5 AI nutrition apps killing it in healthy eating right now

Artificial intelligence has been on the rise for decades, but it is only recently that the adoption has rapidly increased leading to the proliferation of AI apps and platforms that help in optimizing health. In this article we cover the 5 key areas we see of Artificial intelligence or ai nutrition apps that are making healthy eating using a personalized nutrition approach easy. 

Written by Adriana Sales RD 

AI nutrition apps in Digital health

The use of AI in health and nutrition solutions for prevention, performance and to manage chronic conditions such as obesity are rising rapidly across the globe.

In terms of the types of AI technologies employed, these include Machine learning, Natural language processing, Deep learning and Computer vision to name a few, however generative AI and now AI agents are quickly catching up.

The purpose of leveraging AI technologies in digital health solutions is to reduce the effort and burden of tracking and monitoring on the user. It also helps to synthesize and visualize information in an easy digestible format. AI has the ability to quickly match information from the user such as dietary preferences, food avoidances and health goals to food and ingredient databases in order to serve up recommendation and guidance.

Artificial intelligence technologies in Personalized nutrition and Precision nutrition

Here is a brief summary of what each of these artificial intelligence technologies can do as part of their role in Personalized nutrition ai nutrition solutions:

• Machine learning - can learn from your data and provide recommendations by matching your needs, preferences and goals to a product
• Natural Language processing is a technology that can support food logging by voice. This means that all you need to do is describe what you have eaten during the day or after a meal and the technology will recognize what you said and match that  to a food and portion size in their food database 
• Deep learning is a technology which has the ability to recognize patterns from a range of data such as sleep, food, stress, wearables, online surveys and sensors to be able to provide personalized recommendations or predictions.
• Computer vision is used in technologies that can identify what's on your plate and match the ingredients or meal to a food database. It is also used in face scanning tools.  
• Generative AI can create new information such as text and images from existing datasets. For example it can create a new recipe by combining the taste preferences of a user from a wide range of recipes (no glue allowed please)
• AI agents can take charge of entire tasks by understanding and using available data. For example an AI agent can develop an entire eating and exercise plan for the week by looking at your diary, eating habits and wearable data and provide you with real-time feedback when you are going off-track

Examples of AI technologies in Personalised nutrition and wellness apps

Healthy food shopping artificial intelligence apps

These apps work by creating a personal profile for yourself and any members you live with, it can help you to choose foods that match your dietary preferences and goals through barcode scanning, and even guide you along the healthy food aisles through augmented reality, recommend healthy foods according to your budget, make healthy food swaps and suggest recipes. Examples include Smartwithfood and Verdify, Foodsmart and Lifesum.

Nudging artificial intelligence apps for a healthy lifestyle

Changing behaviors is tough and can take a long time. However, recent apps take this into consideration by incorporating a variety of behavior change techniques that can help you to stick to your health goals by sending personalized reminders, reports and advice at the right time. These apps can create a score that matches your personal preferences and goals with products in the store. A few apps can also provide a dietary assessment  for a more detailed view into your usual food intake and how you compare against the national healthy eating guidelines or well research dietary patterns that can promote health. Some examples include Greenhabit, Zoe, bitewell, January AI

Meal planning artificial intelligence apps 

Covid-19 has meant our shopping trips are now carefully planned. This is a great opportunity to consider healthy and thoughtful meals that can be nourishing your body and boost your immune system. Meal planning apps are great for inspiration and create recommended meals from ingredients you already have in your fridge and cupboard.

A great example is EatLove, and app and platform that can take care of your family meals from healthy eating to medical nutrition.You can even drop all the items from your recipe into a shopping cart and have them delivered straight to your door.

Go plant-based artificial intelligence apps

It is now a well-known fact that we don't eat enough plant-based foods that can help to reduce the risk of developing chronic conditions down the road. A simple switch i n your health journey such as including more plant-based foods or meat-free days during your week (note that I did not say switch completely) can do wonders for your health in the long-term and forms the basis of a healthy diet.

Apps such as Plantevo and Verdify are great apps to help you make those veggie switches and provide dietary recommendations that can also match your taste preferences.

Meal tracking artificial intelligence apps 

Tracking meals can be a tedious task, but they can also be educational and motivational. It is easy to underestimate the amount of saturated fat, salt or sugar you consume each day. It is even easier to overestimate the amount of fiber, or water we consume. Therefore, to know and understand what "habitual" dietary intake can mean for you. Food tracking can now occur via image logging or even voice logging which just means it is becoming easier Apps such as Calorimama, Lifesum and Myfitnesspal can assist. Nutrition research has demonstrated benefits of meal tracking for individuals living with chronic conditions such as diabetes and obesity. This would first involve an nutritional assessment by the app or via a healthcare practitioner such as a dietitian for instance.

