Dr Michael Snyder on Using health Data to Keep People Healthy
Having helped to bring big data to genomics through the lab techniques he invented, such as RNA-Seq, the Stanford molecular biologist Michael Snyder is focused today on how to use health data from devices to increase the human healthspan. Some cars have as many as 400 sensors, Snyder notes. “And you can’t imagine driving your car around without a dashboard…Yet here we are as people, which are more important than cars, and we’re all running around without any sensors on us, except for internal ones.” To Snyder, smart watches and other wearable devices should become those sensors, feeding information to our smartphones, which can then be “the health data dashboard for humans and just let us know how our health is doing.” (You can sign up to participate in the Snyder lab’s study of wearables and COVID-19 at https://innovations.stanford.edu/wearables.)
Snyder has been chair of Stanford’s Department of Genetics since 2009 and is director of the Stanford Center for Genomics and Personalized Medicine. He has a BA in chemistry and biology from the University of Rochester (1977) and a PhD from Caltech (1982), where he studied with the molecular biologist Norman Davidson. He did a postdoc at Stanford from 1982 to 1986 and then went to teach at Yale in the Department of Molecular, Cellular, and Developmental Biology from 1986 to 2009, when he moved back to Stanford.
At Yale, Snyder and his lab helped to develop many of the tools undergirding functional genomics, including RNA-Seq, one of the two pillars of transcriptomics (alongside microarrays). Snyder is also known in the world of personalized medicine for having discovered through genomic analysis of his own blood that he was at high risk for Type 2 diabetes, which he later did develop, but controlled through exercise and diet. That work to create an “integrated personal omics profile” (iPOP) was later described in a 2012 Cell article. Eric Topol of the Scripps Research Institute called it “a landmark for personalized medicine” and an “unprecedented look at one person’s biology, showing what can be accomplished in the future.”
Snyder is the author of a 2016 book from Oxford University Press called Personalized Medicine: What Everyone Needs to Know. And he has founded or co-founded numerous life sciences companies, including:
- Personalis (precision oncology through liquid biopsies of tumors)
- SensOmics (genomics + machine learning to screen for childhood conditions such as autism)
- Qbio (membership-based access to “BioVault” platform gathering numerous biomarkers to predict health risks and recommend healthy habits with health data)
- January.AI (albumin-encapsulated nanoparticles to deliver drug molecules to tumors)
- Filtricine (cancer management through “Tality,” a line of foods that cuts off amino acids needed for tumor growth)
- Mirvie (formerly Akna – blood tests to predict pregnancy risks such as preeclampsia, preterm birth, gestational diabetes)
- Protometrix (maker of protein microarrays, acquired by Thermo Fisher)
- Affomix (maker of technology for high-throughput screening of antibodies against human proteins; acquired by Illumina)
Please rate and review MoneyBall Medicine on Apple Podcasts! Here’s how to do that from an iPhone, iPad, or iPod touch:
1.Open the Podcasts app on your iPhone, iPad, or Mac.
2.Navigate to the page of the MoneyBall Medicine podcast. You can find it by searching for it or selecting it from your library. Just note that you’ll have to go to the series page which shows all the episodes, not just the page for a single episode.
3.Scroll down to find the subhead titled “Ratings & Reviews.”
4.Under one of the highlighted reviews, select “Write a Review.”
5.Next, select a star rating at the top — you have the option of choosing between one and five stars.
6.Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.
7.Once you’ve finished, select “Send” or “Save” in the top-right corner.
8.If you’ve never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out.
9.After selecting a nickname, tap OK. Your review may not be immediately visible.
Harry Glorikian: I’m Harry Glorikian, and this is MoneyBall Medicine, the interview podcast where we meet researchers, entrepreneurs, and physicians who are using the power of health data to improve health and make healthcare delivery more efficient. You can think of each episode as a new chapter in the never-ending audio version of my 2017 book, “MoneyBall Medicine: Thriving in the New Data-Driven Healthcare Market.” If you like the show, please do us a favor and leave a rating and review at Apple Podcasts.
Harry Glorikian: Michael Snyder says his life is all about using big health data to understand things.
He’s a molecular biologist, genomics expert, and life sciences entrepreneur based at Stanford University. It’s partly thanks to Snyder’s work that genomics is a field defined today by big data.
In an earlier phase of his career, when he was at Yale, he and his lab members invented some of the fundamental technologies behind functional genomics, that is, the study of gene transcription and regulation, and also transcriptomics, which focuses on the RNA transcripts genes produce.
At Stanford he’s focused on using big data to transform the healthcare industry, so that it focuses less on reacting to illness and more on proactively lengthening people’s healthy lifespans.
Snyder is like me in that he’s convinced that smartwatches and other wearable devices are going to be an important source of health data. If everyone had one, we could probably detect health problems a lot earlier and make better lifestyle decisions thanks to health data.
In fact, about halfway through the interview you’ll hear Snyder explain how his own wearable devices have gotten him out of some personal health scrapes. In the middle of one flight to Norway, Snyder says his heart rate went up and his blood oxygen went down. Before his flight even landed, he’d correctly diagnosed himself with Lyme disease and was able to get an antibiotic that quickly cleared out the infection.
Later, during the height of the covid pandemic in the U.S., Snyder’s lab proved that about three-quarters of the time, they could predict which FitBit users would develop covid symptoms based solely on heart rate health data from their devices.
The medical establishment hasn’t always been receptive to this kind of science. And the era of health data-driven collaboration between patients and their doctors has been a long time coming. But thanks to better technology and the impact of the pandemic, Snyder thinks it’s finally arriving now.
Harry Glorikian: Dr. Snyder, welcome to the show.
Michael Snyder: Thanks for having me.
Harry Glorikian: It was funny cause I was reading your background and I was like, wow. I mean, so many different aspects of your background, both, you know, from a scientist and an entrepreneur from, you know, helping start, like, I was going through the list of the companies. It was longer than, than I remember. Like, I know quite a few of them, but not all of them. And so I just thought like from a high level, like, how do you explain to someone what you do and why you do it?
Michael Snyder: Okay. Well, we’re all about big health data. We like to use big health data to understand things. And these days we want to use big health data to transform health. And really that’s what my career has kind of been built around. So over the years, we’ve invented technologies for collecting big health data and then we’ve implemented them. For a long time, when I started out, it was really to try and understand biological systems. People use to study genes one at a time, for example, and proteins, one at a time, we came up with a way of studying them all at once. And that hadn’t been done before. And then try and understand them in a systems context so that you weren’t really just looking at, you know, if you have a jigsaw puzzle, look at one or a few pieces of the time, we wanted to see the whole puzzle at once as best we could. And so that’s really been the philosophy.
