In the poorest areas of the planet, being bitten by a poisonous snake is part of everyday reality and every second that passes until treatment with the antivenin is a matter of life or death. “We call the hour between the bite and the treatment the golden hour”explains Gabriel Alcoba, a doctor who is an expert in snake bites from Doctors Without Borders (MSF) who has been working for years in countries such as South Sudan, Cameroon and Nepal.
In his long experience, this doctor has seen all types of cases and knows that information about the snake is vital, whether it is a description of witnesses, a photograph or the dead body of the animal, although authorities recommend not trying to kill them. “I remember the case of a 7-year-old boy who put his hand in a burrow and was bitten by a cobra,” he tells elDiario.es. “The father reacted and the snake also bit him. “We were only able to save the child.”
According to data from the World Health Organization (WHO), snake venom kills between 81,000 and 138,000 people worldwide each year and leaves another 400,000 disabled for life. A good part of the 2.7 million people who receive bites from venomous snakes each year are usually immersed, at the same time, in forced migration due to conflicts or natural disasters, which increases the chances of crossing flooded areas and receiving a stroke.
Some patients arrive after 24 hours in very serious condition, with gangrene that ends in amputations.
Gabriel Alcoba
— Snake bite expert doctor from Doctors Without Borders (MSF)
Since they do not have access to medical care, victims’ first resort is usually a healer, which multiplies the chances of a fatal outcome. “They come to us with tourniquets and incisions, sometimes they have rubbed urine or cow feces on them, things that can be very toxic,” explains Alcoba. “Some patients arrive after 24 hours in very serious condition, with gangrene that ends in amputations.” Knowing whether it is a venomous snake or an imitator is also important to apply scarce resources well and to avoid the risk of anaphylactic shock, since antivenoms—which are made with horse serum—can trigger an allergic reaction.
AI against the black mamba
This harsh reality has led Alcoba and Rafael Ruiz de Castañeda, from the University of Geneva, to develop a program based on artificial intelligence (AI) that helps local teams make quick decisions. The system, presented in the magazine PLOS Neglected Tropical Diseasesis already underway in an MSF pilot project in South Sudan. Its basis is a machine learning program that has been trained with more than 380,000 images of snakes from around the world and which is used to identify the species and its type of venom.
“Although in some places there is very little information, we are managing to improve the results and the algorithm reaches success rates of 90%,” Ruiz de Castañeda explains to elDiario.es. “In the end, what it allows us is to know what is happening out there, because we have a great information gap; “We know there are people dying, but we don’t know what bit them.”
We have a great information gap; We know there are people dying, but we don’t know what bit them.
Rafael Ruiz de Castañeda
— Researcher at the University of Geneva
Researchers are aware that there is a very complex reality and different levels of information and access to treatment depending on each country and region. If patients arrive at a health center on time, doctors can try to find out which snake it is from the symptoms: swelling and bleeding may point to vipers, while if there is muscle paralysis it could be a mamba or a cobra. . All of this conditions the treatment, which in the case of the black mamba can be between 6 and 9 doses, but if there is an error a lot of antivenom can be wasted, which is a very scarce and expensive treatment.
A growing problem
“When I was working in South Sudan, in 2014, we received around three patients a day, and ten years later the situation has been getting worse,” explains Dr. Alcoba. Between January and July of this year alone, MSF has treated more than 300 snakebite patients in health centers in this country. Doctors have chosen this region because it has one of the lowest numbers of snake studies, but experiences one of the highest rates of bite admissions.
“Some snakes are very similar, they camouflage themselves as toxic and it is very difficult to identify them, there is a fairly high level of error,” he emphasizes. Another case that shocked him was that of a 4-year-old boy he treated in 2016 who had been bitten by a snake on the right cheek, just below the eye. “We didn’t know what snake had bitten him, we only saw that he was swelling and it is dangerous because the inflammation can affect the respiratory tract,” he recalls. “The father had seen a snake in the house, small and black, we didn’t know if it was a cobra or if it was a Atractaspisin which case there is no antivenom.” It is in these types of cases where the tool can be vital, he insists.
“Many situations can arise, we want to use the tool to carry out mapping and know where the most dangerous snakes are to react immediately,” says Dr. Alcoba. “Now we understand which species are affecting which populations in which part of the world,” adds Ruiz de Castañeda. “And now we also know what treatments need to be put in that part of the planet, because the problem is that the ministries of Health buy products, but they don’t know very well how to distribute them, because they don’t know what is out there.”
The new tool will not only serve to react to cases that arrive, but to prepare. “Knowing that there are poisonous snakes in an area, thanks to the collaboration of users, will allow us to anticipate the arrival of possible victims,” concludes Ruiz de Castañeda. “Identify their presence with AI and alert that doctor in the area to prepare to receive cases. “It is just one more grain of sand, one more contribution to what we call zoological diagnosis, which in certain places in the world can make a difference.”
#Artificial #intelligence #snake #bites #stop #deaths #year
