For the first time, scientists have used innovative tech to demonstrate that a healthy microbiome needs a consistent flow of the right foods, finally proving that the "hunch" advice of 5 A Day is spot on, as far as your gut bugs are concerned.
Researchers at Swiss university École Polytechnique Fédérale de Lausanne (EPFL), working with scientists at the University of California, San Diego, have used AI and machine learning to make new discoveries about diet and health, analyzing the nutritional data of 1,000 participants in the Food & You study, including stool samples. Perhaps most importantly, they found that it's not just about including fruit, vegetables and grains in your diet – consistency is crucial. The study is the first to confirm that well known advice of "five serves a day" of fruit and vegetables – which the team says has always been just a hunch – is spot on.
“This research clearly shows that you cannot binge on vegetables on your healthy day and then eat in an unhealthy way for the rest of the week or month,” said Associate Professor Marcel Salathé, head of the Digital Epidemiology Lab and co-director of the EPFL AI Center. “In fact, our study suggests that irregular consumption of healthy foods undoes many of their beneficial effects on the gut microbiota. This is a real incentive for future studies to not just look at what people are eating but the patterns of what they are eating over time.”
The strength of the findings is due to how the researchers gathered data and analyzed the information. Participants in the study used the AI-powered app MyFoodRepo, which identifies food from photographs and barcodes to collect nutritional data, doing away with the need for individuals to keep manual food diaries (the data was later assessed for accuracy by researchers).
“Historically, nutrition research has relied on food frequency questionnaires and 24-hour dietary recalls," said Rohan Singh, a Doctoral Assistant in EPFL's Digital Epidemiology Lab and lead author of the paper. "In theory, you could ask somebody to write down everything they eat, but in practice it’s just not done because it’s borderline impossible. Now, the AI is so good that we can do this data collection at a large scale."
What's more, the US team used the technology to analyze stool samples, and were able to tell with 85% accuracy just what the person had eaten based on the microbial makeup. This also means that machine learning analysis could "prescribe" an optimal food plan for improving gut health.
“For our collaborators in San Diego, who are some of the world’s leading experts in microbiome research, this was exciting,” explained Salathé. “Getting such data from a stool sample is relatively easy, but understanding someone’s diet is notoriously difficult, it's data that’s been challenging to collect.”
In recent years, we've become increasingly aware of the role of the microbiome on not just the health of the digestive tract but how it impacts metabolic and cognitive functions, mental health and more. This research is one step closer to science-driven nutritional advice based on data not trends.
“Our study has been particularly interesting because when you look at lifestyle-oriented gastrointestinal disorders, they often develop gradually," said Singh. "Since nutrition is one of the big contributors to these diseases, analyses like ours may be able to assess what can be improved in a person’s diet. AI can then help nudge people to adjust their food intake accordingly."
While we might be some time away from having a personal AI toilet that offers real-time feedback on our microbiome's health, the findings shine a light on the need for nutritional policies to keep pace with the scientific community. The researchers suggest current guidelines might need to be revised to focus less on the type and quantity of certain foods for health, and more on the importance of consistency.
The AI app – which was created by EPFL scientists – is now being used in two new studies, one looking at gut health and cognitive function, and another using the barcode function to assess how food additives impact the microbiome.
“There’s a strong hypothesis that some of these additives really may negatively impact your microbiota, and we have some early indications that this could indeed be the case," said Salathé. "We're still in the analysis stage but we are quite excited about early results.
“From the outset, we knew we needed something extremely consumer friendly and easy to use, while still providing the data that we needed," he added, referring to the app. "We built it to serve our own research needs, but also in a way which others would find useful – and it’s now being used in many other nutrition studies globally."
The research was published in the journal Nature Communications.
Source: EPFL