As I say, it was first choosing to study basic cell biological problems. And then I moved to Stanford now about 12 years ago. And the goal there really was to bring it to medicine see if we can understand medicine, you know, at a holistic level, not just, you know, if you’ve got high sugar that, you know, you’re diabetic. Sure. But are there other things going on as well? Like other metabolic conditions? And that’s really the philosophy. Let’s look at the whole system, better understand what’s going on, and see if we can come up with solutions.
Now, the thing, I think that’s been a big shtick of ours and at least in the recent years has been focused on keeping people healthy, extending the healthspan as opposed to just doing sick care, which is where medicine is today. So we really want to transform medicine.
Harry Glorikian: Yeah. It seems that, you know, health span has become the, the big shift. And if you look at where we’re going from the Affordable Care Act and everything, it’s better to, it’s more profitable actually to keep someone healthy than just treat them when they’re sick. So I like that shift because it brings technology more into the forefront.
Michael Snyder: Totally. Yeah, no. And it’s going to require a lot of changes and a lot of levels, the whole payment level in the United States is broken. People often only get paid when sick people go in to see them like hospitals, you only get paid to show up when you’re ill. We don’t put enough emphasis on keeping people healthy because people have said, well, you know, show me it saves money, show me it does it. But until you run those studies, it’s hard to do that. So I think the incentive systems are changing. That’s slow, but it’s also getting you know, physicians and others used to this concept of bringing in big health data to better understand people’s health.
And maybe to elaborate a little more on this. You know, if you walk into a doctor’s office today, it looks pretty similar to the doctor’s office of 40 years ago, you know, a few gadgets are updated, but otherwise the same. And guess what the number one user fax machines is in the U.S.? It’s the healthcare system. My daughters don’t even know what a fax machine is.
Harry Glorikian: Yes, yes. It’s true. Somebody did ask me the other day, like, can you fax it to me? I’m like, yeah. I think my scanner might, but I don’t think I’ve got a jack that I can actually plug it into to actually send it. ‘Cause I don’t do that anymore.
Michael Snyder: Nobody does that except for the medical system pretty much. Yeah.
What is health data?
Health data refers to any information related to an individual’s physical and mental health, including demographic information, medical history, symptoms, diagnoses, treatments, and outcomes. It can be collected from various sources, such as medical records, wearable devices, and health surveys, and used for research, clinical decision-making, and population health management.
Harry Glorikian: So, you know, you’ve had you, you mentioned it, you had a hand in, in, you know, developing these foundational ideas and technologies in functional genomics, such as, you know, high throughput protein sequencing techniques, you know, known as RNA-seq and then making transcriptomics possible. Like, can you talk about what it’s been like to sort of, you know, develop those technologies and then, you know, be at the forefront of trying to answer these big molecular biology questions and, and what in your mind, what came first? Was it, I gotta answer this molecular biology question so I’m actually, I’m going to develop this instrument and then be able to answer that question. Does that make sense?
Michael Snyder: Yeah, it’s a little of both to be honest. Often we develop technologies out of need or out of observations. We have, so for example, in RNA-seq, we were trying to map where all the transcribed regions were, where all the genes were in yeast, which was the organism we were studying at the time. And we tried this one now very outdated method that just work miserably and we just stepped back a minute, said there’s gotta be a better way. And so that’s how we came up with, we thought about it, came up with a way and then implemented it and, and showed it worked. And then of course if it works, it takes off quickly, very much like CRISPR. And that’s been true for other things. In some cases as we’ll make an observation like when we first invented a way to map the targets of key regulatory proteins called transcription factors there, we saw that these things were, were giving these dots in what’s called the nucleus of the cell. And we said, well, where are those dots located? And so we came up with a method for figuring out where are all the, where all the binding sites for our, for these key regulatory proteins. So it’s, it’s been a variety of ways.
And then when it’s come to medicine, we, once we invent the technology, so well, people will say, well, well, how can we use these now in other ways that would be beneficial. And I’m not sure what you know, but I was at Yale for a long time, and I had a great time, it was fantastic place, but I was more on the main campus and it was just harder to implement them into medicine. And then about 12 years ago, I moved to Stanford and I’m right in the heart of the medical school where there’s all these clinicians and very eager, beavers around, trying to figure out how to better, you know, do medicine these days. And so it’s just been easier as we’ve implemented technologies to roll them out and see how they might work in the clinic.
And so I think one of the biggest projects we launched when it came to Stanford was we call it personal ’omics profiling. The idea, you collect a lot of deep health data around a person and you do it longitudinally. So we’ll, we’ll sequence their genome we’ll look at all the molecules we can in their blood and urine, meaning their RNA and their proteins and their metabolites. We, we do deep questionnaires and clinical tests on people.
And then, and then, yeah, about eight years ago, we sort of got into wearables back when they were just fitness trackers, realizing they would be powerful. So the idea was to collect health data on people—while they’re healthy, by the way, not while they were sick, while they were healthy—and do it longitudinally, do it every three months and see how they change. And if they got ill, then we collected more sample. And that was the idea. That’s turned out to be a really flagship project, I think, for just how we might better implement health.
And you raise the issue about starting companies. So a little of my philosophy is I think academics are great at discovery. They’re great at proof of principle, but they’re not good at scaling. They think they are, but they’re not. And this is what companies are just fantastic about. So we’ve spun off, we think some, what I hope will be powerful companies. One was a DNA sequencing company called Personalis. They’ve done very, very well.
Then we’ve spun off Qbio, which is doing sort of a, you know, a more commercial version of this personal ’omics profiling, as I mentioned, but they added on whole-body MRI and have some other things that are pretty powerful. So they’ve, they’ve got a medical version of, a more actionable version, again, our academic lab is doing this research for us and trying to figure this out, but the company can do it, implement it.
And then we have another company, January AI, it’s doing continuous glucose monitoring for trying to better control diabetes. So again, we figured out some things in the lab and then it made sense to commercialize it. So, so it all goes kind of hand in hand to me. It all makes sense. And it’s very satisfying by the way to do stuff in the lab that, that we think is impactful and then try and get it out there to a broader group. We think that’s how you scale. I don’t think academics are capable of scaling. Certainly not very well, whereas companies are.
