While more healthcare providers turned to chatbots for patient triaging during the COVID-19 pandemic, researchers say the technologies powering these virtual assistants still need advancing before coming close to imitating a physician's brain, The Washington Post reported.
Salt Lake City-based Intermountain Healthcare rolled out artificial intelligence chatbot Scout in March 2020 to navigate calls and concerns from people who were worried they had COVID-19. Health tech company Gyant created the chatbot.
After a successful launch, the health system added a symptom-checker to the assistant in June 2020, which asks patients about 30 questions to narrow in on symptoms, such as how bad their headache is, and then set up an appointment or advise them to visit urgent care.
Intermountain hopes to eventually add a way to have a "doctor's visit" with Scout, where the chatbot would provide care that is quickly reviewed and verified by a real, human physician, according to the report.
Developing a capability such as a physician's visit touches on a big challenge healthcare AI developers have been facing: data. Developers often have to use clinical texts and literature as well as some publicly available databases until they can find their own information and case studies from users.
Developer companies also are careful to market their chatbots as not actually diagnosing patients, but instead pointing them to the correct next steps, whether it's an emergency room or a good night of rest, Dr. Sven Laumer, a professor of information systems at the Friedrich-Alexander University of Erlangen Nuremberg, told the Post.
"They do not want to take over this responsibility," he said. "This is a big challenge for all digital healthcare services."