- Sustainable development goals
- Good health and well-being
- No poverty
- Zero hunger
- Project link
About the project
Kimetrica, a social enterprise with bases in the US, Ethiopia and Kenya, have been working on a machine learning tool, MERON - Method for Extremely Rapid Observation of Nutritional Status in order to detect malnutrition using photographs.
More project information
MERON is using facial recognition technology to detect malnutrition in children (aged 0-5) during humanitarian emergencies. MERON uses an algorithm to analyze facial curvature and assesses other non-traditional markers to estimate body mass index. For child safety, the actual image is not stored, merely key points of the face that are intended to be used to create a facial map. This information can assist in identifying the children who need nutrition support and in getting it to them in a timely manner. MERON is seeks to be a scalable alternative to the Mid-Upper Arm Circumference (MUAC) rapid assessment method, which requires training and supervision to reduce errors in its application. The MERON app was partly funded by the UNICEF Innovation Fund. The anthropometric data and photos used to train the model were collected in collaboration with the Ministry of Health and UNICEF Kenya.