Harry Glorikian: Well, yeah, I mean, I, you know, quite some time ago being a product manager, I mean, you, you, you had to like your biggest accomplishment was getting that thing from the bench right out into somebody in the field and, oh my God, it actually, yeah, it did something. Right. And that was the exciting part. Stopping at the research, I would have been like, “That’s it? Like, all I got was all I got was a paper out of it?” Like, no, no. I want to, you know, I know that that’s always the beginning.
Michael Snyder: Yeah, we got excited about the papers, absolutely. But we’re very also, it’s just fun to see it get out further. Totally. And again, so that’s literally all the companies, maybe with one exception have spun off of the things we were doing in the lab said, all right, we get it. Now it’s time to scale this out and develop it into something people would be interested in. And it is very satisfying, as you say.
Harry Glorikian: So, so, you know, I mean the genome has come down in cost. I mean, a lot of other analytic technologies have come down in cost. I mean, I know the latest thing that Illumina has said is they want to get the genome down to like $60 to do the functional work. Not necessarily the analytics or analyzing part of it. How do you see that changing what you’re doing and the impact? I mean, you’ve got a lot of health data, so I feel like you can almost. paint a picture of the evolution of a person. If you could sort of see the initial traces, how do you see this playing a role in what you’re doing and the impact that it’s going to have on where it’s going next?
Michael Snyder: Yeah. I think getting the cost down is a big deal because when we set this up as research, it was very, very expensive. And so getting it out there will help, especially when you’re talking about keeping people healthy because people don’t want to dump a lot of money into a healthy person. ’Cause they don’t know that—here’s a problem with our healthcare system. Most people will shift every 18 months, that’s the average time people stay with their provider and then they’ll shift to a new one. And that may be because their company’s shifted. Not necessarily they did, but their company may have done it. And sometimes they change their job, they shift. So that’s whyIt’s a barrier then for, for providers, healthcare providers put a lot of money into you, when 18 months later you’re going to be with somebody else. But if the costs are pretty cheap, like the genome sequences, let’s say, but the interpretation is $200. It’s worth it to you because then it’s a lot easier to execute preventative medicine, get your genome sequenced, predict what you’re at risk for, and with a fairly low cost. But if they’re going to dump $2,000 and you’re going to be with somebody else, there’s a lot more balking, if you know what I mean.
So I think, I think keeping the costs down is a big deal. Qbio, for their exam, they charge $3,500, and on one hand that’s a lot of money and we, we like people to do it two months. You get a whole-body MRI and other things. On the other hand, we would argue for it. It should save and already has. We found like early prostate cancer, early ovarian cancer, early pancreatic cancer, which is a big deal and some heart things and stuff like this is from the first a hundred people that we did. And it’s more now. So, so we show it has utility. And of course, if you’re one of those people, it’s a big, big deal.
So, and, but by getting the cost down, it just gets the whole barrier away. Right now you have to pay out of pocket because there is no reimbursement. So the cost gets down and I think people would reimburse because there’ll be willing to run trials to show it does work and saves money. So I, I think the whole thing will go together as costs drop, and we can expand this out and show utility.
Harry Glorikian: Well, and you know, if you think about the implementation of technology, like if you could carry it around on your iPhone, when you go to your next physician, and you’ve got it with you right at that also brings the cost down rather than have to do everything all over again.
Why is data important in healthcare?
Health data is important for several reasons:
- Clinical decision making: Health data can provide crucial information for healthcare providers to make informed diagnoses and treatment decisions for their patients.
- Research: Health data can be analyzed to gain insights into disease trends and risk factors, leading to the development of new treatments and cures.
- Population health management: Health data can be used to track the health of populations and identify areas where public health interventions may be necessary.
- Personalized medicine: Health data can help to tailor treatment plans to the unique needs and characteristics of individual patients.
- Quality improvement: Health data can be used to monitor and improve the quality of healthcare delivery.
Overall, health data plays a vital role in advancing medical knowledge, improving patient outcomes, and promoting public health.
Michael Snyder: Totally. Yeah. In the future. And I think physicians are just warming up those. There’s an education side of this from the physicians, you know. When we first got involved in the wearable space, they would tell us how inaccurate it was. And they didn’t like the idea that your iPhone would be so powerful. Possibly more powerful than they are. There was a threatening aspect of the whole thing. And I think they’re now reassured that, first of all, they’re very important. They’re not going away. There’s these technologies to augment what they’re already doing.
And, and it’s, there’s an education side. I remember when genome sequencing first came out, even at an enlightened place like Stanford, I would talk to some of my colleagues and they’d say, well, nobody shows that really worked, you know, and it’s got a lot of errors. They just think about the negative. The instant reaction is, you know we don’t really know how to do it. You might tell people something they’re not going to get. That’s harmful and, and try to tell them, well, look, you have just educate people and educate the physicians.
And now, when we first started actually, you know, cancer, even people were pushing back and cancer is a no brainer. You need genetic tests or sequencing. But for elderly people, it was a strong pushback, right? Everybody’s telling you, Mike, what you’re doing is really harmful to people. You’re going to get people to turn them into hypochondriacs when you sequence their DNA. And now there’s some, some people feel that way, but most people have kind of warmed up or at least maybe it’s 50-50 are receptive to the idea. Maybe it is a good idea to get a, to find these risks.
From our standpoint, just from the first 70 people we sequenced the genome, we found someone’s BRCA mutation. And now that person out of mutation suggests they might have certain kinds of cancer. They did a whole-body MRI that early thyroid cancer, we caught that had it removed, saved their thyroid, the rest of their thyroid. That is, you know, very, very useful. Another person, a very young person had a mutation in a heart gene and would have been at risk for cardiomyopathy. It turns out his father died young of a heart attack. And so he had this mutation, we saw this thing and sure enough, he had a heart defect. Didn’t even know it. He’s on drugs now.
So, so these technologies can be very, very useful, very, very powerful. But you have to show physicians that, and then they sort of go, “Oh yeah. Now I get it. We kind of get it.” They may say, well, show us the evidence. And so that’s what we’re trying to do.
Harry Glorikian: Yeah. I mean, I just. I’ve got a book coming out in the fall and I just interviewed somebody who had done participated in BabySeq. Robert Greene’s thing, right? And identified an issue that had a profound effect actually on the decisions of the mother, not the baby. And so it’s an interesting story when she went through it, I was like, wow, that is super impactful. You know, it adds a lot of, you know, it is funny. She said, you know, we did this and I was not expecting this. Right. So it was an eye opener, but it’s affected her decision-making going forward. And it’s along the lines of BRCA, what she was informed of, but I’m sort of saving it for the book. So when it comes out in the fall.
Harry Glorikian: But you know, you wrote a book back in 2016, that introduces non-experts to personalized medicine. You know, you covered everything from how DNA works to the applications in genomics, in cancer. So. I almost think like that might need a refresh or at least the publisher might want to put it out again, because I think people are more interested now. But if you were writing that book from scratch today, you know, five years later would you write it at all? Would you, the field is, I feel like it’s exploded in the last five years on the one hand. On the other hand, I still feel like I talk to people that still don’t understand the impact of it. So I feel like I’m talking to both sides sometimes, but. How do you think the field has changed in the last five years? And where do you see it going next?
Michael Snyder: Yeah. Great question. So when we wrote the book, you know, people really didn’t like this area. They didn’t like it, sequencing genomes and things. They thought it was harmful. And the same idea where, I mean, we literally collect millions of health data points. Every time we sample someone, then people still bring it up. And so it was really, the goal there was to educate people about what the technologies are, what they’re capable of, and this sort of thing.
So I think we have come a long ways since then, where the field was mostly against. I asked people to raise their hand. How many of you want to get their genome sequenced? Usually there’s a small fraction, even in an educated group. Now it’s probably the majority. If they haven’t even done it already—they may have already done it. So I think the world has changed. I think what I would do is update the power of the new technologies. New technologies have come out, even since we first put that book out.
So I’d add more. Expand the wearable space. I just think we can put a smartwatch on every person on the planet. If we wanted to a very inexpensive one that would be a health monitor for people. And, and there would be a no better time for that than this pandemic that’s going on now, because we actually can show, we can tell when people are getting ill prior tosymptoms from a smartwatch, from covid and other infections. So we can talk about that more if you like, but it’s a pretty cool study. We can show again, 70% of the time, we can tell when you’re getting ill, because your heart rate jumped up, and we pick it up with a smartwatch. So imagine putting that on everyone in the planet and just letting them know, “Look, we can tell when you’re getting ill.” You know, even if it’s not perfect, a bunch of the time that we think would be very useful. They don’t send their kids who are sick to school, affecting everyone, or it shows up in a nursing home and, you know, you flag it right away. And that would be, we think very, very powerful.
I view it as analogous to, you know, a car. A car usually has several sensors. Some have as many as 400 sensors on them. And you can’t imagine driving your car around without a dashboard, the gas gauge or, you know, a speedometer or an engine light or all these things on we’ve gotten so used to this is what you do when you drive a car.
Yet here we are as people, which are more important than cars, and we’re all running around without any sensors on us, except for internal ones. They’re okay. But they’re kind of slow. And I just, to me, it’s just totally logical. We should all have our own, you know, sensors on us. It’s the car health dashboard. Our smartphone will be the health dashboard for humans and just let us know how our health is doing. And it doesn’t mean when you see a light go off that for sure something is wrong, but it gives you a heads up. And it has, you know, in, in some cases our profiling has really had life-saving consequences.
Harry Glorikian: Yeah. And I’m, well, I mean, it’s funny cause I think about these things and I look at a lot of these technologies and. You know, it’s always a single biomarker of some sort, right? That that’s, you know, a heartbeat or temperature or something. And then I think about, well, the next level has got to be a combination of them, which makes the predictive power that much better.
Michael Snyder: That’s right. Yeah. We call that multivariate, yeah, where you bring in several features. So you start seeing it enlarge something or a thing on an image, and then you see that those biomarkers of those. That’s how we discovered someone with an early lymphoma in our study that had an enlarged spleen, and then we saw certain markers are up in their blood and said, something’s not right here. And then they did follow up and sure enough had early lymphoma, no symptoms yet. So again, caught it early, a lot easier to manage just much better off. We have a number of examples like that. So the combination tells you.
And the other thing that’s very under appreciated is the longitudinal profiling. People don’t realize that if you go in and get tested now, and they rarely look at your old measurements. And so they just see if you’re in the normal range and you can be at the high end of the normal range, but you’re still “No, all right, you’re fine. Don’t worry about it.” But if you look at your trajectory, you know, maybe you’ve been running kind of normally in the low normal range and suddenly this one jumped up, you know 50%. You can still be in the normal range, up 50% and something’s headed in the wrong direction and you would be ignored for that. Whereas if we just had very simple algorithms that can flag that sort of stuff. “Look, you’re not only up in this marker, but you’re up in that one too, which is related, you know, maybe something’s going on early.” Let’s see what’s going on there a little better and catch things earlier again when you can manage it better. So, so I think we ought to bring in longitudinal information again, to me, that’s why the wearables are so powerful because they measure it 24/7.
Harry Glorikian: Well, I do that with my, my physician. I walk in, I’m like, okay, here’s my health data for the last, you know, X amount of time. And it’s funny because even I’ve noticed, like during covid, cause I was much more sedentary, like certain things were going in the wrong direction. And I was like, oh no, no, no, no. I got to get those, those back in line. If I didn’t have the ability to look at it over time. And I was only looking at that one point, you know, how am I going to see where it’s going?
Michael Snyder: Out of context. Yeah. Here’s another thing that’s wrong with medicine today. It’s all population-based, so they will make every decision about your health based on population averages and hence that normal range. But again, you may not at all be like normal population levels.
And so you’ve been told, and here’s my favorite example, you’ve been told since day zero that your oral temperature, when you put it thermometer in your mouth is 98.6, but it turns out, first of all, that number is wrong. Yeah. Average temperature is 97.5. But more importantly, there’s a spread. So the what’s called the 25th quartile is 94.6. So four degrees below and the 75th quartile, 99.1.
So in today’s world, if your normal baseline temperature is 94.6, that’s your healthy temperature, and you walk into a physician’s office at 98.6, they’ll tell you, “You’re healthy. Everything’s great. What are you doing? Go home.” But you’re at four degrees Fahrenheit over your baseline. I guarantee you’re ill. This is just, it’s not healthy. So you got to know your baseline. And for me, by the way, mine is 97.3 and it’s been dropping a little bit over the last 10 years. Which is, there’s some studies suggesting that is the case actually, so that people do drop a little bit as they get older. But the point is that, you know, my baseline is not 98.6, if I am at 98.6, I am ill.
Harry Glorikian:I want to pause the conversation with Michael Snyder for a minute to make a quick request.
If you’re a fan of MoneyBall Medicine, you know that we’ve made more than 60 episodes of the show. And you can listen to all of them for free at Apple Podcasts, or at my website glorikian.com, or wherever you get your podcasts.
