On November 25, 2024, the World Health Organization (WHO) met with Kenya’s Ministry of Health to discuss early findings from the first real-world evaluation of the WHO Skin Neglected Tropical Diseases (NTDs) App. This app uses two artificial intelligence (AI)-based algorithms to assist in diagnosing skin diseases.
The study, a collaboration with TDR, the Open University of Catalonia, the Catalan Institute of Health, the Kenya Medical Research Institute (KEMRI), and the University of Bristol, is the first to test two AI algorithms simultaneously. One algorithm, developed by Universal Doctor, focuses on 12 skin-related NTDs, while the other, created by Belle.ai, is customized for 24 common skin conditions, as requested by WHO.
The study took place across five counties in Kenya, where 40 frontline health workers collected 605 images of skin lesions from an equal number of patients between June and October 2024. Skin diseases are a significant public health concern in Kenya, making up 10–30% of outpatient visits. The country also faces a shortage of dermatologists, which complicates the diagnosis and treatment of these conditions. The WHO Skin NTDs App, powered by AI, aims to support healthcare workers in managing skin diseases more effectively.
Preliminary results showed that both AI algorithms had an average sensitivity of around 80%, when compared with the diagnoses made by three board-certified dermatologists. Dr. José Antonio Ruiz Postigo, a Medical Officer at WHO’s Global Neglected Tropical Diseases Programme, called the results “encouraging,” noting the study’s success in quickly gathering data from remote areas.
The study also gathered valuable feedback from the healthcare workers using the app. Using the User Version of the Mobile Application Rating Scale (uMARS), the app received a score of 3.82 out of 5. In focus group discussions, the app scored 8 out of 10.
Professor Carme Carrion, Principal Investigator at the Open University of Catalonia, noted that healthcare workers felt more empowered by the app. “Their self-esteem increased, and both patients and colleagues began to trust them more when assessing skin lesions,” she said. Dr. Ruth Nyangacha, a research scientist at KEMRI and site Principal Investigator in Kenya, added that the app helped reduce the stigma around patients with skin NTDs, as frontline health workers saw the technology as a valuable partner in diagnosis.
WHO plans to replicate this study in other countries, including Brazil, Cameroon, Côte d’Ivoire, and India, to test the performance of the AI algorithms in different epidemiological settings. The next step is a more detailed analysis of the study results to determine the future direction of the program.
The WHO Skin NTDs App marks a significant step forward in improving the diagnosis and treatment of skin diseases, particularly in regions with limited access to dermatologists.
Related topics
