Sperling Medical Group

reading & research

Will Artificial Intelligence Determine What You Should Eat?

How would you like a tailor-made food plan that told you the healthiest things to eat based entirely on your personal biology? The analysis of what you need, as a unique individual, would be based on things like your gut microbiome, your blood glucose levels, your overall metabolism, your activity level, and so much more. Imagine it’s 12:30 pm on a Tuesday in mid-July and you’re hungry for lunch. You open your customized smartphone app and it instantly tells you exactly the right thing to eat to maintain optimal health for every system in your body.

Does this idea appeal to you? If so, you’ll be excited to know that nutritional researchers and program developers are already harnessing Artificial Intelligence (AI) to improve each person’s dietary health. In the book Artificial Intelligence in Precision Medicine, Lopes, et al. (2020) assure us that when it comes to nutrition and fitness, “…[i]current technology available (information technology, several sensors, the use of nanotechnology and the advent of computers, IPhones, and smartphones) is favorable to the application of AI, since a large amount of data is collected by these technologies and, therefore, AI could be very useful in their mining.”

A year later, Limketkai, et al. (2021) noted, “Mobile applications and wearable technologies have provided opportunities for real-time collection of granular nutrition-related data. Machine learning has allowed for more complex analyses of the increasing volume of data collected. The combination of these tools has also translated into practical clinical applications, such as decision support tools, risk prediction, and diet optimization.”[ii]

The future is now

Nutritional apps indeed need huge amounts of data backed by research showing that a food that promotes wellness for one person may not react as favorably with another person’s biochemistry. An example is the DayTwo app. It specifically targets metabolic diseases like diabetes and clinical obesity, thanks to an algorithm that matches food plans to an individual’s metabolism and gut bacteria. According to a New York Times story, “…it was better at controlling blood sugar than the Mediterranean diet, considered one of the healthiest in the world.”[iii] As supporters of the Mediterranean diet, we have mentioned it in several Sperling Prostate Center blogs, such as the benefits of this meal plan for prostate cancer patients on Active Surveillance. Now, with trained machine learning, the ability to tailor food guidance to each person’s needs will transcend the general advice provided in a book or article about the Mediterranean diet, or any other diet.

That said, an element of caution is warranted before going to your phone’s app store and downloading one that proposes to lower your blood sugar or help you lose weight. Who did the research? Who developed, tested and validated the algorithm? The DayTwo app was developed on carefully monitored data from 800 patients showing that sushi might have no impact on one person’s glucose level, but drive another’s through the roof. That research, performed by Israel’s Weizmann Institute of Science, delivered compelling evidence that personalizing diet was key to metabolic control. Weismann Institute is a well-respected research center, but persons eager to take advantage of AI applications available in a wrist-worn device or smartphone “…should be wary of overly broad claims that go beyond predicting how foods affect blood sugar.”[iv]

The DayTwo app is the tip of a future-is-now iceberg. Don’t go looking for it yet in Google Play or Apple, since as of this writing, it’s available only through employers or healthcare plans. But below the visible 10% of the iceberg, you can be sure there’s 90% activity generating new AI algorithms that will design your very own menu plan. Just be sure to do your due diligence as to the source of the app, and the quality of research on which it’s founded. Perhaps the day is not very distant when you’re riding in your self-driving car, which is choosing the best route to your destination—and all the while you’re sipping a smoothie you blended at home from ingredients your smart phone chose. All this and more, thanks to Artificial Intelligence.

NOTE: This content is solely for purposes of information and does not substitute for diagnostic or medical advice. Talk to your doctor if you are experiencing pelvic pain, or have any other health concerns or questions of a personal medical nature.

[i] Lopes M, Ferreira D, Ferreira A, da Silva G et al. “Chapter 20 – Use of artificial intelligence in precision nutrition and fitness.” Artificial Intelligence in Precision Health: From Concept to Applications. Academic Press. 2020:465-96.
[ii] Limketkai, B.N., Mauldin, K., Manitius, N. et al. The Age of Artificial Intelligence: Use of Digital Technology in Clinical Nutrition. Curr Surg Rep 9, 20 (2021).
[iii] Ravindram, Sandeep. “Here Come the Artificial Intelligence Nutritionists.” New York Times, Mar. 14, 2022.
[iv] Ibid.