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.”
Sustainable Urban Farming Has a Rising Hot Star: Bugs
In Sydney, Australia, in the basement of an inner-city high-rise, lives a mass of unexpected inhabitants: millions of maggots. The insects are far from unwelcome. They are there to feast on the food waste generated by the building's human residents.
Goterra, the start-up that installed the maggots in the building in December, belongs to the rapidly expanding insect agriculture industry, which is experiencing a surge of investment worldwide.
The maggots – the larvae of the black soldier fly – are voracious, unfussy eaters. As adult flies, they don't eat, so the young fatten up swiftly on whatever they can get. Goterra's basement colony can munch through 5 metric tons of waste in a day.
"Maggots are nature's cleaners," says Bob Gordon, Head of Growth at Goterra. "They're a great tool to manage waste streams."
Their capacity to consume presents a neat response to the problem of food waste, which contributes up to 8% of global greenhouse gas emissions each year as it rots in landfill.
"The maggots eat the food fairly fresh," Gordon says. "So, there's minimal degradation and you don't get those methane emissions."
Alongside their ability to devour waste, the soldier fly larvae hold further agricultural promise: they yield an incredibly efficient protein. After the maggots have binged for about 12 days, Goterra harvests and processes them into a protein-rich livestock feed. Their excrement, known as frass, is also collected and turned into soil conditioner.
"We are producing protein in a basement," says Gordon. "It's urban farming – really sustainable, urban farming."
Goterra's module in the basement at Barangaroo, Sydney.
Supplied by Goterra
Goterra's founder Olympia Yarger started producing the insects in "buckets in her backyard" in 2016. Today, Goterra has a large-scale processing plant and has developed proprietary modules – in shipping containers – that use robotics to manage the larvae.
The modules have been installed on site at municipal buildings, hospitals, supermarkets, several McDonald's restaurants, and a range of smaller enterprises in Australia. Users pay a subscription fee and simply pour in the waste; Goterra visits once a fortnight to harvest the bugs.
Insect agriculture is well established outside of the West, and the practice is gaining traction around the world. China has mega-facilities that can process hundreds of tons of waste in a day. In Kenya, a program recently trained 2000 farmers in soldier fly farming to boost their economic security. French biotech company InnovaFeed, in partnership with US agricultural heavyweight ADM, plans to build "the world's largest insect protein facility" in Illinois this year.
"The [maggots] are science fiction on earth. Watching them work is awe-inspiring."
But the concept is still not to everyone's taste.
"This is still a topic that I say is a bit like black liquorice – people tend to either really like it or really don't," says Wendy Lu McGill, Communications Director at the North American Coalition of Insect Agriculture (NACIA).
Formed in 2016, NACIA now has over 100 members – including researchers and commercial producers of black soldier flies, meal worms and crickets.
McGill says there have been a few iterations of insect agriculture in the US – beginning with worms produced for bait after World War II then shifting to food for exotic pets. The current focus – "insects as food and feed" – took root about a decade ago, with the establishment of the first commercial farms for this purpose.
"We're starting to see more expansion in the U.S. and a lot of the larger investments have been for black soldier fly producers," McGill says. "They tend to have larger facilities and the animal feed market they're looking at is potentially quite large."
InnovaFeed's Illinois facility is set to produce 60,000 metric tons of animal feed protein per year.
"They'll be trying to employ many different circular principles," McGill says of the project. "For example, the heat from the feed factory – the excess heat that would normally just be vented – will be used to heat the other side that's raising the black soldier fly."
Although commercial applications have started to flourish recently, scientific knowledge of the black soldier fly's potential has existed for decades.
Dr. Jeffery Tomberlin, an entomologist at Texas A&M University, has been studying the insect for over 20 years, contributing to key technologies used in the industry. He also founded Evo, a black soldier fly company in Texas, which feeds its larvae the waste from a local bakery and distillery.
"They are science fiction on earth," he says of the maggots. "Watching them work is awe-inspiring."
Tomberlin says fly farms can work effectively at different scales, and present possibilities for non-Western countries to shift towards "commodity independence."
"You don't have to have millions of dollars invested to be successful in producing this insect," he says. "[A farm] can be as simple as an open barn along the equator to a 30,000 square-foot indoor facility in the Netherlands."
