Synthetic intelligence & veterinary medication

Ad Blocker Detected

Our website is made possible by displaying online advertisements to our visitors. Please consider supporting us by disabling your ad blocker.

More than a century ago, the automobile ushered in a new age that fundamentally changed the practice of veterinary medicine. Will artificial intelligence do the same?

Virtually every area of ​​life is somehow affected by AI, which improves our understanding of complex problems and makes better outcomes more likely. In the healthcare industry, AI is used in image interpretation, disease diagnosis, patient monitoring, drug development, and even robotic surgery. Google and IBM have invested heavily in the AI ​​health sector, which is projected to reach $ 150 billion over the next decade.

Veterinary medicine and pet owners are also using AI technologies, particularly in the areas of radiography, triage and diagnosis.

Scientific facts versus fiction

Artificial intelligence is a field of computer science that deals with simulating human intelligence using computers.

AI technology quickly analyzes large amounts of data using a series of instructions called algorithms to accomplish a specific task. These tasks range from creating an online book or movie recommendation to identifying a person based on their facial features.

And yet the technology is far from being able to reproduce human knowledge or creativity. AI can only do what it needs to do, which means the tax fraud detection algorithms cannot predict tomorrow’s weather.

Thomas Strohmer, PhD, is a math professor and director of the Center for Data Science and Artificial Intelligence Research at the University of California-Davis. The center fosters interdisciplinary collaborations that use data science and AI to find solutions to some of the world’s most pressing problems, such as: B. Climate change and affordable health care for all. Dr. Strohmer says there are two types of AI.

“One is a general, very high-level view of AI that can think and read like humans. This is a great vision of AI that doesn’t exist yet, right? It’s science fiction and doesn’t even exist around, ”he explained. “Then you have the tighter AI that you use for driving a car, language translation, and other really impressive applications. This is what we usually mean when we talk about AI: task-specific AI.

“But I should make it very clear that there is still no I in AI. The people who write these algorithms are very intelligent, but the algorithms themselves are not intelligent enough to argue. “

In a 2019 report, the National Academy of Medicine wrote, “AI has the potential to revolutionize healthcare,” and “offers unprecedented opportunities to improve patient and clinical team outcomes, reduce costs, and improve the health of the population affect. “

However, the academy also tried to temper expectations about what AI could achieve. “One of the biggest short-term risks with the current development of AI tools in medicine is not that it does serious unintended damage, but that it simply cannot meet the incredible expectations that excessive hype creates. In fact, so-called AI technologies such as deep learning and machine learning are at the height of excessive expectations of new technologies. “

Data analysis

Dr. Krystle Reagan makes it clear that she is not a computer scientist. Rather, she is an internist at UC-Davis Veterinary Medical Teaching Hospital and an attorney for the AI. She helped develop an algorithm to detect Addison’s disease with an accuracy rate of greater than 99%.

“We call Addison’s disease ‘the great excuse’ because dogs come in with very vague clinical symptoms. The blood count can look like a bowel disease, it can look like kidney disease, it can look like liver disease. So it’s one of those conditions that you really need to be on your toes, ”said Dr. Reagan.

Blood test results from more than 1,000 dogs previously treated at the teaching hospital were used to train an AI program to identify complex patterns that suggest the disease. The computer program could then use these patterns to determine whether a new patient had Addison’s disease. Dr. Reagan and her team published their findings in the July 2020 issue of Domestic Animal Endocrinology magazine.

Now Dr. Reagan data from canine patients seen at UC-Davis Teaching Hospital for the past decade who have been diagnosed or suspected of leptospirosis but later ruled out. The project is a collaboration between Dr. Reagan and Strohmer and the Center for Data Science and AI.

“Then we use machine learning algorithms to try to identify subtle patterns in these dogs’ blood counts that could help us classify it as leptospirosis or no earlier than traditional diagnostics,” explained Dr. Reagan.

Timing is important in diagnosing leptospirosis, said Dr. Reagan, as the disease can cause serious kidney problems, which can become severe enough to require dialysis. “Unfortunately, the gold standard test for leptospirosis requires two antibody tests about 10 days apart,” she continued.

“The gold standard tells us that I cannot make a diagnosis until at least 10 days after the disease. And we really need a tool that will help us give a forecast to the owners as we look at this sick dog and decide whether or not to continue on dialysis.

“We hope that we can find patterns in the data that will help us classify our canine patients as leptospirosis or not – or at least to say that we have an 80% chance that your dog has leptospirosis, or.” we think it is very unlikely that your dog has leptospirosis. “

Two x-ray images are displayed on a tablet

X-ray vision

Radiography is another area where AI is being used with great success. It has been shown that complex algorithms are very precise when recognizing patterns in image data.

The National Academy of Medicine estimates that about 100 scientific reports on AI in radiology were published in 2005, but the number of publications had grown to over 800 in 2017.

“Some of the tasks that current AI technology seems well suited to include prioritizing and tracking results that require early attention, comparing current and past images, and high-throughput screenings that allow radiologists to focus on images that are most likely to be abnormal, “the academy wrote in its 2019 article Report.” However, over time, it is likely that routine imaging interpretation will increasingly be done using AI applications. “

Vetology has been providing traditional veterinary teleradiology services since 2010. Two years ago, the company began offering the ability to provide AI analysis of chest, heart and lung x-rays in dogs. Results are available within five minutes and promise an accuracy equivalent to that of a living veterinary radiologist, said Vetology Founder and CEO Dr. Seth Wallack, a board certified veterinary radiologist.

“Studies by MD radiologists have shown that, on average, they are correct about 70% to 75% of the time. I always tell people that 80% of the time I would like to get the correct diagnosis, ”said Dr. Wallack.

“Having a feedback loop is critical to improving AI. When we discover a problem, we can ask, “What did the AI ​​report say and why did the AI ​​interpret it that way?” Then we tweak things a bit to make it easier for the machine to learn and improve future AI results. “

Dr. Wallack recalled a recent case with a referring veterinarian who believed a dog might have left-sided heart failure. The owners considered euthanasia. After the referring vet received the Vetology AI’s radiology report, which found there was no evidence of heart disease or heart failure, he asked Vetology to have the images examined by a board-certified veterinary radiologist. Dr. Wallack said, “I received this template and there was just enough rotation and fluid in the caudal thoracic esophagus that made me think, ‘I can see perfectly how this could be interpreted as pulmonary edema. ‘It wasn’t like that and the Vetology AI system read it right. I think AI just saved the life of a dog. “

He added, “We have always believed that receiving a Vetology AI X-ray report within five minutes or less of taking the X-rays will have a positive impact on patient outcomes. Even so, every day I’m overwhelmed by what Vetology AI is doing. “

Future perfect?

Dr. Rolan Tripp is interested in the future of the veterinary profession. He’s been talking about it for 30 years and even founded the Veterinary Future Society. Dr. Tripp believes AI is the future of veterinary medicine.

“I think most people don’t understand how big the impact will be, any more than they did a hundred years ago when vets saw that first tractor in the field and laughed when it broke down. Many veterinarians now consider AI a fad, but it’s not. It will revolutionize the way we practice veterinary medicine, mostly in a good way, ”said Dr. Tripp.

As elected President of the Veterinary Medical Ethics Society, Dr. Tripp extremely concerned about the ethical considerations surrounding the use of AI in veterinary medicine. “This is an almost virgin area because very little has been written and addressed about it,” he said.

Dr. Tripp wants AVMA to work with various stakeholders to take a leadership role in anticipating and considering the impact of AI technologies on the veterinary profession. “We should have a plan to try and control this machine intelligence because it has a huge impact and most people don’t understand that.”