Accès ouvert · CC BY

Artificial intelligence-supported One Health surveillance for early warning of Rift Valley fever in Senegal

Article scientifique 2026 Sciences de la santé › Santé publique (OCDE 3.3) Anglais

Résumé

Background Rift Valley Fever (RVF) is a zoonotic disease affecting humans and livestock across Africa, with outbreaks influenced by ecological, animal, and social factors. In Senegal, nomadic livestock systems, endemic mosquito vectors, and mobile pastoralist communities create recurrent outbreak cycles, threatening public health, food security, and livelihoods. Early detection of animal and environmental signals is critical for timely interventions. This study analyzed the 2025 RVF outbreak in Senegal, examining its spatiotemporal dynamics and assessing the contribution of an artificial intelligence (AI)–enhanced One Health surveillance platform to early detection and national response capacity. Methodology/Principal findings We conducted a mixed-methods study of the 2025 RVF outbreak in Senegal, integrating quantitative data from humans, animals, and environmental sources with qualitative insights from community-based surveillance. Multi-source data—including AI-generated predictions, epidemiological records, and community alerts—were analyzed alongside institutional and operational challenges. Outbreaks were characterized by widespread livestock abortions, concentrated in northern regions and shaped by livestock mobility, ecological conditions, and vector activity. The AI-based One Health platform detected early warning signals days to weeks before official confirmation. Connectivity gaps, uneven digital literacy, delayed validation, and weak cross-sector coordination constrained effectiveness of detection and response. Conclusions/Significance Our study demonstrates that AI-enhanced, community-integrated One Health surveillance can improve early outbreak detection, but technological innovation alone is insufficient without institutional alignment, inclusive governance, and community engagement. Strengthening these systems is crucial for equitable, timely responses to zoonotic threats in agro-pastoral regions of Africa.

Citer ce document

Diop, B., Faye, S. L., Cissé, B., Sow, G. H. C., NDAO, A., Badiane, M., Diakhate, F., Dia, N., Ndiaye, F., Bocoum, M., Camara, B., Faye, F. N., Diop, R., Mbengue, M. R. H., Diongue, F. B., Thiam, O. A., Duclos, V., Ndiaye, D., Ba, M. L., Fall, M., Lo, M., Ba, I., Sall, Y., Kébé, K., Ndour, D., Dieye, P. S., & Ndiaye, M. (2026). Artificial intelligence-supported One Health surveillance for early warning of Rift Valley fever in Senegal. Frontiers in Tropical Diseases. https://doi.org/10.3389/fitd.2026.1778438

Exporter : BibTeX · RIS (Zotero, Mendeley, EndNote)

Accès au document

Texte intégral archivé sur SPHAERO, en accès ouvert : lisible gratuitement en ligne après connexion. Le document reste aussi disponible à sa source. Se connecter

Licence et provenance

Licence : CC BY

Notice moissonnée depuis OpenAlex le 30/09/2026. Le document reste hébergé par sa source.
Voir le document à la source →

Statistiques

Consultations (hors robots) : 13

Téléchargements (hors robots) : 0

Méthode de comptage