interesting. What do you think, Nathan? I know these are hard questions, but you guys are smart, so I'm asking you the hard questions. I think it's a really good question. So a lot of it has to do with how you set these things up. So the AIs, there's many, many ways you can set up A you know, you can set up AIs, but there, but the, but as long as it's really focused on, like you were saying, like diagnosis, you know, here's the steps and these are the buckets and we're just trying to optimize kind of this information we have down to these buckets. You're exactly right. It's not going to know more than that. It's just going to do that.

So partly, you know, what I think is really important is that we go down a layer to where we're really trying to understand the biology behind it. I think this is where you're where you're getting. Yeah. Yeah. And also lifestyle. And so some of the things that we really want to say, and this is partly what we get into in the age of scientific wellness, because like our understanding of genetics, genetics is all based around disease. So we understand all kinds of things about the genetics so forth, is we should have modules that are looking at things related to your health, like systemic inflation, like how much information is the passaging between or molecules are getting from your gut into your blood, right? And you can look at that. How much of an integrity do you have in your blood-brain barrier? So you're basically going down, and now you're trying to develop these modules that are related to different aspects of the function of the health of all these different biological systems. And so you're not just trying

to learn, okay, what's my diagnosis? You're actually looking at the function towards homeostasis of multiple different elements at the same time. And this can be quite surprising and insightful. You know, when we did this, you know, I mentioned we built these models for brain health, for example, and it was really about that, like trying to understand how does the brain maintain homeostasis. And so you're using a certain form of AI to do that. And most of those papers and the things that we put in there and the data that we hold was not data about Alzheimer's disease. It was data about health, was data about how does the brain stay alive? What are the things that it has to satisfy? How much energy does it have to make? How does it take out the trash? How does it do, you know, and get very much more technical if we wanted to. But, you know, there's all kinds of things that are that are in there. And so and it can lead to surprising outcomes. Like one, you know, one thing that crystallized that was pretty interesting is, you know, that as your neurons tend to die and a big trigger for that is low oxygen. And then ApoE4, it turns out that

when you put these things together, you want to keep cholesterol levels in these supporting cells, astrocytes, really low. And ApoE4, which gives you high risk for Alzheimer's, will transport that cholesterol out of astrocytes, but it's slow, so that concentration stays high. ApoE2 will do it quickly, so it stays low. Those two facts together will predict for you the age of onset of all the different genotypes and when they get Alzheimer's. So then a surprising thing happens is as those neurons die, you have to secrete a molecule to recruit additional synapses in order to keep your brain functioning. And what's the molecule that the body uses? Amyloid beta. And so beta amyloid then, rather than being thought of as the cause of Alzheimer's, where we've spent,

I got a quote from a guy the other day, I have to go verify it, that we've spent over a trillion dollars on. He was a pretty good pharma source, but I haven't verified it. But I've been using $300 billion as my super conservative estimate, but somewhere in that range. So with that amount of money, 450 failed clinical trials, we have a couple that kind of help a little bit right now. But the point is that by mistaking cause and consequence, by not understanding homeostasis, not breaking, you know, understanding, you know, I think the, you know, the essence of that disease and putting it into a, you know, a structure that's set up to, you know, operate on, on, you know, this one drug paradigm like, like it does. And it does that, that, that well, but it's, you know, it's aimed at a certain thing that causes a massive problem. So, so that was an area where we went into an AI and you start piecing all these different things

together. It explains why statins look like they're good for the prevention of Alzheimer's in observational studies, but bad for Alzheimer's when you look at a RCT with MCI, we can get into details on that, but it's, you know, that gets, but you can sort these kinds of things out. So anyway, all that to say that we could go through examples, but as you start moving from, okay, I'm just doing a diagnosis to, I'm going to break down all the different biological modules and try to understand them in depth. And then, and then arm, depending on the, you know, which situation you're in, either the person in their home, if we're talking about wellness, or the physician in the hospital system, if we're talking about disease. But you can inform that by this basic biology informed by this really deep phenotyping.

