Health Life

AI algorithms detect diabetic eye disease inconsistently

Credit: CC0 Public Domain

Diabetes continues to be the leading cause of new cases of blindness among adults in the United States. But the current shortage of eye-care providers would make it impossible to keep up with demand to provide the requisite annual screenings for this population. A new study looks at the effectiveness of seven artificial intelligence-based screening algorithms to diagnose diabetic retinopathy, the most common diabetic eye disease leading to vision loss.

In a paper published Jan. 5 in Diabetes Care, researchers compared the algorithms against the diagnostic expertise of retina specialists. Five companies produced the tested algorithms—two in the United States (Eyenuk, Retina-AI Health), one in China (Airdoc), one in Portugal (Retmarker), and one in France (OphtAI).

The researchers deployed the algorithm-based technologies on from nearly 24,000 veterans who sought screening at the Veterans Affairs Puget Sound Health Care System and the Atlanta VA Health Care System from 2006 to 2018.

The researchers found that the algorithms don’t perform as well as they claim. Many of these companies are reporting excellent results in clinical studies. But their performance in a real-world setting was unknown. Researchers conducted a test in which the performance of each algorithm and the performance of the human screeners who work in the VA teleretinal screening system were all compared to the diagnoses that expert ophthalmologists gave when looking at the same images. Three of the algorithms performed reasonably well when compared to the physicians’ diagnoses and one did worse. But only one performed as well as the human screeners in the test.

“It’s alarming that some of these algorithms are not performing consistently since they are being used somewhere in the world,” said lead researcher Aaron Lee, assistant professor of ophthalmology at the University of Washington School

Health article

Keep Your Dogs and Cats Safe From Holiday Hazards

 

Happy holidays? Not if your pet gets sick. FDA’s Center for Veterinary Medicine (CVM) discusses some unhealthy holiday temptations and how to keep your animals safe.

Stocking Stuffers and Pet Treats

If your dog received a stocking full of pet treats, make sure he doesn’t gobble them all up at once, making them hard to digest. Unchewed pet treats can get stuck in the trachea (windpipe) or gastrointestinal tract (esophagus, stomach, and intestines).

If your dog is in obvious distress from eating too much too fast, contact your vet immediately. Some telltale signs are drooling, choking, or vomiting.

Take note of timing. If a bone or chew toy lodges in your dog’s stomach or intestines, the symptoms might not be immediate. Hours to days later, he may vomit and have diarrhea, be less active, not want to eat, and have stomach pain. If the blockage stays there too long, your dog may become very ill. When in doubt, contact your veterinarian, who may need to take x-rays or use an endoscope to see what and where the problem is. 

Tinsel and Ribbons

Decorating your tree? Wrapping or unwrapping gifts? Keep a close eye on where you leave leftover tinsel, string, and ribbons.

Your cat may find these decorations irresistible because they look like easy-to-catch, sparkly, and wiggly prey. In fact, they can cause serious stomach and intestinal damage.

Play it safe by keeping tinsel off the tree and collecting all ribbons and strings after gifts are opened.

Salt-Dough Ornaments

If you’re making salt-dough ornaments or play dough, do not let your pets near them. They contain a great deal of salt, which can be fatal to pets if eaten. Make sure the ornaments or play dough are well out of reach. Be sure to warn children who may want to