Poor quality nutritional data

The problem

Poor quality nutritional data

The important role of food intake on health outcomes, both for disease prevention and treatment, remains poorly understood.

Skepticism about nutritional science is widespread both in academia and in the public. A key contributor to the problem is how food intake is measured in the first place: food-frequency questionnaires (FFQs) and diet recalls are still the standards, despite their well-known weaknesses such as imprecision, dependence on human memory, lack of associated data such as the timing of food intake, etc.

While other aspects of health and behaviour measurements have evolved and improved steadily over the past decades (genomics, metagenomics, sensors, etc.), nutrition measurement has been stuck in time: it is still done the same way it was done decades ago.

The solution

Introducing the AI for Nutrition project

The AI for Nutrition project provides a comprehensive, scalable, and demonstrated solution to digital diet logging suitable for the use in research settings.

Developed in the Digital Epidemiology Lab at EPFL, it combines three essential parts:


A mobile app (Android and iOS) for individuals to track food by picture taking or barcode scanning.

The Open Food Repo
The Open Food Repo

An open database of barcoded food products, and an open, extensible categorization of food items.

MyFoodRepo AI Benchmark
MyFoodRepo AI Benchmark

An annotation framework combining artificial intelligence (AI) algorithms and human expertise.

See how digital diet logging will revolutionise nutritional science

Proof of principle


Proof of principle

Early stage clinical trials have been established in Switzerland.

  • Ongoing trials

    3 ongoing; 2 in the pipeline

  • App usage

    Used by study participants daily

  • Barcode database

    40k+ products (foodrepo.org)

  • Image recognition algorhytm

    Trained on 50k+ images

Our progress

Achieved milestones

Project goals

The future

Project goals

Set milestones for 2020 — 2023.

  • Improve accuracy

    Steady development of the MyFoodRepo AI Benchmark for best possible food image recognition.

  • Enhance ease of use

    Further development of the mobile application to provide a user-friendly experience.

  • Scale up internationally

    Establish MyFoodRepo in at least 6 new geographies.

  • Reach self-sustaniability

    Ensure MyFoodRepo will become a non-profit service platform able to sustain itself.

The team

Involved grantees

The Santorio Foundation is a pooled non-profit Swiss foundation fund hosted by the umbrella foundation Fondations des Fondateurs.

How can you help create impact?


How can you help create impact?

With more resources, AI For Nutrition can be accelerated in different ways:

  • Roll out into new countries
  • Rolling out for specific clinical trials
  • Improve the digital infrastructure
  • Improve user friendlyness
  • Improve AI algorhytms
Exploration phase
Theoretical feasibility
Prototyping / PoC
Scaling and implementation
AI for nutrition
is currently on this stage

More information

Links and documentation

If you want to know more about this project, you can refer to the links and documents below.

Santorio Project Steward

Sandra Suiser, PhD

Senior Scientific Project Manager,
Seerave Foundation

Sandra Suiser, PhD
Support this project

Contact Sandra to learn more about AI for nutrition and become a co-impactor.