Emergence of infectious zoonotic diseases poses a global threat, with the ability to cause significant harm to society, as exemplified by COVID-19. More than 70% of the 400 infectious diseases that emerged in the past five decades have a zoonotic origin, including all recent pandemics. To date, most methods for predicting spillover risks have relied on correlative approaches. We explored both mechanistic modelling and machine learning based methods, resulting in the development of a Digital Twin based on a One Health approach.
Our mechanistic model approximates the mass action approach that underpins most transmission models, combining zoonotic viral diversity and human population density to identify high-risk regions. Although our results indicate higher risk in regions along the equator and in Southeast Asia where both viral diversity and human population density are high, it should be noted that this is primarily a conceptual exercise. We compared our spillover risk map to key factors, including zoonotic viral diversity estimates and species richness distributions. This provides further context to the maps and emphasises sources of bias.
Employing one-vs-all classifiers, we targeted Mycobacterium and Listeria due to their significant impact on human and animal health. To address data biases, we used under-sampling and incorporated animal richness data, enhancing prediction accuracy. Our findings highlight that there is a weak relationship between the predictive features and the relative occurrence of the target pathogen. Our findings underscore the need for incorporating spatial-temporal information to improve prediction generalisability. Further validation through targeted infectious disease surveillance is crucial.
Finally, we developed a One Health-based digital twin approach to improve our understanding of complex disease dynamics and enhances our ability to mitigate future threats.