The World Health Organization skin neglected tropical diseases app: A dynamic capacity-building training tool enhanced with artificial intelligence.

Skin neglected tropical diseases (NTDs) remain a major public health challenge in low- and middle-income countries, where frontline health workers often lack dermatological training. In response, the World Health Organization created the Skin NTDs App-developed by UniversalDoctor-to support frontline health workers in resource-limited settings. Initially created as a digital adaptation of a World Health Organization training guide, the app evolved by incorporating another clinical decision support tool from Until No Leprosy Remains and an artificial intelligence-powered visual classifier. Our purpose is to describe the World Health Organization Skin NTDs App and evaluate its artificial intelligence-powered visual classifier. The visual classifier was trained to identify 12 out of 13 skin NTDs through a convolutional neural network (DenseNet-121). Performance was assessed through sensitivity, specificity, accuracy, precision, F1-score, and per-class sensitivity from top-1 to top-5. The visual classifier demonstrated high performance in internal evaluations, achieving 99.8% top-5 sensitivity across all diseases and top-1 accuracy above 75% for most diseases. Some underrepresented conditions (eg, chromoblastomycosis, sporotrichosis) showed lower precision. In conclusion, the artificial intelligence-powered World Health Organization Skin NTDs App is a promising digital tool for capacity-building of frontline health workers in underserved areas. Continued development, external validation, and integration into clinical workflows will be critical to assessing its performance globally.