As the world's population balloons, food insecurity is an increasing concern. By 2050, the UN predicts that to feed our projected population we will need to ramp up food production by at least 60%. Insect agriculture, which uses very little land and water compared to traditional livestock farming, could play a key role.
Insects may become more common human food, but the current commercial focus is animal feed. Aquaculture is a key market, with insects presenting an alternative to fish meal derived from over-exploited stocks. Insect meal is also increasingly popular in pet food, particularly in Europe.
While recent investment has been strong – NACIA says 2020 was the best year yet – reaching a scale that can match existing agricultural industries and providing a competitive price point are still hurdles for insect agriculture.
But COVID-19 has strengthened the argument for new agricultural approaches, such as the decentralized, indoor systems and circular principles employed by insect farms.
"This has given the world a preview – which no one wanted – of [future] supply chain disruptions," says McGill.
As the industry works to meet demand, Tomberlin predicts diversification and product innovation: "I think food science is going to play a big part in that. They can take an insect and create ice cream." (Dried soldier fly larvae "taste kind of like popcorn," if you were wondering.)
Tomberlin says the insects could even become an interplanetary protein source: "I do believe in that. I mean, if we're going to colonize other planets, we need to be sustainable."
But he issues a word of caution about the industry growing too big, too fast: "I think we as an industry need to be very careful of how we harness and apply [our knowledge]. The black soldier fly is considered the crown jewel today, but if it's mismanaged, it can be relegated back to a past."
Goterra's Gordon also warns against rushing into mass production: "If you're just replacing big intensive animal agriculture with big intensive animal agriculture with more efficient animals, then what's the change you're really effecting?"
But he expects the industry will continue its rise though the next decade, and Goterra – fuelled by recent $8 million Series A funding – plans to expand internationally this year.
"Within 10 years' time, I would like to see the vast majority of our unavoidable food waste being used to produce maggots to go into a protein application," Gordon says.
"There's no lack of demand. And there's no lack of food waste."
One of the biggest challenges of the COVID-19 pandemic is the way in which it has forced us to question our hopes. In normal times, hope is a tonic we take in small doses to keep us moving forward through the slog of daily life. The pandemic, however, has made it a much scarcer commodity, spurring us not only to seek it more desperately but to scrutinize it more closely.
Every bit of reassurance seems to come with caveats: Masks can shield us from the coronavirus, but they may need to be doubled in some situations to provide adequate protection. Vaccines work, but they may not be as effective against some viral variants—and they can cause extremely rare but serious side effects. Every few weeks, another potential miracle cure makes headlines (Hydroxychloroquine! Convalescent plasma!), only to prove disappointing on closer inspection. It's hard to know which alleged breakthroughs are worth pinning our hopes on, and which are the products of wishful thinking or hucksterism.
In January 2021, a study published in the journal Gut offered evidence that bacteria in the intestines might influence a whole spectrum of symptoms in long-haul patients.
Lately, two possible sources of hope have emerged concerning so-called "long COVID"—the debilitating syndrome, estimated to affect up to one-third of patients, in which physical, neurological, and cognitive symptoms persist for months. The first encouraging item has gotten plenty of media attention: reports that some long-haulers feel better after being vaccinated. The second item, while less widely covered, has caused a stir among scientists: a study suggesting that rebalancing the gut microbiome—the community of microorganisms in our intestines—could decrease both the severity and duration of the illness.
How optimistic should we allow ourselves to be about either of these developments? Experts warn that it's too soon to tell. Yet research into how vaccines and gut bacteria affect long-haulers—and how both factors might work together—could eventually help solve key pieces of the pandemic puzzle.
Investigating the Role of the Gut Microbiome
The idea that there may be a link between COVID-19 and gut health comes as no surprise to Jessica Lovett. Her case began in June 2020 with gastrointestinal distress—a symptom that was just beginning to be recognized as commonplace in what had initially been considered a respiratory illness. "I had diarrhea three to five times a day for two months," Lovett recalls. "I lost a lot of weight." By July, she was also suffering shortness of breath, chest pain, racing heartbeat, severe fatigue, brain fog, migraines, memory lapses, and more. As with many other COVID long-haulers, these troubles waxed and waned in an endless parade.
