Answers are grounded in this paper and cite their sources.
Purpose: This study present the evolution of the alert generation framework of the Brazilian Wildlife Health Information System (SISS-Geo), a citizen science platform supporting wildlife health surveillance and zoonosis prevention.Methods: Three complementary alert strategies were investigated: (i) a rule-based approach based on predefined expert criteria, (ii) an index-based approach that combines multiple cluster attributes through multi-objective optimization, and (iii) an anomaly-basedapproach that employs unsupervised machine learning to identify atypical spatiotemporal clusters. The methodologies were evaluated using two real-world case studies. The first focused on Yellow Fever surveillance using non-human primate records and official datafrom the Brazilian Ministry of Health, while the second addressed Avian Influenza surveillance using bird records and outbreak data from the World Organisation for Animal Health (WOAH).Results: The findings indicate that the three strategies offer complementary capabilities for identifying records and clusters of interest, supporting risk assessment, facilitating detection and early warning in potential health and biodiversity emergencies.Conclusion: Integrating these strategies can strengthen wildlife disease surveillance by supporting the prioritization of field investigations and resource allocation. The framework contributes to scalable, data-driven decision support within the One Health approach.
No takes yet. Share an insight, caveat, or question.
Angelo et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: