AI-based predictive and detection models for Avian Pox caused by Avipoxvirus Spp in the Galápagos Islands

Predicting infection byAvipoxvirus spp, the causative agent of avian pox, in endemic Galápagos Islands species such as theGeospiza fuliginosafinches, represents an innovative approach to controlling viral diseases in vulnerable ecosystems. This study uses artificial intelligence-based predictive models trained on a database compiled from previous research. The database was balanced and subjected to data augmentation like synthetic minority oversampling and tablediffusion. Compared with alternative studies, where the data is converted from tabular data into an image achieving a recall of 85%; our results achieve a recall of near 100% using a multi-state analysis over susceptible-infectious-recovered models in infectious diseases for populations of the European serins (Serinus serinus), highlighting the anticipatory capacity for early identification of outbreaks and risk factors. This predictive tool not only strengthens biodiversity protection in the archipelago but also supports the development of targeted vaccines and treatments, ensuring the preservation of this unique ecosystem and providing a model applicable for monitoring other infectious diseases in bird populations.