Lovett was the marketing manager for a music school in Austin, Texas, and the mother of a two-year-old boy. Just before she got sick, she ran a 5K race for her 40th birthday. Afterward, she had to give up her job, stop driving, and delegate childcare to her husband (who fell ill shortly before she did but recovered in 12 days). Tests showed no visible damage to her lungs, heart, or other organs. But she felt intuitively that taming her GI troubles would be key to getting well. On the advice of fellow patients in a long-COVID Facebook group—and, later, with the guidance of a doctor—she tried avoiding foods thought to trigger histamine reactions or inflammation. That seemed to help some, as did nutritional supplements, antihistamines, and angina medications. Still, she relapsed frequently, and was often bedridden.
In January 2021, a study published in the journal Gut offered evidence that bacteria in the intestines might influence a whole spectrum of symptoms in patients like Lovett. Researchers at the Chinese University of Hong Kong examined blood and stool samples and medical records from 100 hospital patients with lab-confirmed COVID-19 infections, and from 78 people without the disease who were taking part in a microbiome study before the pandemic.
The team, led by professor Siew Chien Ng, found that the makeup of the gut microbiome differed sharply between the two groups. Patients with COVID had higher levels of three bacterial species than those without the infection, but lower levels of several species known to enhance immune system response. Reductions in two of those species—Faecalibacterium prausnitzii and Bifidobacterium bifidum—were associated with more severe symptoms. And the numbers of such helpful bacteria remained low in stool samples collected up to 30 days after infected patients had seemingly cleared the coronavirus from their bodies.
Analysis of blood samples, moreover, showed that these bacterial imbalances correlated with higher levels of inflammatory cytokines (immune system chemicals that are elevated in many patients with severe COVID-19) and markers of tissue damage, such as C-reactive protein.
These findings led the researchers to suggest that rebalancing the microbiome might lessen not only the intensity of COVID symptoms, but also their persistence. "Bolstering of beneficial gut species depleted in COVID-19," they wrote, "could serve as a novel avenue to mitigate severe disease, underscoring the importance of managing patients' gut biota during and after COVID-19."
Soon afterward, Ng revealed that she was working on a solution. Her team, she told Medscape, had developed "a microbiome immunity product that is targeted to what is missing in COVID-19 patients." Early research showed that hospitalized patients who received the treatment developed more antibodies, had fewer symptoms, and were discharged sooner. "So it is quite a bright and promising future," she enthused, "in alleviating some of these detrimental effects of the virus."
The Chicken-and-Egg Problem
Ng's study isn't the only one to suggest a connection between the gut and long COVID. Researchers led by gastroenterologist Saurabh Mehandru at New York's Mount Sinai Hospital recently determined that SARS-CoV-2, the virus that causes COVID-19, can linger in the intestines for months after a patient tests negative. Some studies have also found that gastrointestinal symptoms in the acute phase of the illness correlate with poorer outcomes—though that's far from settled. (In another study, Mehandru's team found lower mortality among patients presenting with GI symptoms.) But the Hong Kong group's paper was the first to posit that resident microbes may play a decisive role in the disease.
That view reflects growing evidence that these bugs can influence a range of ailments, from diabetes to schizophrenia. Over the past decade, the gut microbiome has emerged as a central regulator of the immune system. Some intestinal bacteria emit chemicals that signal immune cells to reduce production of inflammatory proteins, or help those cells effectively target invading pathogens. They also help maintain the integrity of the intestinal lining—preventing the syndrome known as "leaky gut," in which harmful microbes or toxins penetrate to the underlying tissue, potentially wreaking havoc throughout the body and brain.
Nonetheless, many experts have responded to Ng's findings with distinct caution. One problem, they point out, is the chicken-and-egg question: Do reduced levels of beneficial gut bacteria trigger the inflammation seen in COVID-19, or does inflammation triggered by COVID-19 kill off beneficial gut bacteria? "It's an issue of causality versus just association," explains Somsouk Ma, a professor of gastroenterology at the University of California, San Francisco. "I tend to think that the shift in microbes is more likely a consequence of the infection. But, of course, that's just speculation."
A related issue is whether a pill that replenishes "good" bacteria can really combat the effects of COVID-19—whether acute or chronic. Although scientists are studying fecal transplants and other probiotic therapies for many disorders, none has yet been approved by the U.S Food and Drug Administration. "The only situation where bacterial transplantation is known to work is in a form of colitis called Clostridium difficile," notes Mehandru. "I think it's a bit premature to lay too much emphasis on this in the context of COVID."
Placebo-controlled clinical trials will be needed to determine the efficacy of Ng's approach. (Consumer warning: The bacteria she's employing are not found in commercially available probiotics.) Whatever the results, such research—along with studies that track patients' gut microbiomes before, during, and after COVID-19 infection—could help scientists understand why some people have such trouble kicking the disease.
An Unexpected Benefit of Vaccines
The question of what causes long COVID is also central to understanding the effects of vaccines on the condition. In March, as inoculation campaigns took off across the nation, many long-haulers were delighted to see their symptoms disappear within days of getting the shot. "I woke up and it was like, 'Oh what a beautiful morning,'" one patient told The New York Times.
Yet the effects have been far from uniform. Although scientific surveys have not yet been conducted, an April poll by a Facebook group called Survivor Corps found numbers close to experts' estimates: 39 percent said they experienced partial to full recovery post-vaccination; 46 percent saw no difference; and 14 percent felt worse.
How could vaccines—which are designed to prevent COVID-19, not cure it—help some chronic patients get well? In a blog post, Yale immunologist Akiko Iwasaki suggested that the answer depends on what is driving a particular patient's symptoms. Iwasaki identified three possible mechanisms behind long COVID: 1) a persistent viral reservoir; 2) a "viral ghost," composed of fragments of the virus (RNA or proteins) that linger after the infection has been cleared but can still stimulate inflammation; and 3) an autoimmune response triggered by the infection, inducing a patient's immune cells to attack her own tissues.
These mechanisms "are not mutually exclusive," Iwasaki wrote, "and all three might benefit from the vaccines." If a patient has a viral reservoir, vaccine-induced immune cells and antibodies might be able to eliminate it. If the patient has a viral ghost, those vaccine-primed immune responses might knock it out as well. And if the patient is suffering from a COVID-triggered autoimmune syndrome, the vaccine might act as a decoy, shifting the immune system's attention to antigens contained in the shot (and perhaps reprogramming autoimmune cells in the process). The varying role of these underlying factors, and possibly others—such as the gut microbiome—might also help explain why vaccines don't benefit all long-haulers equally. Iwasaki and her team recently launched a clinical study to investigate this theory.
Pato Hebert, a professor of art and public policy at NYU, contracted COVID-19 in March 2020 while on sabbatical in Los Angeles. Hebert, then 50, started out with mild flu-like symptoms, but he was slammed with fatigue, headaches, and confusion a week after testing positive. In April, he landed in urgent care with severe shortness of breath. His brain fog worsened that summer, and a gentle swim brought on a dizzy spell so overwhelming that he feared it was a stroke. (Thankfully, tests showed it wasn't.) In September, he developed severe GI issues, which came and went over the following months. He found some relief through medications, dietary adjustments, acupuncture, herbal remedies, and careful conservation of his physical and mental energy—but a year after his diagnosis, he was still sick.
Hebert received his first dose of the Moderna vaccine on March 1, 2021; it made no difference in his symptoms. After his second dose, on the 29th, he suffered terrible headaches—"like early COVID days," he told me. A week later, his condition had improved slightly compared to pre-vaccination. "With a few exceptions, my fatigue and brain fog have been less challenging," he reported. "I'm cautiously optimistic." But in late April, he suffered another flareup of respiratory and GI issues.
For Jessica Lovett, the vaccine's effects were more dramatic. After her first dose of the Pfizer-BioNTech formula, on February 26, her cognitive symptoms improved enough that she was able to drive again; within a week, she was pushing her son uphill in a stroller, lifting light weights, and running for short distances. After the second dose, she says, "I had incredible energy. It was insane, like I drank three cups of coffee."
Lovett (who now runs a Facebook support group for Austin locals, ATX Covid Long Haulers) stresses that the vaccine hasn't cured her. She winds up back in bed whenever she pushes herself too hard. She still needs to take antihistamines and shun certain foodstuffs; any slip-up brings another relapse. Yet she's able to live more fully than at any time since she fell ill—and she has begun to feel a renewed sense of hope.
Recently, in fact, she and her husband decided to expand their family. "I guess that tells you something," she says with a laugh. "The doctors have given us the okay, and we're going to try."