There’s one small thing you could do in return, and that’s to leave a rating and a review of the show on Apple Podcasts. It’s one of the best ways to make sure that other listeners will find and follow the show.
If you’ve never posted a review or a rating, it’s easy. All you have to do is open the Apple Podcasts app on your smartphone, search for MoneyBall Medicine, and scroll down to the Ratings & Reviews section. Tap the stars to rate the show, and then tap the link that says Write a Review to leave your comments. It’ll only take a minute, but it’ll be a huge boost for the show.
Thank you! And now back to the interview.
Harry Glorikian: You know, just talking about the wearables, because I noticed like earlier you had at least four devices and I think an Oura ring, or maybe…
Michael Snyder: I lost it recently, but yes, I normally wear, I normally wear eight of these devices. An Oura ring and four smart watches. I have a continuous glucose monitor and environmental sensors. I’ve got all kinds of gadgets.
Harry Glorikian: Oh Jesus. Okay. Well, so tell us where you see the overlap of these digital devices and the personalized medicine sort of coming together, because I feel like one is much earlier warning system or could be an earlier warning system of what may come in the future. And one is a current monitoring system, of how the machine is working.
Michael Snyder: Yeah. I mean, I do think they’re an integral part of personalized medicine. Only now I think people are realizing the power. The pandemic, I hate to say it, helped with that because remote monitoring is now become popular and the concept that you can start managing people.
So, a little background, we started on this about eight years ago, when the Fitbit was out there. And people are using these fitness trackers. We thought, well, gosh, these are pretty powerful health monitors because they’re measuring your heart rate and they measured 24/7. In fact you know, the first device we used doesn’t exist anymore, a Base watch, it takes 250,000 measurements a day. Now some of them will take 2.5 million measurements. They really follow you in a deep way and they’ll measure heart rate, variability, skin temperature. Those can all be pretty accurate, by the way. It depends on the device. Some will measure blood oxygen and even blood pressure. Those are less accurate, but their deltas are pretty good, meaning the changes. And then there’s other things out there too, something called galvanic stress response.
So they can measure all kinds of things. They’re always following you. So we think that’s super powerful. Now when we first started, again, physicians pushed back and said, well, you know, everybody knows they’re not accurate and we actually want paper coming out. Very soon [they started] saying, well, actually they’re more accurate for some measurements, like heart rate than what you measure in a physician’s office. My heartbeat can vary by as much as 40 beats per minute, depending whether I drove their biked there. Even if I rest at 15 minutes, it’s still different and whatever’s going on in my life.
And, but if I pull my resting heart rate off in the morning, first thing it’s pretty constant, unless I’m either stressed or ill. So you actually have better measurements from some, for certain kinds of measurements from these devices.
So that’s the first thing you have to show, show them they are accurate and things. So we think we’ve done that in some cases for some kinds of things. So I think we now just need to get physicians to start thinking about that more and get them as an integral part of your healthcare. That when they show up, they don’t have to take your heart rate anymore. They’ll just read it from, it’ll already be pumped into the system. You can already have it there, and they can follow your trajectory. Since the last time they saw it last, whatever month, six months, two years, what have you, and see what’s going on much, much better than these static measurements that they take every few years when you’re healthy.
So I just think they’re going to be super powerful for following your healthy physiology. And then when you get ill, it’s all about the delta, the shift from your personal baseline. And what’s powerful is because we all have different baselines, different heart rate, different blood oxygen, just what have you. When you shift up, you can figure it out.
And the way we got in the most was from our first work, we actually showed a, I actually figured out my Lyme disease. I picked it up from my smartwatch. I suddenly got a pulse-ox, a blood oxygen. And it was because my, my heart rate went up. I was flying to Norway, of all things, and my heart rate went up much harder than normal. And my blood oxygen dropped much lower than normal. And I saw it on the airplane and it didn’t return to normal after I landed. And I knew something wasn’t right. I thought it was Lyme disease, because two weeks earlier, I was in a Lyme-infested area helping my brother put a fence in in Massachusetts. Most places are Lyme-infested in Massachusetts.
And then I saw this and I, I warned a doctor there. It might be, that’s a classic case, I warned him, it might be Lyme because of the timing. And later got, by the way, I didn’t have symptoms. That was a key. I saw these things before symptoms. I later had symptoms, went to a doctor in Norway. He pulled blood said, yep. My immune cells are up. I’ve got a bacterial infection. And he wanted me to take penicillin. I said, no, I should take doxycycline. The classic case of, you know, you have to take charge of your own health. He pushed back, but he did give in, in the end And, and it turns out it cleared it up. I took it for two weeks and when I got back, I got measured. Sure enough, I was Lyme positive, by a sero test and I give him blood right before I left I was negative, so I seroconverted, a very well controlled experiment.
The point of all of this aside is, I can figure out my Lyme disease from a simple smartwatch and a pulse-ox. And so that showed the power of these smartwatches for doing this sort of thing. And then that’s how we got, we looked into the health data and saw every time I got ill from respiratory viral infection, including asymptomatic time, I could see the jump up in heart rate. So we knew it would work for infectious disease. And then when the covid pandemic came, as you might imagine, we just ramped up or really scaled out that study.
We are device agnostic. So we rolled out the study in a two part manner. So meaning we first wanted to show that our algorithms and perfect algorithms for detecting covid-19. So we partnered with Fitbit but also talk to other groups as well, pulled in health data. We started with Fitbit, we could, right away, we got 32 people who had been covid-infected with their Fitbit watch still running. Some people let them burn out. But we, we, and we had a diagnosis date and a symptom date. And so we could actually show, we initially showed that for 26 of 32, we could see a jump up in resting heart rate from a simple smartwatch, in this case a Fitbit. And we had several different algorithms, both steps and a resting heart rate. We, we showed the algorithms work and then we built what we call it a real time alerting algorithm, actually two of them, we tested them out and they seem to work. So then in December—and we love all of you listening to this to enroll in our study at innovations.stanford.edu/wearables—anyway, what we did in December is showed, we rolled out a real time alerting system that will actually send off a red alert when your heart rate jumps up. It works about 73% of the time. We have 60 people have gotten ill, a little over 60, and we can see those red alert will go out before at the time of symptoms in 73% of cases. And we even now caught two asymptomatic cases where their heart rate went up. They had no symptoms but they happened to get tested and they were positive. So we can show that this thing really does work. And so now we’re trying as the say we are building an infrastructure to roll this out for millions and millions of people.
