AI and you: Is the promise of personalized nutrition apps worth the hype?
As a type 2 diabetic, Michael Snyder has long been interested in how blood sugar levels vary from one person to another in response to the same food, and whether a more personalized approach to nutrition could help tackle the rapidly cascading levels of diabetes and obesity in much of the western world.
Eight years ago, Snyder, who directs the Center for Genomics and Personalized Medicine at Stanford University, decided to put his theories to the test. In the 2000s continuous glucose monitoring, or CGM, had begun to revolutionize the lives of diabetics, both type 1 and type 2. Using spherical sensors which sit on the upper arm or abdomen – with tiny wires that pierce the skin – the technology allowed patients to gain real-time updates on their blood sugar levels, transmitted directly to their phone.
It gave Snyder an idea for his research at Stanford. Applying the same technology to a group of apparently healthy people, and looking for ‘spikes’ or sudden surges in blood sugar known as hyperglycemia, could provide a means of observing how their bodies reacted to an array of foods.
“We discovered that different foods spike people differently,” he says. “Some people spike to pasta, others to bread, others to bananas, and so on. It’s very personalized and our feeling was that building programs around these devices could be extremely powerful for better managing people’s glucose.”
Unbeknown to Snyder at the time, thousands of miles away, a group of Israeli scientists at the Weizmann Institute of Science were doing exactly the same experiments. In 2015, they published a landmark paper which used CGM to track the blood sugar levels of 800 people over several days, showing that the biological response to identical foods can vary wildly. Like Snyder, they theorized that giving people a greater understanding of their own glucose responses, so they spend more time in the normal range, may reduce the prevalence of type 2 diabetes.
The commercial potential of such apps is clear, but the underlying science continues to generate intriguing findings.
“At the moment 33 percent of the U.S. population is pre-diabetic, and 70 percent of those pre-diabetics will become diabetic,” says Snyder. “Those numbers are going up, so it’s pretty clear we need to do something about it.”
Fast forward to 2022,and both teams have converted their ideas into subscription-based dietary apps which use artificial intelligence to offer data-informed nutritional and lifestyle recommendations. Snyder’s spinoff, January AI, combines CGM information with heart rate, sleep, and activity data to advise on foods to avoid and the best times to exercise. DayTwo–a start-up which utilizes the findings of Weizmann Institute of Science–obtains microbiome information by sequencing stool samples, and combines this with blood glucose data to rate ‘good’ and ‘bad’ foods for a particular person.
“CGMs can be used to devise personalized diets,” says Eran Elinav, an immunology professor and microbiota researcher at the Weizmann Institute of Science in addition to serving as a scientific consultant for DayTwo. “However, this process can be cumbersome. Therefore, in our lab we created an algorithm, based on data acquired from a big cohort of people, which can accurately predict post-meal glucose responses on a personal basis.”
The commercial potential of such apps is clear. DayTwo, who market their product to corporate employers and health insurers rather than individual consumers, recently raised $37 million in funding. But the underlying science continues to generate intriguing findings.
Last year, Elinav and colleagues published a study on 225 individuals with pre-diabetes which found that they achieved better blood sugar control when they followed a personalized diet based on DayTwo’s recommendations, compared to a Mediterranean diet. The journal Cell just released a new paper from Snyder’s group which shows that different types of fibre benefit people in different ways.
“The idea is you hear different fibres are good for you,” says Snyder. “But if you look at fibres they’re all over the map—it’s like saying all animals are the same. The responses are very individual. For a lot of people [a type of fibre called] arabinoxylan clearly reduced cholesterol while the fibre inulin had no effect. But in some people, it was the complete opposite.”
Eight years ago, Stanford's Michael Snyder began studying how continuous glucose monitors could be used by patients to gain real-time updates on their blood sugar levels, transmitted directly to their phone.
The Snyder Lab, Stanford Medicine
Because of studies like these, interest in precision nutrition approaches has exploded in recent years. In January, the National Institutes of Health announced that they are spending $170 million on a five year, multi-center initiative which aims to develop algorithms based on a whole range of data sources from blood sugar to sleep, exercise, stress, microbiome and even genomic information which can help predict which diets are most suitable for a particular individual.