Generative AI

Generative AI or GenAI for short can generate text by analyzing disparate dataset very fast. In the context of health, GenAI tools can power a chatbot that can answer questions about your health parameters such as blood results, DNA, online food diary. This makes it easier for the user to ask relevant questions as they come up rather than having to wait for their healthcare professional to respond to emails or phone call. GenAI tools can save time whilst also increasing access to information. The GenAI technology in Personalized nutrition can match the personal, behavioral, biological and physiological data of the user with the scientific literature to ensure the user receives information that is (largely) accurate as well as in the tone that the user can understand by using a simple prompt such as "now explain that to me as if I was a 5-year old"

For example Healome is A US-based company that tracks blood biomarkers, assessing personalized risk scores, and detecting abnormal trends. The company analyses blood results and other data points to generate a single Biological age number which can guide users on actions to take to improve their score.

Insidetracker is a US based Health technology company that uses blood, DNA and wearable data to provide personalised nutrition, supplement and lifestyle recommendations. Their chatbot can answer questions from the user in short sentences which saves the user time to read the online responses or emails.

AI agents

Combining, matching and analyzing food data is no easy feat, especially when making decisions about what to eat can become a daily taxing exercise. AI agents can make life easier my taking care of an entire task or workflow, providing feedback on progress and adjusting the plans as they go along. In areas such as medical nutrition (Food as medicine) where chronic conditions such as Type 2 Diabetes can be managed through dietary intervention, smart food data becomes critical. This involves matching the personal, biological,physiological, behavioral of the user with food databases and product SKU's in order to not only tell the user what to eat but also what they should buy. This requires the combination of private, public and personal databases. The AI agent can for example  be instructed to come up with a weekly exercise plan, meal plan and motivational messages and recommendations on which restaurants to eat at and what to choose for your upcoming lunch time business meeting.

For example Spoonguru is a UK based company that has made food data smart, has an agent that can help consumers develop select foods, create recipes and suggest food products from the retailer to manage a chronic condition. 

However based on the latest nutrition research, AI apps are not without challenges and limitations.

Some of the challenges of leveraging AI in these types of apps can include:

• How an AI system is developed can be a black box ie why did the ai nutrition app provide me those specific recommendations?
• AI algorithms are usually trained on unrepresentative and limited datasets
• Databases used to train AI systems can be inaccurate and incomplete, such as food databases
• AI powered solutions tend to be used mostly by individuals who are digitally literate  

We discuss the ethics and challenges and gaps of AI in nutrition and health solutions extensively in our white paper on the ethics of AI at the intersection of nutrition and behaviour change.

One way of overcoming the lack of transparency in AI nutrition apps are through a Data Nutrition Label. These nutrition labels look like a food ingredients panel on packaged foods, only they include the key "trust ingredients" that are necessary to make an informed decision about whether to use or recommend an ai nutrition app. At present, this standardized label does not exist yet, however in the future such a label could help guide consumer decision and build trust.

In summary, AI will continue to power ai diet and health apps and platforms for the foreseeable future because of its ability to analyze vast amounts of data in a flash, however it is important to keep its long list of limitations in mind. The rapid advances in AI technologies mean that in the near future we can expect deeper integration of different ai technologies such as mirrors, toilets, scales and devices to inform what we should eat and do next.

References

• Mariette Abrahams .& Matusheski N.V.(2020) Personalised nutrition technologies: a new paradigm for dietetic practice and training in a digital transformation era. J Hum Nutr Diet. 33, 295–298 https://doi.org/10.1111/jhn.12746
• Sharon M. Donovan, Mariette Abrahams, Joshua C. Anthony, Robert Bergia, Gil Blander, Tristin D. Brisbois, Anna-Sigrid Keck, Edwin G. Moore, Timothy A. Morck, Kristin M. Nieman, Jose M. Ordovas, Alison Steiber, Barbara L. Winters, Thuyvan Wu, Perspective: Challenges for Personalized Nutrition in the Current U.S. Regulatory Framework and Future Opportunities, Advances in Nutrition, 2025,100382, ISSN 2161-8313,
• Mariette Abrahams, Bryant E, Frewer L, Stewart-Knox B (2019) Personalised nutrition technologies: A cross-national survey of Registered Dietitians. Public Health Genomics DOI: 10.1159/000502915.
• Mariette Abrahams, Frewer L, Bryant E, Stewart-Knox B (2018) Perceptions and experiences of early-adopting registered dietitians in integrating nutrigenomics into practice. British Food Journal 120: 763-776. https://www.researchgate.net/publication/320472722_Perceptions_and_experiences_of_early-adopting_registered_dietitians_in_integrating_nutrigenomics_into_practice
• d' Auria E, Mariette Abrahams, Zuccotti GV, Venter C (2019) Personalized Nutrition Approach in Food Allergy: Is It Prime Time Yet? Nutrients 11, no 359 doi: 10.3390/nu11020359
• Donovan, S. M., Mariette Abrahams., Anthony, J. C., Bao, Y., Barragan, M., Bermingham, K. M., … Winters, B. L. (2025). Personalized nutrition: perspectives on challenges, opportunities, and guiding principles for data use and fusion. Critical Reviews in Food Science and Nutrition, 1–18. https://doi.org/10.1080/10408398.2025.2461237