Potential of the World Health Organization’s Skin NTDs App to Support and Improve the Detection of Skin-Related Neglected Tropical Diseases: Protocol for a Performance Evaluation and Feasibility Study in Senegal
Notice bibliographique
Résumé
Background The World Health Organization (WHO) roadmap aims to control, eliminate, or eradicate neglected tropical diseases (NTDs) by promoting innovation in prevention, diagnosis, and treatment. In this context, mobile health (mHealth) tools could play an important role in improving health care across the globe, including for skin-related NTDs. One such tool is the WHO Skin NTDs App (currently available in its beta version), which utilizes artificial intelligence (AI) algorithms to classify skin lesion images and offers diagnostic suggestions and management information to bolster early detection at primary care levels. However, to harness the full potential of this and similar mHealth tools, additional insights into their diagnostic performance and potential implementation avenues in settings with limited access to trained dermatologists are essential. Objective The objective of our mixed methods study is to test the functionality, operability, and potential of the AI-supported diagnostic component of the WHO Skin NTDs App (beta version) to support the detection of skin NTDs and common skin conditions in Senegal. Methods We are conducting a diagnostic accuracy study combined with a qualitative preimplementation usability exploration. For the quantitative component, we will collect and analyze approximately 800 skin lesion images from patients presenting to the dermatology unit at the Thiès regional hospital in Senegal. Each lesion will be independently assessed by the AI-based WHO Skin NTDs App and by a dermatologist who will provide a diagnosis serving as the reference standard. Performance metrics, including accuracy, sensitivity, specificity, precision, F1-score, and area under the receiver operating characteristic curve, will be calculated for each diagnostic category to evaluate the app’s ability to detect skin-related NTDs. In parallel, we will conduct semistructured in-depth interviews with a purposive sample of 70-80 stakeholders, including policymakers, health care workers, community leaders, dermatologists, and members of leprosy-affected communities. Interviews will explore perceptions of the app’s usability, acceptability, and potential barriers and facilitators to its adoption within Senegal’s health system. Thematic analysis will be used to interpret qualitative data. Findings will help inform the design of an app-based intervention to be piloted in future community-level studies. Results We expect the results to provide detailed insights into the feasibility and potential of the WHO Skin NTDs App to support and improve the detection of skin NTDs and common skin conditions at the community level in Senegal. We started data collection in August 2024, with the first results expected to be available in 2025. Conclusions Our study will assess the performance and potential use of the WHO Skin NTDs App to detect skin NTDs and common skin conditions in Senegal, outlining its potential role in supporting early diagnoses and enhancing public health responses. Trial Registration German Clinical Trials Register DRKS00034297; https://drks.de/search/de/trial/DRKS00034297/details International Registered Report Identifier (IRRID) DERR1-10.2196/69420
Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.
Comment cette classification a été obtenuedéplier
Prédiction machine sur la base complète
Imitation des enseignantsNi prévalence calibrée, ni vérité terrain. Validation humaine à venir. Le volet Gemma est une étiquette directe du modèle pour chaque travail de la base, lue sur la notice réduite au titre. Le volet Codex est un classifieur appris des 10 348 étiquettes directes de Codex et calibré sur les taux pondérés de l'échantillon; les champs sans appui suffisant ne portent aucun appel Codex. Le mode candidate est l'union des deux volets; le consensus est leur intersection. Ces sorties portent le statut machine_predicted_unvalidated et ne sont pas des étiquettes humaines.
Scores du classifieur distillé par catégorie (deux têtes)
| Catégorie | Codex | Gemma |
|---|---|---|
| Métarecherche | 0,063 | 0,056 |
| Méta-épidémiologie (sens strict) | 0,003 | 0,002 |
| Méta-épidémiologie (sens large) | 0,002 | 0,004 |
| Bibliométrie | 0,002 | 0,002 |
| Études des sciences et des technologies | 0,004 | 0,003 |
| Communication savante | 0,003 | 0,002 |
| Science ouverte | 0,003 | 0,003 |
| Intégrité de la recherche | 0,003 | 0,004 |
| Charge utile insuffisante (le modèle a refusé de juger) | 0,022 | 0,006 |
Scores machine (provisoires)
Les deux têtes enseignantes du modèle étudiant, lues sur ce travail. Un score ordonne la base pour la relecture; il n'affirme jamais une catégorie, et le statut de validation accompagne chaque rangée tel quel.
Scores de référence d'un modèle non mature (critères de maturité non atteints, 7 itérations). Un score ordonne; il n'affirme jamais une catégorie.
score_only:v0-immature-baseline · tel quel depuis la passe de notation : score_only signifie que le nombre peut ordonner les travaux, et qu'aucune étiquette de catégorie n'en découleClassification
machine, non validéePrédiction automatique; un appel candidat d’une seule source (Gemma direct ou Codex distillé), pas un consensus.
Le détail, modèle par modèle et score par score, se trouve en fin de page sous « Comment cette classification a été obtenue ».