“There's so many different factors which influence what you put into your mouth but also what happens to different types of nutrients and how that ultimately affects your health, which means you can’t have a one-size-fits-all set of nutritional guidelines for everyone,” says Bruce Y. Lee, professor of health policy and management at the City University of New York Graduate School of Public Health.
With the falling costs of genomic sequencing, other precision nutrition clinical trials are choosing to look at whether our genomes alone can yield key information about what our diets should look like, an emerging field of research known as nutrigenomics.
The ASPIRE-DNA clinical trial at Imperial College London is aiming to see whether particular genetic variants can be used to classify individuals into two groups, those who are more glucose sensitive to fat and those who are more sensitive to carbohydrates. By following a tailored diet based on these sensitivities, the trial aims to see whether it can prevent people with pre-diabetes from developing the disease.
But while much hope is riding on these trials, even precision nutrition advocates caution that the field remains in the very earliest of stages. Lars-Oliver Klotz, professor of nutrigenomics at Friedrich-Schiller-University in Jena, Germany, says that while the overall goal is to identify means of avoiding nutrition-related diseases, genomic data alone is unlikely to be sufficient to prevent obesity and type 2 diabetes.
“Genome data is rather simple to acquire these days as sequencing techniques have dramatically advanced in recent years,” he says. “However, the predictive value of just genome sequencing is too low in the case of obesity and prediabetes.”
Others say that while genomic data can yield useful information in terms of how different people metabolize different types of fat and specific nutrients such as B vitamins, there is a need for more research before it can be utilized in an algorithm for making dietary recommendations.
“I think it’s a little early,” says Eileen Gibney, a professor at University College Dublin. “We’ve identified a limited number of gene-nutrient interactions so far, but we need more randomized control trials of people with different genetic profiles on the same diet, to see whether they respond differently, and if that can be explained by their genetic differences.”
Some start-ups have already come unstuck for promising too much, or pushing recommendations which are not based on scientifically rigorous trials. The world of precision nutrition apps was dubbed a ‘Wild West’ by some commentators after the founders of uBiome – a start-up which offered nutritional recommendations based on information obtained from sequencing stool samples –were charged with fraud last year. The weight-loss app Noom, which was valued at $3.7 billion in May 2021, has been criticized on Twitter by a number of users who claimed that its recommendations have led to them developed eating disorders.
With precision nutrition apps marketing their technology at healthy individuals, question marks have also been raised about the value which can be gained through non-diabetics monitoring their blood sugar through CGM. While some small studies have found that wearing a CGM can make overweight or obese individuals more motivated to exercise, there is still a lack of conclusive evidence showing that this translates to improved health.
However, independent researchers remain intrigued by the technology, and say that the wealth of data generated through such apps could be used to help further stratify the different types of people who become at risk of developing type 2 diabetes.
“CGM not only enables a longer sampling time for capturing glucose levels, but will also capture lifestyle factors,” says Robert Wagner, a diabetes researcher at University Hospital Düsseldorf. “It is probable that it can be used to identify many clusters of prediabetic metabolism and predict the risk of diabetes and its complications, but maybe also specific cardiometabolic risk constellations. However, we still don’t know which forms of diabetes can be prevented by such approaches and how feasible and long-lasting such self-feedback dietary modifications are.”
Snyder himself has now been wearing a CGM for eight years, and he credits the insights it provides with helping him to manage his own diabetes. “My CGM still gives me novel insights into what foods and behaviors affect my glucose levels,” he says.
He is now looking to run clinical trials with his group at Stanford to see whether following a precision nutrition approach based on CGM and microbiome data, combined with other health information, can be used to reverse signs of pre-diabetes. If it proves successful, January AI may look to incorporate microbiome data in future.
“Ultimately, what I want to do is be able take people’s poop samples, maybe a blood draw, and say, ‘Alright, based on these parameters, this is what I think is going to spike you,’ and then have a CGM to test that out,” he says. “Getting very predictive about this, so right from the get go, you can have people better manage their health and then use the glucose monitor to help follow that.”
The "Making Sense of Science" podcast features interviews with leading experts about health innovations and the ethical questions they raise. The podcast is hosted by Matt Fuchs, editor of Leaps.org, the award-winning science outlet.
My guest today is Nanea Reeves, the CEO of TRIPP, a wellness platform with some big differences from meditation apps you may have tried like Calm and Headspace. TRIPP's experiences happen in virtual reality, and its realms are designed based on scientific findings about states of mindfulness. Users report feelings of awe and wonder and even mystical experiences. Nanea brings over 15 years of leadership in digital distribution, apps and video game technologies. Before co-founding TRIPP, she had several other leadership roles in tech with successful companies like textPlus and Machinima. Read her full bio below in the links section.
Nanea Reeves, CEO of TRIPP.
TRIPP
Listen to the Episode
Listen on Apple | Listen on Spotify | Listen on Stitcher | Listen on Amazon | Listen on Google
This conversation coincided with National Brain Awareness Week. The topic is a little different from the Making Sense of Science podcast’s usual focus on breakthroughs in treating and preventing disease, but there’s a big overlap when it comes to breakthroughs in optimal health. Nanea’s work is at the leading edge of health, technology and the science of wellness.
With TRIPP, you might find yourself deep underwater, looking up at the sunlight shimmering on the ocean surface, or in the cosmos staring down at a planet glowing with an arresting diversity of colors. Using TRIPP for the past six months has been a window for me into the future of science-informed wellness and an overall fascinating experience, as was my conversation with Nanea.
Show notes:
Nanea and I discuss her close family members' substance addictions and her own struggle with mental illness as a teen, which led to her first meditation experiences, and much more:
- The common perception that technology is an obstacle for mental well-being, a narrative that overlooks how tech can also increase wellness when it’s designed right.
- Emerging ways of measuring meditation experiences by recording brain waves - and the shortcomings of the ‘measured self’ movement.
- Why TRIPP’s users multiplied during the stress and anxiety of the pandemic, and how TRIPP can can be used to enhance emotional states.
- Ways in which TRIPP’s visuals and targeted sound frequencies have been informed by innovative research from psychologists like Johns Hopkins’ Matthew Johnson.
- Ways to design apps and other technologies to better fulfill the true purpose of mindfulness meditation. (Hint: not simply relaxation.)
- And of course, because the topic is mental wellness and tech, I had to get Nanea's thoughts on Elon Musk, Neuralink and brain machine interfaces.
Here are links for learning more about TRIPP:
- TRIPP website: https://www.tripp.com/about/
- Nanea Reeves bio: https://www.tripp.com/team/nanea-reeves/
- Study of data collected by UK's Office for National Statistics on behavior during the pandemic, which suggests that TRIPP enhanced users' psychological and emotional mindsets: https://link.springer.com/chapter/10.1007/978-3-03...
- Research that's informed TRIPP: https://www.tripp.com/research/
- Washington Post Top Pick at CES: https://www.washingtonpost.com/technology/2019/01/...
- TRIPP's new offering, PsyAssist, to provide support for ketamine-assisted therapy: https://www.mobihealthnews.com/news/tripp-acquires...
- Randomized pilot trial involving TRIPP: https://bmjopen.bmj.com/content/bmjopen/11/4/e0441...
This month, Leaps.org had a chance to speak with Holden Thorp, Editor-in-Chief of the Science family of journals. We talked about the best ways to communicate science to the public, mistakes by public health officials during the pandemic, the lab leak theory, and bipartisanship for funding science research.
Before becoming editor of the Science journals, Thorp spent six years as provost of Washington University in St. Louis, where he is Rita Levi-Montalcini Distinguished University Professor and holds appointments in both chemistry and medicine. He joined Washington University after spending three decades at the University of North Carolina at Chapel Hill, where he served as the UNC's 10th chancellor from 2008 through 2013.
A North Carolina native, Thorp earned a doctorate in chemistry in 1989 at the California Institute of Technology and completed postdoctoral work at Yale University. He is a fellow of the National Academy of Inventors and the American Association for the Advancement of Science.
Read his full bio here.
This conversation was lightly edited by Leaps.org for style and format.
Matt Fuchs: You're a musician. It seems like many scientists are also musicians. Is there a link between the scientist brain and the musician brain?
Holden Thorp: I think [the overlap is] relatively common. I'm still a gigging bass player. I play in the pits for lots of college musicals. I think that it takes a certain discipline and requires you to learn a lot of rules about how music works, and then you try to be creative within that. That's similar to scientific research. So it makes sense. Music is something I've been able to sustain my whole life. I wouldn't be the same person if I let it go. When you're playing, especially for a musical, where the music is challenging, you can't let your mind wander. It’s like meditation.
