Personalized nutrition apps could provide valuable data to people trying to eat healthier, though more research must be done to show effectiveness.
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.”
In 2015, about a year before he was diagnosed with terminal lung cancer, John Vlahos posed for a picture with his son, James.
In 2016, when my family found out that my father was dying from cancer, I did something that at the time felt completely obvious: I started building a chatbot replica of him.
I simply wanted to create an interactive way to share key parts of his life story.
I was not under any delusion that the Dadbot, as I soon began calling it, would be a true avatar of him. From my research about the voice computing revolution—Siri, Alexa, the Google Assistant—I knew that fully humanlike AIs, like you see in the movies, were a vast ways from technological reality. Replicating my dad in any real sense was never the goal, anyway; that notion gave me the creeps.
Instead, I simply wanted to create an interactive way to share key parts of his life story: facts about his ancestors in Greece. Memories from growing up. Stories about his hobbies, family life, and career. And I wanted the Dadbot, which sent text messages and audio clips over Facebook Messenger, to remind me of his personality—warm, erudite, and funny. So I programmed it to use his distinctive phrasings; to tell a few of his signature jokes and sing his favorite songs.
While creating the Dadbot, a laborious undertaking that sprawled into 2017, I fixated on two things. The first was getting the programming right, which I did using a conversational agent authoring platform called PullString. The second, far more wrenching concern was my father's health. Failing to improve after chemotherapy and immunotherapy, and steadily losing energy, weight, and the animating sparkle of life, he died on February 9.
John Vlahos at a family reunion in the summer of 2016, a few months after his cancer diagnosis.
(Courtesy James Vlahos)
After a magazine article that I wrote about the Dadbot came out in the summer of 2017, messages poured in from readers. While most people simply expressed sympathy, some conveyed a more urgent message: They wanted their own memorializing chatbots. One man implored me to make a bot for him; he had been diagnosed with cancer and wanted his six-month-old daughter to have a way to remember him. A technology entrepreneur needed advice on replicating what I did for her father, who had stage IV cancer. And a teacher in India asked me to engineer a conversational replica of her son, who had recently been struck and killed by a bus.
Journalists from around the world also got in touch for interviews, and they inevitably came around to the same question. Will virtual immortality, they asked, ever become a business?
The prospect of this happening had never crossed my mind. I was consumed by my father's struggle and my own grief. But the notion has since become head-slappingly obvious. I am not the only person to confront the loss of a loved one; the experience is universal. And I am not alone in craving a way to keep memories alive. Of course people like the ones who wrote me will get Dadbots, Mombots, and Childbots of their own. If a moonlighting writer like me can create a minimum viable product, then a company employing actual computer scientists could do much more.
But this prospect raises unanswered and unsettling questions. For businesses, profit, and not some deeply personal mission, will be the motivation. This shift will raise issues that I didn't have to confront. To make money, a virtual immortality company could follow the lucrative but controversial business model that has worked so well for Google and Facebook. To wit, a company could provide the memorializing chatbot for free and then find ways to monetize the attention and data of whoever communicated with it. Given the copious amount of personal information flowing back and forth in conversations with replica bots, this would be a data gold mine for the company—and a massive privacy risk for users.
Virtual immortality as commercial product will doubtless become more sophisticated.
Alternately, a company could charge for memorializing avatars, perhaps with an annual subscription fee. This would put the business in a powerful position. Imagine the fee getting hiked each year. A customer like me would find himself facing a terrible decision—grit my teeth and keep paying, or be forced to pull the plug on the best, closest reminder of a loved one that I have. The same person would effectively wind up dying twice.
Another way that a beloved digital avatar could die is if the company that creates it ceases to exist. This is no mere academic concern for me: Earlier this year, PullString was swallowed up by Apple. I'm still able to access the Dadbot on my own computer, fortunately, but the acquisition means that other friends and family members can no longer chat with him remotely.
Startups like PullString, of course, are characterized by impermanence; they tend to get snapped up by bigger companies or run out of venture capital and fold. But even if big players like, say, Facebook or Google get into the virtual immortality game, we can't count on them existing even a few decades from now, which means that the avatars enabled by their technology would die, too.
The permanence problem is the biggest hurdle faced by the fledgling enterprise of virtual immortality. So some entrepreneurs are attempting to enable avatars whose existence isn't reliant upon any one company or set of computer servers. "By leveraging the power of blockchain and decentralized software to replicate information, we help users create avatars that live on forever," says Alex Roy, the founder and CEO of the startup Everlife.ai. But until this type of solution exists, give props to conventional technology for preserving memories: printed photos and words on paper can last for centuries.
The fidelity of avatars—just how lifelike they are—also raises serious concerns. Before I started creating the Dadbot, I worried that the tech might be just good enough to remind my family of the man it emulated, but so far off from my real father that it gave us all the creeps. But because the Dadbot was a simple chatbot and not some all-knowing AI, and because the interface was a messaging app, there was no danger of him encroaching on the reality of my actual dad.
But virtual immortality as commercial product will doubtless become more sophisticated. Avatars will have brains built by teams of computer scientists employing the latest techniques in conversational AI. The replicas will not just text but also speak, using synthetic voices that emulate the ones of the people being memorialized. They may even come to life as animated clones on computer screens or in 3D with the help of virtual reality headsets.
What fascinates me is how technology can help to preserve the past—genuine facts and memories from peoples' lives.
These are all lines that I don't personally want to cross; replicating my dad was never the goal. I also never aspired to have some synthetic version of him that continued to exist in the present, capable of acquiring knowledge about the world or my life and of reacting to it in real time.
Instead, what fascinates me is how technology can help to preserve the past—genuine facts and memories from people's lives—and their actual voices so that their stories can be shared interactively after they have gone. I'm working on ideas for doing this via voice computing platforms like Alexa and Assistant, and while I don't have all of the answers yet, I'm excited to figure out what might be possible.
[Adapted from Talk to Me: How Voice Computing Will Transform the Way We Live, Work, and Think (Houghton Mifflin Harcourt, March 26, 2019).]