So it can be incredibly, incredibly powerful. And we could go, anyway, on and on about how you set up these different kinds of AIs because it gets really rich, actually. But I think your early point, Mark, was really an important one. You have to take these data and put them into a systems biology context that gives you causality. That's the really important point. And that's, as Nathan said really nicely, what's going to differentiate out what these large language models can do from, you know, what IBM did, where it had the wrong set of data. And it was, I think the other major mistake that IBM made is it was all done by engineers who thought they knew what doctors needed and they didn't, frankly. I think the difference between cause and consequence is really critical. You know, when we say functional medicine is the medicine of why, not what, and it's based on mechanisms and causes, not symptoms and location,

which is what traditional medicine is. And this is the revolution you're talking about. And I think there's an importance to understand what are the root causes of disease, but also what are the causes of health and what are the features of health? And I think the hallmarks of aging, which is a sort of a new heuristic to understand what goes wrong as we age that are underlying all diseases, the things that actually are the root cause of the dysfunctions that lead to symptomatic disease, things like nutritional sensing problems, mitochondrial issues, damaged proteins, stem cell exhaustion, zombie cell formation, the senescent cells, the shortened bar telomere, the increase in inflammation, the microbiome changes, the altered cellular communication,

inflammation, all these things are things that are described in functional medicine as root causes, that if we treat those, the diseases get better. And the argument is we treat diseases, we may extend life by five to seven years. If we treat causes, we might get 30 or 40 years. But there's also an interesting paper that I'm not sure if you both saw in Cell in 2021 that talked about the hallmarks of health. And they sort of break it down into a similar framework, which is the first thing we have to do is be able to maintain homeostasis. We have to be able to respond to stress. We have to actually make sure things stay in their right location and don't have a leaky gut or a leaky brain. And their hallmarks of health are the homeostatic resilience, hormetic regulation, repair and regeneration, which are our response to stress,

the maintenance of homeostasis, which is how do we recycle and turn over parts that we need? How do we integrate different circuitries of communication? How do we have a balance in a rhythmic oscillation circadian rhythms? And how do we compartmentalize things spatially with making sure our intestinal barrier is right and our brain barrier is right and communication systems are right? And how do we contain things that are bad things like allergens or toxins or microbes from affecting us? So this hallmarks of health framework is really interesting. And I think it's a very different way of looking at and modeling what's going on to actually define what is scientific wellness? What is the measure of wellness? Because like, oh, I know how to diagnose diabetes. I get your

blood sugar, and if it's over 126, you're diabetic. But gee, what do I measure to determine if you have a high level of scientific wellness? What are the things that you're looking at that are the most important things to determine that? Yeah, I love that. So we've referred to these typically as metrics. Are you familiar with this paper? Are you familiar with this paper? Yeah, it's a terrific paper. The hallmarks of health. It's interesting. And it's exactly along the lines of what we're talking about. And this is why we talked about needing this enterprise of scientific wellness to establish markers and models and the deep science behind health so that you don't go in and you just get a test for disease or not. Because this is exactly what I think the,

you know, the health checkup of the future, whether it's at home or in an office, you know, should look like, which is how good is your body at dealing with oxidative stress? You know, are you able to, you know, are you able to, you know, what's your glucose control actually look like? That one's easy now because we have CGMs and so forth. You know, how robust is, yeah, exactly the integrity of your intestinal lining? Is your gut microbiome healthy, et cetera, et cetera. And so defining what those are is, I think, in many ways, the central effort of scientific wellness, because those are the kind of things that I agree with your other point, which is if you can optimize those as you go along. pathways, you're just much, much more likely to gain a lot. Because once you're down the disease pathway in a long way, like coming back to Alzheimer's just as an example, once you've lost a bunch of your neurons have died and billions of synapses are gone, there's no notion that you can

have a small molecule drug that's going to regrow those back. There's no chance of that. But prevention, right, thinking about, okay, what do I have to do so that my brain cells don't die in the first place is a much more doable cause. And we wrote this piece on Alzheimer's prevention for the LA Times a few weeks ago that goes into some of that. But basically, those two problems, like the regrowth of your brain after it dies and the prevention of it from dying, are not in the same universe in terms of complexity and in terms of your likelihood of being successful. And so you've got to think about, you know, how do we stay healthy? Stay away from those boundaries where you're going to cross some irreversible threshold and stay as healthy as possible. And things like those metrics for health,