MF: I bet it helps to do something totally different from your editing responsibilities. Maybe lets the subconscious take care of tough problems at work.
HT: Right.
MF: There's probably never been a greater need for clear and persuasive science communicators. Do we need more cross specialty training? For example, journalism schools prioritizing science training, and science programs that require more time learning how to communicate effectively?
HT: I think we need both. One of the challenges we've had with COVID has been, especially at the beginning, a lot of reporters who didn’t normally cover scientific topics got put on COVID—and ended up creating things that had to be cleaned up later. This isn't the last science-oriented crisis we're going to have. We've already got climate change, and we'll have another health crisis for sure. So it’d be good for journalism to be a little better prepared next time.
"Scientists are human beings who have ego and bravado and every other human weakness."
But on the other side, maybe it's even more important that scientists learn how to communicate and how likely it is that their findings will be politicized, twisted and miscommunicated. Because one thing that surprised me is how shocked a lot of scientists have been. Every scientific issue that reaches into public policy becomes politicized: climate change, evolution, stem cells.
Once one side decided to be cautious about the pandemic, you could be certain the other side was going to decide not to do that. That's not the fault of science. That’s just life in a political world. That, I think, caught people off guard. They weren't prepared to shape and process their messages in a way that accounted for that—and for the way that social media has intensified all of this.
MF: Early in the pandemic, there was a lack of clarity about public health recommendations, as you’d expect with a virus we hadn’t seen before. Should public officials and scientists have more humility in similar situations in the future? Public officials need to be authoritative for their guidance to be followed, so how do they lead a crisis response while displaying humility about what we don't know?
HS: I think scientists are people who like to have the answer. It's very tempting and common for scientists to kind of oversell what we know right now, while not doing as much as we should to remind people that science is a self-correcting process. And when we fail to do that – after we’ve collected more data and need to change how we're interpreting it – the people who want to undermine us have a perfect weapon to use against us. It's challenging. But I agree that scientists are human beings who have ego and bravado and every other human weakness.
For example, we wanted to tell everybody that we thought the vaccines would provide sterilizing immunity against infection. Well, we don't have too many other respiratory viruses where that's the case. And so it was more likely that we were going to have what we ended up with, which is that the vaccines were excellent in preventing severe disease and death. It would have been great if they provided sterilizing immunity and abruptly ended the pandemic a year ago. But it was overly optimistic to think that was going to be the case in retrospect.
MF: Both in terms of how science is communicated and received by the public, do we need to reform institutions or start new ones to instill the truth-seeking values that are so important to appreciating science?
HS: There are a whole bunch of different factors. I think the biggest one is that the social media algorithms reward their owners financially when they figure out how to keep people in their silos. Users are more likely to click on things that they agree with—and that promote conflict with people that they disagree with. That has caused an acceleration in hostilities that attend some of these disagreements.
But I think the other problem is that we haven’t found a way to explain things to people when it’s not a crisis. So, for example, a strong indicator of whether someone who might otherwise be vaccine hesitant decided to get their vaccine is if they understood how vaccines worked before the pandemic started. Because if you're trying to tell somebody that they're wrong if they don't get a vaccine, at the same time you're trying to explain how it works, that's a lot of explaining to do in a short period of time.
Lack of open-mindedness is a problem, but another issue is that we need more understanding of these issues baked into the culture already. That's partly due the fact that there hasn't been more reform in K through 12 and college teaching. And that scientists are very comfortable talking to each other, and not very comfortable talking to people who don't know all of our jargon and have to be persuaded to spend time listening to and thinking about what we're trying to tell them.
"We're almost to the point where clinging to the lab leak idea is close to being a fringe idea that almost doesn't need to be included in stories."
MF: You mentioned silos. There have been some interesting attempts in recent years to do “both sides journalism,” where websites like AllSides put different views on high profile issues side-by-side. Some people believe that's how the news should be reported. Should we let people see and decide for themselves which side is the most convincing?
HS: It depends if we're talking about science. On scientific issues, when they start, there's legitimate disagreement about among scientists. But eventually, things go back and forth, and people compete with each other and work their way to the answer. At some point, we reach more of a consensus.