Harry Glorikian: That’s good because I was just thinking it would be great if these things would proactively ping you and tell you there’s a problem rather than you have to look at them all the time and see where you are compared to baseline.
Michael Snyder: Yeah. The one minus is you have to open your app and sync it, and we’re trying to do exactly what you just said, set it up so you don’t even have to open the app. You probably have to leave it open, but we want to be able to ping you. We have to get IRB approval. That’s our review board approval, but we want to do exactly what you just said. So right now you just have to check it out every day. You open your app and you’ll see, oh, do I have an alert or not, when you wake up. Do it first thing in the morning. And if you have an alert. We’re not allowed to give a medical recommendation but we could say, look, you have a jump up a resting heart rate and I’ll let you figure out how to interpret it. But ultimately the plan would be to say, you know, Gosh, maybe you don’t want to go to that party tonight or go to work and maybe you want to go get tested for that. Something could be up. That’s ultimately where we want to get to with this alerting system. So, and I don’t think it will be too far away where we’re showing it, where it’s going to pull in more kinds of health data. So we can get that 73% up to 95%. That’s our goal.
Harry Glorikian: Yeah, it’s interesting. Cause I was talking to just the other night to a friend of mine who’s a primary care physician and she was saying, “Well, you know, these things are not very accurate and you know, people are going to come in for problems.” I’m like, okay, hold on. They’re, they’re actually pretty accurate. They take a lot of health data over a long period of time. So, you know, those blips, I can sort of, you know, wipe them out if it’s a truly a blip and I can see a lot of information. And it’s more accurate than me coming in that one time you’ll see me. But the other thing I said to her was, you know, you realize like this is just going to get better. Like the more and more health data we have, the better and better these things get. And at some point it is going to be like the standard of how things are done. And it’s, I think it’s difficult for people to understand that more health data, better algorithms. You know, better equipment, all of them coming together. You just end up at a place where you’re going to, this is going to be the standard.
Michael Snyder: A hundred percent agree. A good case is, imagine if we told people you can’t own a thermometer. They’re medical devices, nobody should have a thermometer. That means that, you know, nobody would be taking their kid’s temperature. By the way, a thermometer is a terrible way to tell if you’re getting ill. It’s an okay way, I should say. Your resting heart rate is way better. When you show that, that it’s kind of funny. A thermometer is a 300-year-old technology, very ingrained in our medical system, and it has some value. Don’t get me wrong. But it’s not as good as any of these other technologies. We can pull off a smartwatch like resting heart rate and other signals and soon respiration rate, all that stuff you can pull off and you’ll have a much better signal for when you’re getting ill than a simple, stick a thermometer in your mouth.
And it’s going to go way beyond infectious disease. One thing we can show, we can get a signal for something called a hematocrit and hemoglobin from a smartwatch, and we can, and that actually can be an early sign that following those levels can give you a clue as to whether you’re getting anemia.
We have another signal coming from a smartwatch about diabetes, something called insulin resistance with diabetes. So we can get, they’re not clinically diagnostic tests. So that, and they’re just, they’re kind of hints if you know what I mean, but very valuable hints. We think, oh, you see this and you see this change, maybe you should go to a physician and follow up on this.
And there’s some measurements from a wearable that there isn’t even a clinical correlate for. There’s something called galvanic stress response, which is conductance on your skin that you know, there is no medical, typical medical correlate for that yet that’s a valuable measure. If you’re stressed, you will sweat more. If your diabetic you’ll have drier skin, it’ll give you a signal towards diabetes.
So these measurements we think are going to be very, very powerful. No one measurement, it comes back to what you were saying earlier. Multiple measurements together will help give you a better idea of what’s going on and clues that something may be up that alert you while you’re still in this, you know, fairly healthy state, we hope and can then take the right course, the right intervention course
Harry Glorikian: You almost wish there was a spider graph that had your normal, and then show deviation from normal on these multivariates. So you could evaluate it over time. I mean, I find myself having to go, I have to go to that one and I have to go to that one. Then I have to go to that one and it would be a whole lot easier if it was in one format or one graph that could show me where things are. Let me ask you a question…
Michael Snyder: By the way I think those integrated systems will happen. Yeah. And your car dashboard is a good example, right? There’s aren’t usually single or single sensors that are triggering. Sometimes they’re integrating multiple sensors to set up a signal and that’ll be true for your health. And just the way the health data is organized again, in our antiquated healthcare system, it comes back because to these individual measurements, whereas instead, you want this as well here, here’s your cardiovascular panel, you know, with the five measurements all together and these other panels around systems to tie and even some broader panels besides that, so that you can see things in this more holistic fashion. And another analogy might be, you know, when a pathologist reads images, they write up a report which they give to your physician. Hour physician can’t read a pathology image slide to see if you have cancer not, but they can read the report that pathologists get. And so I think that’s how we need to integrate these health data. To put it in a usable fashion. To be honest, it’s not just for the physician, but for the consumer, because they’re the ones who can act on it most quickly. They’re the ones who are going to have the most time to think about the information. Again, another flaw, and it’s, it’s no negativity to the physician, but they only have 15 minutes to spend with you. At least in the U S you know, you get a half hour appointment, the physician’s only there 15 minutes, they glance at your chart. They do a few things. They make a quick assessment and they’re off to the next patient. Then they have to write it up manually. Ironically. And then you know, you have a lot more time to spend thinking about what’s going on. So if you have this information accessible to you, something doesn’t look right. I think it’s a better chance for you to take control. It’s like me and my Lyme disease, you know, if I wasn’t watching what was going on, I don’t know what would have happened. It was very valuable for me to have that information.
Harry Glorikian: No, no. I mean, I, you know, it’s funny because I was, you know, we’re using these machines all the time and you know I try to be as deep in the space as I can be. But if there was an algorithm or a series of algorithms, looking at different health data streams that are coming off of me and can sort of be like my friend, right? Whether it’s weight or heartbeat or blood ox or something else that could sort of highlight it for me and then put it into a format that is easy for me to digest. Either graphically or, or a few words. I mean, it would be a lot easier for me to manage myself.
Michael Snyder: Yeah, it’s coming. I think it will hit, but you’re right. I mean, again, medicine’s conservative. If you do belong to, you know, Fitbit, or there are certain programs. Or Apple. They’ll ping you, you know, here was your weight this week, you get these, but we’re just at the trivial stage of what can come. Obviously I think what you’re saying, where you would integrate different health data types and then see these, and again, in this paper we’ll have coming out soon weshow that you can actually follow people’s trajectories and set up AI systems, artificial intelligence systems, follow people’s trajectories to look for these deviations. It’s still very, very at the early phases. I think they’re going to be super powerful for managing chronic diseases like diabetes, obesity.
