摘要：Avian Influenza (AI) is a complex but still poorly understood disease; specifically when it comes to reservoirs, co-infections, connectedness and wider landscape perspectives. Low pathogenic (Low-path LP) AI in chickens caused by less virulent strains of AI viruses (AIVs)—when compared with highly pathogenic AIVs (HPAIVs)—are not even well-described yet or known how they contribute to wider AI and immune system issues. Co-circulation of LPAIVs with HPAIVs suggests their interactions in their ecological aspects. Here we show for the Pacific Rim an international approach how to data mine and model-predict LP AI and its ecological niche with machine learning and open access data sets and geographic information systems (GIS) on a 5 km pixel size for best-possible inference. This is based on the best-available data on the issue (~ 40,827 records of lab-analyzed field data from Japan, Russia, Vietnam, Mongolia, Alaska and Influenza Research Database (IRD) and U.S. Department of Agriculture (USDA) database sets, as well as 19 GIS data layers). We sampled 157 hosts and 110 low-path AIVs with 32 species as drivers. The prevalence across low-path AIV subtypes is dominated by Muscovy ducks, Mallards, Whistling Swans and gulls also emphasizing industrial impacts for the human-dominated wildlife contact zone. This investigation sets a good precedent for the study of reservoirs, big data mining, predictions and subsequent outbreaks of HPAI and other pandemics.
其他摘要：Abstract Avian Influenza (AI) is a complex but still poorly understood disease; specifically when it comes to reservoirs, co-infections, connectedness and wider landscape perspectives. Low pathogenic (Low-path LP) AI in chickens caused by less virulent strains of AI viruses (AIVs)—when compared with highly pathogenic AIVs (HPAIVs)—are not even well-described yet or known how they contribute to wider AI and immune system issues. Co-circulation of LPAIVs with HPAIVs suggests their interactions in their ecological aspects. Here we show for the Pacific Rim an international approach how to data mine and model-predict LP AI and its ecological niche with machine learning and open access data sets and geographic information systems (GIS) on a 5 km pixel size for best-possible inference. This is based on the best-available data on the issue (~ 40,827 records of lab-analyzed field data from Japan, Russia, Vietnam, Mongolia, Alaska and Influenza Research Database (IRD) and U.S. Department of Agriculture (USDA) database sets, as well as 19 GIS data layers). We sampled 157 hosts and 110 low-path AIVs with 32 species as drivers. The prevalence across low-path AIV subtypes is dominated by Muscovy ducks, Mallards, Whistling Swans and gulls also emphasizing industrial impacts for the human-dominated wildlife contact zone. This investigation sets a good precedent for the study of reservoirs, big data mining, predictions and subsequent outbreaks of HPAI and other pandemics.