For example, on climate change, I think it's gotten to the point now where it's irresponsible, if you're writing a story about climate change, to run a quote from somebody somewhere who's still—probably because of their political views—clinging to the idea that anthropogenic global warming is somehow not damaging the planet.
On things that aren't decided yet, that makes sense to run both. It's more a question of judgment of the journalists. I don't think the solution to it is put stark versions of each side, side-by-side and let people choose. The whole point of journalism is to inform people. If there's a consensus on something, that's part of what you're supposed to be informing them about.
MF: What about reporting on perspectives about the lab leak theory at various times during the pandemic?
HS: We’re the outlet that ran the letter that really restarted the whole debate. A bunch of well-known scientists said we should consider the lab leak theory more carefully. And in the aftermath of that, a bunch of those scientists who signed that letter concluded that the lab leak was very, very unlikely. Interestingly, publishing that letter actually drove us to more of a consensus. I would say now, we're almost to the point where clinging to the lab leak idea is close to being a fringe idea that almost doesn't need to be included in stories. But I would say there's been a lot of evolution on that over the last year since we ran that letter.
MF: Let's talk about bipartisanship in Congress. Research funding for the National Institutes of Health was championed for years by influential Republicans who supported science to advance health breakthroughs. Is that changing? Maybe especially with Sen. Roy Blunt retiring? Has bipartisanship on science funding been eroded by political battles during COVID?
HS: I'm optimistic that that won't be the case. Republican Congresses have usually been good for science funding. And that's because (former Sen.) Arlen Specter and Roy Blunt are two of the political figures who have pushed for science funding over the last couple decades. With Blunt retiring, we don't know who's going to step in for him. That's an interesting question. I hope there will be Republican champions for science funding.
MF: Is there too much conservatism baked into how we research new therapies and bring them to people who are sick, bench-to-bedside? I'm thinking of the criticisms that NIH or the FDA are overly bureaucratic. Are you hopeful about ARPA-H, President Biden’s proposed new agency for health innovation?
HS: I think the challenge hasn't been cracked by the federal government. Maybe DARPA has done this outside of health science, but within health science, the federal government has had limited success at funding things that can be applied quickly, while having overwhelming success at funding basic research that eventually becomes important in applications. Can they do it the other way around? They’ll need people running ARPA-H who are application first. It’s ambitious. The way it was done in Operation Warp Speed is all the money was just given to the companies. If the hypothesis on ARPA-H is for the federal government to actually do what Moderna and BioNTech did for the vaccine, themselves, that's a radical idea. It's going to require thinking very differently than the way they think about dispersing grants for basic research.
MF: You’ve written a number of bold op-eds as editor of the Science journals. Are there any op-eds you're especially proud of as voicing a view that was important but not necessarily popular?
HS: I was one of the first people to come out hard against President Trump['s handling of] the pandemic. Lots of my brothers and sisters came along afterwards. To the extent that I was able to catalyze that, I'm proud of doing it. In the last few weeks, I published a paper objecting to the splitting of the OSTP director from the science advisor and, especially, not awarding the top part of the job to Alondra Nelson, who is a distinguished scientist at black female. And instead, giving part of it to Francis Collins. He’s certainly the most important science policy figure of my lifetime, but somebody who’s been doing this now for decades. I just think we have to push as hard as we can to get a cadre of young people leading us in Washington who represent the future of the country. I think the Biden administration leaned on a lot of figures from the past. I’m pushing them hard to try to stop it.
MF: I want to circle back to the erosion of the public’s trust in experts. Most experts are specialists, and specialists operate in silos that don’t capture the complexity of scientific knowledge. Are some pushbacks to experts and concerns about the perils of specialization valid?
HS: You're on the right track there. What we need is more respect for the generalist. We can't help the fact that you have to be very specialized to do a lot of stuff. But what we need is more partnership between specialists and people who can cross fields, especially into communication and social sciences. That handoff is just not really there right now. It's hard to get a hardcore scientist to respect people who are interested in science, education and science communication, and to treat them as equals. The last two years showed that they're at least as important, if not more so.
MF: I’m grateful that you’re leading the way in this area, Holden. Thank you for sharing your thoughts and your work.