that's a bridge to get there. You know, I'll make a quick point on metrics for health, that's a bridge to get there. You know, I'll make a quick point on metrics for health, and that is in the AirVale program where we had people ranging in age from 91 to up from 21 to 97. We were able to determine parameters from looking at blood analytes that gave us an algorithm for biological age. That's the age your body says you are as opposed to your chronologic age. The further your biologic age is below your chron for men, it was 0.8 years. a metric that allows you to assess aging. Here is a metric that in a sense allows you to assess wellness. And it's the integration of a whole series of measurements in the blood that culminate in essentially one. And we're going to be looking in the million-person project for tens, if not twenties, of these summation products that can look at integrated sets of networks and their behaviors. And of course,

for aging, it's an enormously integrated set of networks you're assessing. But you can get single measurements that give you very, very deep insights. And these are the things that are going to be the gauges for assessing wellness in as many different dimensionalities. Yeah. I mean, and the quantitative sophistication is going to get more and more. Right now, for example, Aravel, I'm sure you weren't using DNA methylation, using other intermediate biomarkers that you sort of aggregate and come up with a biological age estimate, right? And now we'll be able to use other biomarkers like DNA methylation or other measurements

like telomere length or the age of our immune system and actually have a very much more robust picture than even what's available then. So this is accelerating so fast, it's exponential. But methylation will never give you suggestions about how to improve your education, your aging, whereas the metabolic analyses from the blood do give you insights into things you can do to improve your aging. So these different things give you different capacities, okay? I mean, that's really why I created and co-founded Function Health, which is a testing platform to get your biomarkers interpreted through AI, through the lens of functional medicine to help you personalize and see what's going on. And at this sort of rate of dysfunction in your body

were things that we weren't looking at very often. So it's very powerful. And at this sort of rate of dysfunction in your body were things that we weren't looking at very often. So it's very powerful. Now, I know both of you are younger than your biological age. Nathan, you're in your 40s. You're about 10 years younger. Lee, you're 85 and are 70 years old biologically. I actually recently saw an article about you and read it in Popular Mechanics, which is an interesting place to read an article about you, Lee. But it talked about your own health routine. So you've been deep in the weeds on this. What have you come to as a synthesis for your own program for how to actually live

in a way that is about scientific wellness and that is about reversing your own biological age? Well, I would say that nathan still looks like he's 12 so i think i think i want to hear you i'm waiting for people to say that after i'm 50 you know which isn't so far away who's got it well i would say that i fundamentally agree that the core set of things for health, namely diet, exercise, sleep, and stress, I really believe in ways to mediate them. For exercise, I was an athlete, played football in high school and college. I've exercised my entire life, vigorous exercises. And it's a way of my life. I do it virtually every single morning. I spend 40 minutes and I do intense aerobic exercises like

150 pushups and 100 sit-ups, 100 deep knee bends to exercise all the deep muscles. And that's really important as you age because- Well, you do 150 push-ups all at once? No, I do 80 at the beginning of my routine and 70 at the end of my routine. Wait, you can do 80 push-ups straight? Absolutely. At 85 years old? That's unbelievable. That's unbelievable. I mean, I can get to about 70, but I'm like younger than you. Well, but you haven't done those kind of

things. So exercise is a big part of my life. I'll tell you on the diet, it's all the classic things, vegetables and fruit and low on the gluten kind of thing. But I think what has been a real I ballooned up to 195 pounds at one point in my earlier career. And I've used intermittent fasting to painlessly bring me down to I weigh just about what I weighed when I played high school football now. And I'm in terrific shape. So I think intermittent fasting where you eat it in the evening and not again until noon the next day and then dinner. So you do your eating in an eight-hour window rather than a 16-hour window. But the other things I do balance out in my blood, all these chemistries that you've talked

about in the blood, I try and I have two genes that block the uptake of vitamin D, so I have to take megadoses, 5,000 international units, just to keep it at a normal level and everything. And there are other chemistries that are being explored that block aging and so forth that I think are going to be very intriguing to look at in the future. And all the things we've learned, the actionable possibilities, where they're relevant, I've tried to adopt those and use those. Keeping your blood cholesterol down. I have a terrible family history of heart attacks in the fifties for my three previous

generations. And, and so I've made it well past the fifties with, with a subset of the genes my ancestors had anyway. That's amazing, Lee. I mean, I think you're a testament to what's possible. I mean, you're clearly sharp as ever. You're doing 150 pushups a day. That's a lot. And you're continuing to as ever. You're doing 150 pushups a day. That's a lot. And you're continuing to produce your life's greatest work. And I think the best is yet to come, I think, for you guys. That's how I look at it.

