Biosurveillance and early outbreak detection of rabies in settings with limited laboratory capacity using spatiotemporal clustering and a machine learning framework.

Rabies is an important but often neglected zoonotic disease with significant public health, veterinary, and economic impacts. Inadequate surveillance and diagnostic resources in low- and middle-income countries impede its effective public health responses. This study demonstrates the use of an extreme gradient boosting (XGB) technique for animal rabies risk assessment in endemic areas of Haiti with limited diagnostic resources. We employed spatiotemporal clustering and trend analysis techniques to assess rabies status across large geographic areas. The XGB model achieved high specificity (0.99, 95% CI: 0.98-0.99), sensitivity (0.78, 95% CI: 0.61-0.95), negative predictive value (1.0, 95% CI: 0.99-1.00), and accuracy (0.98, 95% CI: 0.98-0.99) in predicting animal rabies cases. The framework identified 20 high-risk rabies clusters, representing a 40% increase in detected transmission zones compared to laboratory-confirmed data alone. This included 8 clusters in underserved communities where no diagnostic infrastructure was previously available, enabling real-time monitoring of disease and surveillance trends in previously unmonitored regions. Trend analysis facilitated real-time monitoring of high-risk clusters with significantly changing disease and surveillance statuses. This study showcases a data-driven, evidence-based framework for neglected and emerging zoonotic disease surveillance in economically constrained regions.