There’s something called chronic fatigue syndrome that a lot of folks have, and they have crash days and good days. And to be able to tell all these things are associated with your crash days, watch out for those trying to avoid those. These are your good days, do more of those. It’s very, very true in the glucose monitoring space, diabetes. People don’t realize it’s the next endemic, if you don’t realize that. 9% of the us population is diabetic 33% are pre-diabetic. And 70% of those are going to become diabetic. By 2050, they estimate half the population can be diabetic if we keep going the way we’re going. So we need new intervention plans while people are healthy. Don’t wait until they’re already diabetic and have problems.
And this is where the continuous glucose monitoring technology I think is going to be really powerful. Figure out what spikes you. It’s very personalized. What spikes you is very different from what spikes me. Right. And be able to see that. I don’t know if you’ve ever worn one, but they’re just very, very powerful. And so it’s, again, one reason why we formed a company called January AI to help help with that.
Harry Glorikian: Well, it’s funny because my wife was asking me, she goes, you know, I’m wanting, I’m thinking I want to wear one of these so that I can see what I eat, sort of how it affects me, but it’s all by physician prescription. Go and convince your physician, you know, Hey, by the way, I need a script for this.
Michael Snyder: Yeah. So two comments there. One is in Europe there is no prescription, you can get over the counter. So there’s less regulation. So they’re ahead of us on that. I think it’ll happen in the U.S. Right now you do need a physician, but there are studies, there are groups rolling out. So again, I mention ours, but there are others as well. But with January AI, their case. They’d take it even further and you get this continuous glucose monitor for, for 28 days and do the program longer. But you can, it not only shows you what spikes you, but they also train you a little bit, meaning you eat, you know, your favorite food or it could be rice, what have you. Rice, by the way spikes almost everybody. And then the next day you did the same thing. You do it for breakfast, you do the same thing and take a 15 minute walk and it shows how it suppresses your spike. So it’s a, it’s a behavior intervention program as well. So it teaches you. And we think that’s kind of powerful as well. You not only want to get the health data in and have people learn from it. And this thing does food recommendations as well. You want to be able to teach people how to live better, healthier lives as well, doing an intervention, as they say,
Harry Glorikian: Oh yeah, yeah. I mean, I think that, you know, some seeing it so that the health data convinces me and then understanding what I need to do to fix it is also very useful. Right. So. Do you think we’re ever going to get to? You know, I know that we have health data-driven healthcare. Everybody always likes to say we are health data-driven, but I mean, truly, like I don’t make decisions on businesses without really understanding their profit and loss where their costs are, what their spent. I mean, very detailed analysis. Do you think that we’re going to get to this point of [going] beyond hunch-driven medical decision-making? What was that show, oh my God, where the doctor would sort of put all these pieces together and then come out, with a famous actor, I forgot the name of it, but—House yes, yes. House. That was it. I mean, do you think are going to get to more health data-driven. I feel like we should be there already in some way.
Michael Snyder: Yeah. So, you know, I’m very Pollyannaish. I believe the answer is going to be yes. I’m like you, I feel like we should be a lot further along and I just think that’s the conservative nature of medicine. People think, you know, do no harm. And so they do nothing. And I would argue that doing nothing is harmful. So I do think we need to get these, the, you know, this health data integrated better. I think the best way is to roll out studies like the ones we’re doing and others that can show it has power has impact. And that’s how you convince people.
I’d love to come up with a way to accelerate it. I think programs like this are a really great way to do it. A lot of this stuff is going to be consumer driven. I mean, people are now wearing smartwatches not just for fitness tracking, but for health devices, which is itself now the new concept.
So it’s coming. And luckily they’re fairly inexpensive. I think that’s the way it’ll happen at, you know, when a lot of new technologies roll out, they are pretty expensive and then only the wealthy can have access to it. But the hope is that as the wealthy uses these and shows it has utility, then the price drops and they get out to everyone. Certainly that’s how genome sequencing started. And I think it will be true for a lot of these other technologies. Luckily, smartwatches are pretty cheap to begin with. So even a hundred-dollar smartwatch is a pretty powerful health device, I would argue.
Harry Glorikian: Yeah. I mean, you know, if, if Illumina achieves its $60, right, for the function—I’ve been looking at an analytics approach that will bring down whole genome sequencing to $60. So if it’s $60 to do the actual work, the wet chemistry, and then $60 to do the analysis, I don’t think there’s many barriers in the way anymore.
Michael Snyder: Yeah,totally, and we’re not so far away where people will they’ll get their genome sequenced, but now there are technologies to look for early cancer by sequencing DNA in blood, and you know
Harry Glorikian: Liquid biopsy.
Michael Snyder: So GRAIL and Gaurdant are leaders there. My company, Personalis is, I think, doing all right. So anyway, that’s a, those are areas that we think are going to be powerful and soon they’ll become routine tasks, once you show utility. But no company pays for it right now until you show that gee, you do this on healthy people and it doesn’t cost the company $5 billion to find three cases, which I won’t yeah, that then it’ll roll out.
So right now, and the way this works too, for the liquid biopsies, it’s looking for, they use it for cancer recurrence, if you’ve had cancer, you try and see if it’ll appear again. And that’s very logical. They’ll demonstrate utility there. They already are. And then soon it’ll be early detection and that’ll go to the high-risk families. And it always comes down to who pays and insurers won’t pay unless you’re at high risk generally. And then soon if it’s cheap enough, comes back to your point, if it’s cheap enough. It’ll be there for everybody.
Harry Glorikian: Yeah. I have this vision that you’re going to go into your CVS or your Walgreens and you, you know, once a year or whatever, and we’re going to see things so early that, I’m hoping one day in my lifetime that people will be like “Cancer. What, what, what, what happened?” Like you were able to get so far ahead of it, that it stops becoming an issue.
Michael Snyder: “What do you mean you detected cancer only when you saw this giant lump what’s that all about?”
Harry Glorikian: Yes, exactly. Exactly.
Michael Snyder: Yeah. I’m a hundred percent with you. Yeah.
Harry Glorikian: So let’s say we start, I mean, implementing this at a much larger scale, and broader than what we have now, because I think you and I are probably way ahead of a lot of others on these things. But do you see that effecting a longer life, or do you see it—like, I’m trying to weigh healthspan and lifespan, right?
Michael Snyder: Well, it’s all about healthspan, yeah. It’s all about healthspan. You want to extend the healthy life. You don’t want people hanging on in miserable fashion for years. I think anyway, that’s, that’s my own view and I think it’ll definitely extend healthspan because you’ll catch things while people are healthy, not once they’re ill, and then you take corrective action and keep them healthy. I think it’ll totally extend the healthspan. And the goal is to do that. You know, you want have people that have held a healthy life and then just die. That’s how it should go.
Harry Glorikian: That’s yes. My, my grandmother used to say that when I was younger and I thought it was morbid. And then now as I’ve gotten older, I’m like, Nope, Nope. That’s, that’s a good way to go. Like if you’re just going to go go,
Michael Snyder: Yeah, I think so too. We all know cases where people say, well, at least they died quickly. And we all know cases where somebody is hung on for three years and a lot of pain and very miserable fashion. And I don’t, again, at least my own personal view is that that’s just certainly not what I want. And those probably should be personal decisions, but minimally, regardless, everything we’ve been talking about should extend the healthspan, catch things while people are healthy, see these trajectories heading in a bad direction and then take corrective action. And that will have the desired impact.
Harry Glorikian: So, one, one final question, before we go. Who do you think is going to drive that? Is it going to be the healthcare life sciences world, or is it going to be the technology world? That’s quickly encroaching. Cause it’s, it’s not Pfizer that’s making this device on my wrist, right? It’s, you know, all the other companies you can name.
Michael Snyder: Yeah, no, I think it’s kind of, ideally it would involve everybody partnering together, but you’re right. Technology is having a big impact because consumers are eager for this information, as they often are. And especially as the word gets out and people like you and me start, you know, espousing the wonders and the power of those, these technologies.
So I think there’s that part. I do think we’ve got to get all the shareholders aligned, meaning I think employers as well should be big incentivizers of this. Meaning it pays for them to have their employees healthy. And that could be a plan I offer. If you’re a big employer, maybe you have your folks enroll in one of these, you know, preventative plans, a hundred bucks a month, keep them healthy. You save a lot of money. I do think it helps to incentivize the users as well. I think people are often lazy. But they’re, they’re all concerned about their pocketbook and their loved ones.
So I think the two ways to incentivize people are give them, you know, discounts on their insurance if they walk their 10,000 steps and you got to come up with ways for them not to cheat or, or do various things. But I, I do think that will help. Or you relay their family members who like egg them on a bit. It’s because sometimes that’s very incentivizing. So I think we need, we need to have good incentive ways to do that.
I think financial incentives are one of the better ones. And again, that can relay back to the employer. The employer can offer these plans and then give people bonuses if they do, they’re supposed to, you know, if you, if you are overweight and lose weight you know, maybe that would, well, you don’t want to be able to get overweight and then lose weight, but you want to incentivize people to lose weight.
Anyway, you come up with the right models for incentivizing folks. So, so we need to get the financial models in place. We need to show the stuff works and the technology is going to keep improving, getting cheaper, et cetera. So it’s all going to go together, I think, in parallel. And then people like you and me will be out there saying, man, this is amazing. Everybody should be doing this sort of stuff.
Harry Glorikian: I say it now. It’s just tough to get everybody on board.
Michael Snyder: Yeah. People are still scared. Yeah. But that’ll go away.
Harry Glorikian: I hope so. I hope that physicians get less scared. That’s my biggest hope.
Michael Snyder: Yeah. We’ve got to educate them. And those folks, you have to show that it works, that it has power. But they do have these refresher classes, they call them continuing medical education, and a lot of physicians do that. And I think it’s a great way. I give a lot of talks at those, as a way to try to, I think, at least show the potential of what we’re trying to do. And I think some of them buy it and some of them don’t.
Harry Glorikian: Yeah. And, and, you know, I think it needs to be integrated into their technological solutions to make it easier for them to sort of absorb it. And the current systems suck.
Michael Snyder: That’s true. Very true. Yeah. Yeah. They say, well, how do I have time to learn this and know if it’s working, I’m too busy taking care of my patients. Yeah. Your point’s well taken.
Harry Glorikian: So great to speak to you. I look forward to continuing to read all the stuff that you produce and all these amazing, you know, technologies that you’re constantly prolifically seem to be putting out there. And I’ll let you know when the, when the, when my book is out,
Michael Snyder: I definitely want to see it. Thank you.
Harry Glorikian: Take care. Bye-bye.
FAQs about health data
What are the main sources of health data?
The main sources of health data include:
- Electronic Health Records (EHRs): Detailed records of an individual’s medical history, treatments, and outcomes stored in a digital format.
- Wearable Devices: Devices such as fitness trackers and smartwatches that collect data on an individual’s physical activity, heart rate, and sleep patterns.
- Clinical Trials: Controlled studies that collect data on the safety and effectiveness of medical treatments and interventions.
- Surveys: Self-reported information on health behaviors, conditions, and outcomes collected through questionnaires or interviews.
- Administrative Data: Data from healthcare claims, billing records, and other administrative sources that provide information on utilization, cost, and outcomes of healthcare services.
- Public Health Surveillance Systems: Systems that collect data on infectious diseases, foodborne illnesses, and other public health threats.
- Laboratories: Data from laboratory tests and scans, such as blood tests, imaging studies, and genetic tests.
These sources of health data can be combined to provide a comprehensive view of an individual’s health, which can be used for various purposes, including clinical decision making, research, and population health management.
What is the use of data in healthcare?
Data is used in healthcare for several purposes, including:
- Clinical decision making: Health data can be used by healthcare providers to inform diagnoses, treatment plans, and to monitor the effectiveness of treatments.
- Research: Health data can be analyzed to gain insights into disease trends, risk factors, and the effectiveness of medical interventions.
- Population health management: Health data can be used to track the health of populations, identify health disparities, and allocate resources where they are needed most.
- Quality improvement: Health data can be used to monitor and improve the quality of healthcare delivery, patient safety, and outcomes.
- Personalized medicine: Health data can be used to tailor treatment plans to the unique needs and characteristics of individual patients.
- Fraud detection: Health data can be used to detect and prevent fraud, waste, and abuse in the healthcare system.
- Public health surveillance: Health data can be used to track the spread of infectious diseases and other public health threats, and to implement effective public health interventions.
In summary, data plays a critical role in healthcare by providing valuable information for decision-making, improving the quality of care, advancing medical knowledge, and promoting public health.