Detect skin diseases using your mobile phone

The results of the first phase of the validation study of the Skin NTDs mobile application, designed to help keep at bay some common skin diseases, and especially certain neglected tropical diseases, which mainly affect the population, have been publicly presented. from countries with low per capita income.

The study is led by Carme Carrion, principal researcher at the eHealth Lab of the Open University of Catalonia (Universitat Oberta de Catalunya, UOC), deputy director of research at Health Sciences Studies, and fellow UOC researcher Mireia Cano, project manager in the Care Strategy and Innovation Department of the Germans Trias i Pujol Hospital in Badalona.

The validation project began in 2021 at the request of the World Health Organization (WHO), owner of the application, which is developed by the Catalan company Universal Doctor. The results of the first phase show the good reception among professionals who have participated in the project in Ghana and Kenya. The second phase of the study started this past April with field work in Kenya to validate the inclusion of artificial intelligence (AI) elements that have been integrated into a new beta version of the application.

The study highlights the “good results in terms of usability,” highlights Mireia Cano. These results, according to the parameters of the scale that was used by the research team to evaluate the tool, “are independent of the country, the person’s experience in dermatology and the management of the diseases.” Likewise, as Cano continues, it has been observed that good evaluation “does not depend on the age nor the level of technological knowledge of the participants.” For the UOC researcher, “this is very important, because the fact that there is no difference between the two countries – which have similarities, but also differences – can reinforce the hypothesis that the application should not be customized for each country; This makes it more scalable, it would only be a matter of translating it into the language of each country,” Cano emphasizes.

Fifty professionals on the ground

The first part of the study involved the participation of fifty professionals on the ground in Ghana and Kenya. The application seeks to help health professionals detect 12 neglected tropical diseases and 24 common skin diseases, both in terms of diagnosis and treatment. The fact that the project began during the pandemic limited contact with participants in the field, so now the field work with Kenyan health professionals will allow us to work more closely and continue with the evaluation of the developments of the application based on artificial intelligence, which has to facilitate the identification of diseases using two algorithms that work from photographs.

With the help of the right software, a smart mobile phone can detect skin diseases. (Illustration: Amazings/NCYT)

Validate and improve photo-based algorithms

This new phase of the project aims to verify “to what extent the application allows us to identify a set of diseases accurately or not,” explains Carme Carrion. The two experts will give some first seminars to explain the project and how to use the tool. For two months, the professionals participating in the project, when they meet people affected by a skin disease, will make their diagnosis and, in parallel, will ask the application “what is your opinion.” The result will be sent to a WHO platform, in which two dermatologists, from Tunisia and Kenya, without knowing the result shown by the artificial intelligence, will make their own diagnosis, and then it will be compared with that of the algorithms. This way you can determine if it is sufficiently precise.

“Until now the application, which is conceived in all cases as a training tool for professionals and not as a medical diagnostic device, had a logical algorithm that used a list of signs and symptoms; with artificial intelligence it is expected that results allow us to obtain additional information based on each patient’s injury,” says Carrion.

Working on improving the diagnosis of these diseases, as Carrion highlights, is very relevant in low- and middle-income countries; That is why it is important to have “digital tools for people who are not specialists in dermatology in rural areas”, the usual context in most of these countries.

The WHO, explains Carrion, “is strongly committed to mobile health as a way to improve access to the health system.” The second phase of the study seeks to obtain between 250 and 500 cases in the field, with photographs that will be used to evaluate the artificial intelligence algorithms and find out what the health personnel who will use it think.

The study now made public is titled “Evaluating the World Health Organization’s SkinNTDs App as a Training Tool for Skin Neglected Tropical Diseases in Ghana and Kenya: Cross-Sectional Study.” And it appears in the academic journal Journal of Medical Internet Research. (Source: Open University of Catalonia)