With Nathan, I think we both look at it exactly the same way. And Nathan is in his infancy. He's got a long ways to go. He's a baby. So how did you get 10 years younger, Nathan? Yeah. So the routine that I've been following that's been working for me pretty well, I mean, there's all the usual things that you have to do, right? There's a mix of aerobic and weight training and so forth. The things that I've really found that have been working well

for me, especially lately, and this is the kind of advice you hear all the time, but just focus on things that you think you can do forever. Because I've had a number of times when I've gone on, you know, I tend to go really intense and then I hurt something. And so the things that I've been doing that have worked really well for me. So one on diet. So I also do the intermittent fasting. So, you know, I rarely eat before noon work days. I tend to fast till about two o'clock. If I'm at home, I tend to fast till eleven thirty or so. I usually eat a little earlier if I'm at home. But so I'll eat a little bit later. I tend to have a relatively small meal and I'm very consistent about like lunch or breakfast.

If I'm at home, I pretty much every day will eat plain Greek yogurt with blueberries and a little bit of oats in there. And I put a little collagen in coffee. And so basically what that does for me is it gives me 80 grams of protein to start the day and with a little bit of other things. And I'll take my various supplements. Maybe I'll talk about it in a moment. And so that works well for me. And then I like – for me, it works well because I save about – and then I save my larger meal for dinner. Data is probably that it's probably better to do it the opposite, but I much prefer just from preference to do it that way.

And so, you know, and so I'm generally in a calorie deficit because I'm trying to I'm trying to lose a little bit of weight. So it's a you know, so I'll eat 500 ish calories for lunch and about a thousand ish for dinner typically. And then the thing that's been really helpful to me that I got from a nutritionist has been very helpful is to try to take a, is to use like this rule of thumb on protein. And this is especially, you know, it's probably a little higher than you need on protein, but especially if you're in a calorie deficit, I think that's, that's good is that if you take the number of calories and you drop a zero, then that should be the, you know, that's kind of your target for the amount of protein you'd like to see. So if I, so in my Greek yogurt, so anyway, so if you do, if you have 300 calories, you'd like to get 30

grams of protein as part of that 300 calories. It's a little on the high side, but for me, that works really well. That's partly because I'm in a calorie deficit and partly because I probably don't track every single thing that I eat. So you probably have a little bit of, you know, so it gives you a little bit of leeway there, but like Greek yogurt for 300 calories of Greek yogurt, it's about 60 grams of protein. So I actually start much above that level and it gives me some room to come down as I eat a little bit of fruit or something like that during the day. So, that that has helped a lot. And so far this year, I'm down about 20 pounds and I've also gained five percent of muscle at the same time. So it's been working pretty well for me. So I'm exercising my exercising. My also exercising. Yes, I do. I do resistance training. So I work out. I do my weight training on days that I stay at home.

So I work in the office three days a week. I have exercise bands in my office. So when I get a little tired in the afternoon, I do just kind of some extra resistance training in the office when I'm there. And then in the morning, you know, I'll do yoga on days that I go in. So I do something kind of easier. And I don't do super long yoga. I like to do yoga with Adrienne, you know, on YouTube. So I just do like her routine. So I do, you know, it's that in the morning before going in. And then when I'm home, I alternate between

weightlifting and running. And I find that to be really easy because I, you know, and then if I'm if I'm commuting in, I, you know, I walk for an hour. So I at least get that. And then I'll do running on days I'm home. So my routine is set up in such a way that it's very enjoyable for me, and it's pretty easy for me to do. It's easy to stick to. Well, it's habit. It's just kind of reinforcement. I can do it forever.

Like, it's just – oh, and between my bedroom and my bathroom, I have a pull-up bar. And so I do pull-ups there, and so I can now – so I can do pull-up bar and so i do pull-ups there and so i you know i so i can now you know so i can do i can do pull-ups in between so if i need to go to the bathroom then i do a few pull-ups and so that's so where i watch you know if i'm going to watch a show or something in the evening the other thing i keep by my the different there's two places in my house i'll do this and i keep um forearm exercises there you know so there's like this device that you, you know, you can kind of push your fingers out and then there's, you know, like a hand device. And those are just sitting there.

So if I'm sitting there doing that, so I do those every day. And then in the two rows- Yeah, grip strength is a huge thing correlated with longevity, believe it or not, yeah. I know that, that's why I started it. So, you know, so I do grip strength exercises pretty, you know, almost every day because they're just sitting there.

And the other thing I do is if I'm, you know, if I'm in one of those rooms, we also have a small trampoline in each of those rooms. So, you know, rather than sit, I can just do whatever on a small trampoline and so forth. So what I've tried to do is just build as many like little things into my daily routine such that a little is better than nothing. And then on days I stay home, I reserve those for my bigger workout days because I have the extra time because I'm not commuting for two hours. Well, I think that's what that's key. It's making the healthy choice and the default choice, the default choice and the easy choice, right? If it's hard, you're not going to do it. I'll add one more thing about what I do. I do walk to work a mile each way back and forth, and it's actually a reasonable uphill slog going home. But what I take in a vest are two grippers

and the entire two miles I'm walking, I'm doing the gripper thing. So I'm a firm believer in, if your hand strength is great, you're aging well. There you go. Well, you guys are both inspirations. I mean, both in terms of your own personal routine and what you're doing, but more importantly, paving the way for a radically new, different way of thinking about health and medicine and disease and pioneering something that I think is going to be the future of health care. And I think everybody should definitely get a copy of The Age of Scientific Wellness. It's an amazing book. It's subtitled Why the Future of Medicine is Personalized, Predictive, Data-Rich,

and in Your Hands. It's available everywhere you get books. It's really an important book. I think it's one of the most, I think, important books in medicine in the last half century because it maps out a future that we're all going towards, whether we realize it or not. And I think every doctor should read this. Every healthcare administrator should read this. And certainly every person who has a body, which is most of us, should read this. So I think it's really an incredibly important book. And I really look forward to working with you both this. So I think it's really an incredibly important book. And I really look forward to working with you both on this. I think it's such an important project to sort of map out the phenome and create ways to actually create predictive models based on the

emerging science and systems thinking. So God, thank you so much for being born, for doing this work, for paving the way for so many of us. I feel like we've left a thousand topics on the table, but they're all in the age of scientific wellness. I encourage everybody to grab a copy. If you've loved this podcast and learned a lot, please share with your friends and family on social media. How have you optimized your wellness? How have you measured your own scientific wellness? We'd love to learn from you. And subscribe right with your podcast. We'll see you next week on The Doctor's Pharmacy. Thanks so much, Mark. Hey everybody, it's Dr. Hyman.

Thanks for tuning into The Doctor's Pharmacy. I hope you're loving this podcast. It's one of my favorite things to do and introducing you all the experts that I know and I love and that I've learned so much from. And I want to tell you about something else I'm doing, which is called Mark's Picks. It's my weekly newsletter. And in it, I share

my favorite stuff from foods to supplements, to gadgets, to tools to enhance your health. It's all the cool stuff that I use and that my team uses to optimize and enhance our health. And I'd love you to sign up for the weekly newsletter. I'll only send it to you once a week on Fridays, nothing else, I promise. And all you do is go to drhyman.com forward slash pics to sign up. That's drhyman.com forward slash pics, P-I-C-K-S, and sign up for the newsletter and I'll share with you my favorite stuff that I use to enhance my health and get healthier and better and live younger longer. Hi, everyone. I hope you enjoyed this week's episode. Just a reminder that this podcast is for educational purposes only. This podcast is not a substitute for professional

care by a doctor or other qualified medical professional. This podcast is provided on the understanding that it does not constitute medical or other professional advice or services. If you're looking for help in your journey, seek out a qualified medical practitioner. If you're looking for a functional medicine practitioner, you can visit ifm.org and search their find a practitioner database. It's important that you have someone in your corner who's trained, who's a licensed healthcare practitioner, and can help you make changes, especially when it comes to your health.