Description of the Project

Snakebite is the second most deadly neglected tropical disease being responsible for a dramatic humanitarian crisis in global health. Snakebite causes over 100,000 human deaths and 400,000 victims of disability and disfigurement globally every year affecting poor and rural communities in developing countries, which host the highest venomous snake diversity and the highest burden of snakebite due to limited medical expertise and access to antivenoms (more information here). Antivenoms can be life-saving when correctly administered but, since many are species-specific, this depends first on the correct identification of the biting snake. Snake identification is challenging due to snake diversity and incomplete or misleading information provided by snakebite victims or bystanders to clinicians, who generally lack the knowledge or resources in herpetology. To reduce potentially erroneous and/or delayed healthcare actions, and taking advantage of the expansion of mobile technologies in developing and emerging countries, we propose the first medical decision-support mobile app for snake identification based on artificial intelligence and remote collaborative expertise in herpetology. Our app will combine computer vision with the expertise from a network of herpetologists to identify photos of snakes, particularly supporting victims and clinicians when urgent and reliable snake identification is needed (System Diagram).

This innovative approach is timely and responds to the urgent need for cutting-edge research and scientific leadership following the acceptance of snakebite in the WHO-NTDs list in June 2017 and the current political momentum.

Project partners:

Dr. Rafael Ruiz de Castañeda, Institute of Global Health, UNIGE
Dr. Isabelle Bolon, Institute of Global Health, UNIGE
Dr. Andrew Durso, Institute of Global Health, UNIGE
Prof. François Chappuis, Division of humanitarian and tropical medicine, HUG/UNIGE
Dr. Gabriel Alcoba, MSF and Division of humanitarian and tropical medicine, HUG/UNIGE
Dr. Nicolas Ray, Institute of environmental sciences & Institute of Global Health, UNIGE
Prof. Marcel Salathe, Digital Epidemiology Lab, EPFL
Sharada Prasanna Mohanty, Digital Epidemiology Lab, EPFL
Prof. François Grey, Citizen Cyberlab, UNIGE
Dr. Jose Luis Fernandez, Citizen Cyberlab, UNIGE
Rosy Mondardini, Citizen Science Center Zurich, ETH / UNIZH
Prof. David Williams, Global Snakebite Initiative, University of Melbourne
Dr. Abiy Tamrat, Médecins Sans Frontières, Geneva
Hanne Epstein, Médecins Sans Frontières, Copenhagen
Donald Becker, Christopher Smith, Michael Pingleton, HerpMapper
M. Jose Louies, IUCN Viper Specialist Group, indiansnakes.org & snakebiteinitiative.in
Dr. Brian Lohse, AntiVenom Venture & University of Copenhagen
Dr. Ulrich Kuch, University of Frankfurt, Germany

This project is supported by a seed funding grant from the "Fondation privée des HUG" and is endorsed by MSF (Doctors Without Borders)

Our primary objective is to build a massive and global photo repository of venomous and non-venomous snakes

Thousands of snake photos are needed to develop and train the machine learning algorithm that will be capable of identifying snakes taxonomically. We need your help!

You want to contribute to this humanitarian and scientific project and you own or have access to photos of snakes (venomous, non venomous, identified or not), please contact us!
Andrew Durso, Isabelle Bolon, Rafael Ruiz de Castañeda

News and activities

February 25th, 2019

Citizen Science Challenge: We have made public 1,100 images of snakes from across the globe and with a gamification approach, we expect amateur and professional herpetologists to identify as many images as possible during the next days. Check the beautiful website, take the challenge and enjoy the learning experience!

January 21st, 2019

We have just launched our first collaborative AI challenge on AIcrowd: contribute and compete to develop the best algorithm for snake identification or help us disseminate the challenge!

November 23rd, 2018 

Our project was accepted as a use case by ITU-WHO Focus Group on “AI for Health” and will be supported for the benchmarking of our AI model. This standardization process aims at the responsible adoption of algorithmic decision-making tools.