[ad_1]
During the spring, a worrying pattern occurs while seabirds off the coast of California are killed by domino acid poisoning, caused by harmful algal blooms. An initial clue indicates when and where this problem begins to spread: rescued brown pelicans, red-throated pelicans, and other species begin at wildlife rehabilitation centers with signs of neurological disease. However, even if they have a full state map, these centers are not interconnected enough to germinate the problem. When staff at a center diagnose a sick bird, others may not be aware of that information another 40 miles from the road.
So researchers at UC Davis recently tested an early detection system that uses artificial intelligence to classify admissions in rehabilitation centers to send wildlife agencies and researchers alerts to growing problems between seabirds and many other types of animals. Their system analyzes entry reports from 30 centers in California, listing information such as animal species, age, reason for admission, and diagnosis. The IA then uses natural language processing to classify reports, looking for patterns of the number of entries associated with certain diseases and injuries.
The researchers used five-year data and more than 200,000 records to establish the bases on which these conditions are most frequently found. When the system detects an anomaly (the number of unusual cases in a given species), it automatically generates an alert, and wildlife experts are notified via the system dashboard, an email, or a text message. Because the system processes data for admission to the rehabilitation center in a day or two, it can generate “prediagnostic” alerts, which are faster than waiting for the diagnosis to be confirmed.
In July, the group has published an article describing the test of his system in the magazine Proceedings of the Royal Society. “We wanted to use the data in an aggregate way to better see the improvements, to see better than what they see in their centers,” says Devin Dombrowski, president and role of the Wild Neighbors Database Project.
In a one-year pilot study, the system identified several models that indicated greater problems. The abundance of seabirds with neurological symptoms such as headaches and whole-body tremors triggered the alert. After the post-mortem study, these birds, including the western strikes of white-water bird species, were poisoned by domino acid. A few months earlier, stone pigeons with symptoms of neurological disease caused a high alert for a high rate of admission to the clinic in the San Francisco Bay Area. With further research the parasite was established Sarcocystis calchasi as a cause.
Researcher Terra Kelly, a veterinarian and epidemiologist at UC Davis, has compared the system syndromic surveillance for people, it uses electronic health records to monitor public health concerns, such as flu outbreaks, opioid overdoses, and the Zika virus and Covid-19. He noted that an animal alert system can also benefit human health. According to him, “wild animals can serve as the first indicator of diseases like the West Nile virus.” He has killed the disease More than 2,000 people Since 1999, according to the Centers for Disease Control and Prevention, it has often been detected in sick birds before being diagnosed in domestic animals and people.
In addition, Kelly says, “we could spot the first animal of an invasive species to be introduced to a center in California.” For example, if the number of mourning pigeons allowed at wildlife centers suddenly changes, the system could issue an alert to veterinarians to indicate that the Eurasian collar pigeon has arrived; it is an invasive species that competes with food and can spread parasites to its pigeons.
[ad_2]
Source link
