Dr. Christopher Picard queries personal devices on symptons and asks for advice. (source: video still from City News of Winnipeg, Canada)

Dr. Google May Not Be Able to Save Users in a Medical Crisis

The huge advancements in many medical fields using AI has been, in a word, remarkable. AI has outstripped many human doctors and scientists in assessing medical data. AI finds tumors or cancers in MRIs and CAT scans missed by human eyes. Even robotic surgery driven by AI is pretty common these days.

Many companies are investing in digital medical advice given online or over the phone. While it is an exciting prospect resulting in shortened wait times and less expensive office visits, it’s not quite ready for prime time. Or so says an article by Gillian Rutherford on folio.ca.

Canadian researchers at the University of Alberta released a study casting doubt on digital medical advice.

“We were hoping to find that the devices would have a better response rate, especially to statements like ‘someone is dying’ and ‘I want to die,’ versus things like ‘I have a sunburn or a sliver,’” said lead author Christopher Picard, a master’s student in the Faculty of Nursing and a clinical educator at Edmonton’s Misericordia Community Hospital emergency department. “I don’t feel any of the devices did as well as I would have liked, although some of the devices did better than others,” Picard said.

The researchers tested four commonly used devices—Alexa, Google Home, Siri and Cortana—using 123 questions about 39 first aid topics from the Canadian Red Cross Comprehensive Guide for First Aid, including heart attacks, poisoning, nosebleed and slivers. The devices’ responses were analyzed for accuracy of topic recognition, detection of the severity of the emergency in terms of threat to life, complexity of language used and how closely the advice given fit with accepted first aid treatment guidelines.

Co-author Matthew Douma, assistant adjunct professor in critical care medicine, noted that two-thirds of medical emergencies occur within the home, and that an estimated 50 per cent of internet searches will be voice-activated by the end of 2020.

The exciting part of this article is that medical assistants will soon be as close as saying, “Alexa I need to speak to a doctor.” However, it’s still not at the level of personalized health care.

You can find out how the various assistants did by reading Rutherford’s full article. But keep in mind the words of the co-author of the study:

“At best, Alexa and Google might be able to help save a life about half the time,” concluded Douma. “For now, people should still keep calling 911 but in the future help might be a little closer.”

When it comes to rote tasks, however, machine learning virtual assistants are valuable to the medical field, according to a story in Medical Product Outsourcing magazine. Devices can do six things well: transcription, medical record keeping, radiology diagnostics, patient wellbeing checks, recovery and discharge assistance, and being a healthcare companion. It’s a burgeoning field with dozens of start-up companies racing to fill the need.

But the average consumers’ personal assistant as a medical guide? Not so much.

read more at folio.ca