In the context of the SNSF Snake-Byte project (2018-2022), the unit developed and used a One Health framework to quantify the direct impact of snakebite on human health and the indirect impact through livestock animals and subsequent livelihoods in Nepal and Cameroon. This was the first One Health approach to snakebite, including the economic dimension. With a Swiss and international group of partners and the support of the Fondation privée des HUG, the unit is developing a medical decision-support tool for snake identification based on artificial intelligence and remote collaborative expertise. Snake identification is key to treat patients with specific antivenoms and to improve epidemiological data (Project timeline: 2018-2020). But snakes are diverse, and most healthcare providers lack the expertise to identify them. The unit created the world’s largest snake photo dataset and developed the first AI model and an app to classify snakes and to support snakebite diagnosis. This project has sparked the interest of the AI community, and the unit won an international challenge organized by Facebook AI and was invited to present their research at the Computer Vision for Global Challenges Workshop (CV4GC) in the leading computer vision conference IEEE Computer Vision and Pattern Recognition (CVPR) (California, June 2019). This project currently serves as a use-case of the WHO-ITU Focus Group on “AI for Health” to benchmark the development of AI algorithms applied to healthcare.  In collaboration with  InZone, the unit implemented an innovative blended-learning program on One Health in Kakuma refugee camp (Kenya) combining its interdisciplinary and  multi-expert  MOOC  on  “Global  Health  at the Human-Animal-Ecosystem  interface” and   context-specific   project-based  learning.