According to an expert study published in the British journal The Lancet Digital Health, the artificial intelligence has now reached a stage where it is on a par with human experts in making medical diagnoses based on images. As the British daily The Guardian puts it, the “potential for artificial intelligence in healthcare has caused excitement, with advocates saying it will ease the strain on resources, free up time for doctor-patient interactions and even aid the development of tailored treatment.” The daily adds that in August 2019 the British government announced £250m of funding for a new NHS artificial intelligence laboratory.
In its report, the team of experts led by dr Xioan Liu and prof Alastair Denniston, at the University Hospitals Birmingham NHS foundation trust and other co-authors focused on research papers that were published since 2012. They considered that as the pivotal year for deep learning, something on which using AI in interpreting medical images, when “a series of labeled images are fed into algorithms that pick out features within them and learn how to classify similar images. This approach has shown promise in the diagnosis of diseases from cancers to eye conditions.”
Initially, the researchers found more than 20,000 relevant studies, but only 14 of those that were based on human disease gave them quality data that they could use, “tested the deep learning system with images from a separate dataset to the one used to train it, and showed the same images to human experts.”
Based on their results culled from these 14 studies, the expert team concluded that“deep learning systems correctly detected a disease state 87% of the time – compared with 86% for healthcare professionals – and correctly gave the all-clear 93% of the time, compared with 91% for human experts.”
Talking about the study, prof Denniston said that at the same time “the results were encouraging but the study was a reality check for some of the hype about AI.” Still, he remained optimistic about the use of AI in healthcare saying that “such deep learning systems could act as a diagnostic tool and help tackle the backlog of scans and images.” Also, Dr. Liu thought that “ they could prove useful in places which lack experts to interpret images.”
On the other side of the ocean, and related to the use of AI in medicine, it was announced that Minnesota’s Mayo Clinic, who according to Wired originated “the beginning of modern medical record-keeping in the US,” will partner up with Google to securely store “the hospital’s patient data in a private corner of the company’s cloud. It’s a switch from Microsoft Azure, where Mayo has stored patient data since May of last year when it completed a years-long project to get all of its care sites onto a single electronic health record system.” At the time it was called Project Plummer, after Henry Plummer, the inventor of Mayo Clinic’s medical record-keeping system.
As Wired points out, Google is already involved in other efforts to use AI in health care, with experiments like reading medical images, analyzing genomes, predicting kidney disease, and screening for eye problems caused by diabetes. Based on the 10-year partnership, “Google plans to unleash its deep AI expertise on Mayo’s colossal collection of clinical records. The tech giant also plans to establish an office in Rochester, Minnesota, to support the partnership, but declined to say how many employees will staff it or when it will open.”
To overcome possible regulatory and legal problems that Google has previously had, like the one with “an app called Streams that its DeepMind subsidiary is developing into an AI-powered assistant for doctors and nurses,” Mayo Clinic has announced that“Google will be contractually prohibited from combining Mayo clinical data with any other datasets, according to a hospital spokesperson. That means that whatever data Google has about a person through its consumer-facing services, such as Gmail, Google Maps, and YouTube, can’t be combined with caches of scrubbed Mayo medical records.”