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.”
New Podcast: Dr. Gigi Gronvall Addresses the Risk of Delta and COVID-19’s Possible Origins
"Making Sense of Science" is a monthly podcast that features interviews with leading medical and scientific experts about the latest developments and the big ethical and societal questions they raise. This episode is hosted by science and biotech journalist Emily Mullin, summer editor of the award-winning science outlet Leaps.org.
Listen to the episode:
Why Neglected Tropical Diseases Should Matter to Americans
Daisy Hernández was five years old when one of her favorite aunts was struck with a mysterious illness. Tía Dora had stayed behind in Colombia when Daisy's mother immigrated to Union City, New Jersey. A schoolteacher in her late 20s, she began suffering from fevers and abdominal pain, and her belly grew so big that people thought she was pregnant. Exploratory surgery revealed that her large intestine had swollen to ten times its normal size, and she was fitted with a colostomy bag. Doctors couldn't identify the underlying problem—but whatever it was, they said, it would likely kill her within a year or two.
Tía Dora's sisters in New Jersey—Hernández's mother and two other aunts—weren't about to let that happen. They pooled their savings and flew her to New York City, where a doctor at Columbia-Presbyterian Medical Center with a penchant for obscure ailments provided a diagnosis: Chagas disease. Transmitted by the bite of triatomine insects, commonly known as kissing bugs, Chagas is endemic in many parts of Latin America. It's caused by the parasite Trypanoma cruzi, which usually settles in the heart, where it feeds on muscle tissue. In some cases, however, it attacks the intestines or esophagus. Tía Dora belonged to that minority.
In 1980, U.S. immigration laws were more forgiving than they are today. Tía Dora was able to have surgery to remove a part of her colon, despite not being a citizen or having a green card. She eventually married a legal resident and began teaching Spanish at an elementary school. Over the next three decades, she earned a graduate degree, built a career, and was widowed. Meanwhile, Chagas continued its slow devastation. "Every couple of years, we were back in the hospital with her," Hernández recalls. "When I was in high school, she started feeling like she couldn't swallow anything. It was the parasite, destroying the muscles of her esophagus."
When Tía Dora died in 2010, at 59, her niece was among the family members at her bedside. By then, Hernández had become a journalist and fiction writer. Researching a short story about Chagas disease, she discovered that it affected an estimated 6 million people in South America, Central America, and Mexico—as well as 300,000 in the United States, most of whom were immigrants from those places. "I was shocked to learn it wasn't rare," she says. "That made me hungry to know more about this disease, and about the families grappling with it."
Hernández's curiosity led her to write The Kissing Bug, a lyrical hybrid of memoir and science reporting that was published in June. It also led her to another revelation: Chagas is not unique. It's among the many maladies that global health experts refer to as neglected tropical diseases—often-disabling illnesses that afflict 1.7 billion people worldwide, while getting notably less attention than the "big three" of HIV/AIDs, malaria, and tuberculosis. NTDs cause fewer deaths than those plagues, but they wreak untold suffering and economic loss.
Shortly before Hernández's book hit the shelves, the World Health Organization released its 2021-2030 roadmap for fighting NTDs. The plan sets targets for controlling, eliminating, or eradicating all the diseases on the WHO's list, through measures ranging from developing vaccines to improving healthcare infrastructure, sanitation, and access to clean water. Experts agree that for the campaign to succeed, leadership from wealthy nations—particularly the United States—is essential. But given the inward turn of many such countries in recent years (evidenced in movements ranging from America First to Brexit), and the continuing urgency of the COVID-19 crisis, public support is far from guaranteed.
As Hernández writes: "It is easier to forget a disease that cannot be seen." NTDs primarily affect residents of distant lands. They kill only 80,000 people a year, down from 204,000 in 1990. So why should Americans to bother to look?
Breaking the circle of poverty and disease
The World Health Organization counts 20 diseases as NTDs. Along with Chagas, they include dengue and chikungunya, which cause high fevers and agonizing pain; elephantiasis, which deforms victims' limbs and genitals; onchocerciasis, which causes blindness; schistosomiasis, which can damage the heart, lungs, brain, and genitourinary system; helminths such as roundworm and whipworm, which cause anemia, stunted growth, and cognitive disabilities; and a dozen more. Such ailments often co-occur in the same patient, exacerbating each other's effects and those of illnesses such as malaria.
NTDs may be spread by insects, animals, soil, or tainted water; they may be parasitic, bacterial, viral, or—in the case of snakebite envenoming—non-infectious. What they have in common is their longtime neglect by public health agencies and philanthropies. In part, this reflects their typically low mortality rates. But the biggest factor is undoubtedly their disempowered patient populations.
"These diseases occur in the setting of poverty, and they cause poverty, because of their chronic and debilitating effects," observes Peter Hotez, dean of the National School of Tropical Medicine at Baylor University and co-director of the Texas Children's Hospital for Vaccine Development. And historically, the everyday miseries of impoverished people have seldom been a priority for those who set the global health agenda.
That began to change about 20 years ago, when Hotez and others developed the conceptual framework for NTDs and early proposals for combating them. The WHO released its first roadmap in 2012, targeting 17 NTDs for control, elimination, or eradication by 2020. (Rabies, snakebite, and dengue were added later.) Since then, the number of people at risk for NTDs has fallen by 600 million, and 42 countries have eliminated at least one such disease. Cases of dracunculiasis—known as Guinea worm disease, for the parasite that creates painful blisters in a patient's skin—have dropped from the millions to just 27 in 2020.
Yet the battle is not over, and the COVID-19 pandemic has disrupted prevention and treatment programs around the globe.
A new direction — and longstanding obstacles
The WHO's new roadmap sets even more ambitious goals for 2030. Among them: reducing by 90 percent the number of people requiring treatment for NTDs; eliminating at least one NTD in another 100 countries; and fully eradicating dracunculiasis and yaws, a disfiguring skin infection.
The plan also places an increased focus on "country ownership," relying on nations with high incidence of NTDs to design their own plans based on local expertise. "I was so excited to see that," says Kristina Talbert-Slagle, director of the Yale College Global Health Studies program. "No one is a better expert on how to address these situations than the people who deal with it day by day."
Another fresh approach is what the roadmap calls "cross-cutting" targets. "One of the really cool things about the plan is how much it emphasizes coordination among different sectors of the health system," says Claire Standley, a faculty member at Georgetown University's Center for Global Health Science and Security. "For example, it explicitly takes into account the zoonotic nature of many neglected tropical diseases—the fact that we have to think about animal health as well as human health when we tackle NTDs."
Whether this grand vision can be realized, however, will depend largely on funding—and that, in turn, is a question of political will in the countries most able to provide it. On the upside, the U.S. has ended its Trump-era feud with the WHO. "One thing that's been really encouraging," says Standley, "has been the strong commitment toward global cooperation from the current administration." Even under the previous president, the U.S. remained the single largest contributor to the global health kitty, spending over $100 million annually on NTDs—six times the figure in 2006, when such financing started.
On the downside, America's outlay has remained flat for several years, and the Biden administration has so far not moved to increase it. A "back-of-the-envelope calculation," says Hotez, suggests that the current level of aid could buy medications for the most common NTDs for about 200 million people a year. But the number of people who need treatment, he notes, is at least 750 million.
Up to now, the United Kingdom—long the world's second-most generous health aid donor—has taken up a large portion of the slack. But the UK last month announced deep cuts in its portfolio, eliminating 102 previously supported countries and leaving only 34. "That really concerns me," Hotez says.
The struggle for funds, he notes, is always harder for projects involving NTDs than for those aimed at higher-profile diseases. His lab, which he co-directs with microbiologist Maria Elena Bottazzi, started developing a COVID-19 vaccine soon after the pandemic struck, for example, and is now in Phase 3 trials. The team has been working on vaccines for Chagas, hookworm, and schistosomiasis for much longer, but trials for those potential game-changers lag behind. "We struggle to get the level of resources needed to move quickly," Hotez explains.
Two million reasons to care
One way to prompt a government to open its pocketbook is for voters to clamor for action. A longtime challenge with NTDs, however, has been getting people outside the hardest-hit countries to pay attention.
The reasons to care, global health experts argue, go beyond compassion. "When we have high NTD burden," says Talbert-Slagle, "it can prevent economic growth, prevent innovation, lead to more political instability." That, in turn, can lead to wars and mass migration, affecting economic and political events far beyond an affected country's borders.
Like Hernández's aunt Dora, many people driven out of NTD-wracked regions wind up living elsewhere. And that points to another reason to care about these diseases: Some of your neighbors might have them. In the U.S., up to 14 million people suffer from neglected parasitic infections—including 70,000 with Chagas in California alone.
When Hernández was researching The Kissing Bug, she worried that such statistics would provide ammunition to racists and xenophobes who claim that immigrants "bring disease" or exploit overburdened healthcare systems. (This may help explain some of the stigma around NTDs, which led Tía Dora to hide her condition from most people outside her family.) But as the book makes clear, these infections know no borders; they flourish wherever large numbers of people lack access to resources that most residents of rich countries take for granted.
Indeed, far from gaming U.S. healthcare systems, millions of low-income immigrants can't access them—or must wait until they're sick enough to go to an emergency room. Since Congress changed the rules in 1996, green card holders have to wait five years before they can enroll in Medicaid. Undocumented immigrants can never qualify.
Closing the great divide
Hernández uses a phrase borrowed from global health crusader Paul Farmer to describe this access gap: "the great epi divide." On one side, she explains, "people will die from cancer, from diabetes, from chronic illnesses later in life. On the other side of the epidemiological divide, people are dying because they can't get to the doctor, or they can't get medication. They don't have a hospital anywhere near them. When I read Dr. Farmer's work, I realized how much that applied to neglected diseases as well."
When it comes to Chagas disease, she says, the epi divide is embodied in the lack of a federal mandate for prenatal or newborn screening. Each year, according to the Centers for Disease Control and Prevention, up to 300 babies in the U.S. are born with Chagas, which can be passed from the mother in utero. The disease can be cured with medication if treated in infancy. (It can also be cured in adults in the acute stage, but is seldom detected in time.) Yet the CDC does not require screening for Chagas—even though newborns are tested for 15 diseases that are less common. According to one study, it would be 10 times cheaper to screen and treat babies and their mothers than to cover the costs related to the illness in later years. Few states make the effort.
The gap that enables NTDs to persist, Hernández argues, is the same one that has led to COVID-19 death rates in Black and Latinx communities that are double those elsewhere in America. To close it, she suggests, caring is not enough.
"When I was working on my book," she says, "I thought about HIV in the '80s, when it had so much stigma that no one wanted to talk about it. Then activists stepped up and changed the conversation. I thought a lot about breast cancer, which was stigmatized for years, until people stepped forward and started speaking out. I thought about Lyme disease. And it wasn't only patients—it was also allies, right? The same thing needs to happen with neglected diseases around the world. Allies need to step up and make demands on policymakers. We need to make some noise."