Source: © World Health Organization/Harandane Dicko, 2013 (click to enlarge & download).
Neglected tropical skin diseases (skin NTDs, see box) mainly occur in rural regions of sub-Saharan Africa. They are often detected too late and, if left untreated, can have serious health consequences and lead to stigmatisation. This is where the SkincAIr project comes in: an international consortium coordinated by the Universidad Politécnica de Madrid (Technical University of Madrid) is bringing together African and European partners to methodically combat these diseases. At the heart of this Horizon Europe-funded research project is an AI model developed by the HSLU that analyses skin changes based on smartphone images and assists local healthcare professionals in their diagnosis. The project also involves collecting image material to train the AI model, as there is currently only little data available for darker skin types.
Digital diagnostics for all skin types in remote regions
The image material collected to train the AI model was sourced in different regions and covers the widest possible range of skin types, age groups, and cultural backgrounds. This to ensure that as many people as possible can be diagnosed accurately.
Digital diagnostics for all skin types in remote regions
Another advantage for remote regions is that the app is free and also works without an internet connection. The data collected is automatically synchronised as soon as the device reconnects with the internet.
‘Our AI will help detect NTD skin diseases earlier, reduce transmission rates and treat patients more quickly. This relieves the burden on local health infrastructures and significantly improves care,’ says Gil Sharvit, project manager at the HSLU.
Successful test phase
The SkincAIr app is currently being tested in five countries: Kenya, Senegal, Ethiopia, Nigeria and the Democratic Republic of Congo. Local clinics and research institutions help to collect data for the app. To date, over 7,000 images of skin diseases have been gathered carefully. The aim is to build the largest open collection of skin images in sub-Saharan Africa and to ensure the app works reliably in real-life clinical situations. The developers made sure the app is easy to use for local healthcare professionals.
Data is available to everyone
SkincAIr is an open science project: the data collected and algorithms are freely available to researchers worldwide, the aim being to create the largest publicly available dataset on neglected tropical skin diseases to date. This allows for the solution to be further developed in other countries and extended to other diseases. In addition to AI, there is a focus on training local healthcare workers to improve care and strengthen the early detection of skin diseases in the long term. All data is shared in compliance with ethical standards, informed consent procedures, and strict anonymisation protocols.
Neglected tropical diseases (NTDs)
Neglected tropical diseases (NTDs) are a group of diseases that primarily affect poor people in tropical regions. Unlike AIDS or malaria, NTDs receive little attention and research funding.
Skin NTDs are a subgroup of the kinds of disease that can manifest in visible changes to the skin. These include leishmaniasis, river blindness, scabies, and other parasitic infestations.
