Artificial intelligence tool found signs of cancer in patients not seen by doctors

The reason for a tool called Mia, which was piloted next to NHS clinical physicians and analyzed the mammograms of more than 10,000 women “searching” for . The artificial intelligence (AI) tool tested by the British NIS successfully found tiny signs of breast cancer in 11 women, who had “run out” from doctors. Most of these mammograms were clean, but the AI tool successfully pointed out all those who had symptoms, as well as 11 others that doctors had not identified. In their early stages, cancers can be extremely small and difficult to detect. BBC saw Mia in action at NHS Grampian, where it showed tumors that were practically invisible to the human eye. But depending on their type, they can grow and spread quickly. Barbara was one of 11 patients whose cancer was noted by Mia, but had not been detected by hospital radiologists who examined her mammography. Because her 6mm volume was detected so early, she was undergoing surgery but only needed five days of radiotherapy. Breast cancer patients with tumours less than 15 millimetres, when detected in time, have a survival rate of 90% over the next five years. Without the help of artificial intelligence, Barbara’s cancer might not have been detected until the next planned mammography to be done three years later. She had no notable symptoms. Because they operate instantaneously, tools such as Mia also have the ability to reduce the waiting time for results from 14 days to three, his programming company, Kheiron Medical, supports. None of the cases involved in the test were analysed only by Mia – all of which were examined human. Of the 10,889 women involved in the trial, only 81 did not want the artificial intelligence tool to examine their mammograms, said Dr Gerald Lip, a clinical breast prevention control director in northeastern Scotland, who also led the project. Source: iatropedia