AI Tool Can Help Healthcare Systems Deal With COVID-19 Burden

Killian Meara

Killian Meara, assistant editor for ContagionLive, joined the MJH Life Sciences team in November 2020. He graduated from William Paterson University with a degree in liberal studies, and concentrations in history and psychology. He enjoys film, reading, and pretending he is a good cook. Follow him on Twitter @krmeara or email him at [email protected]

While symptom checkers have the potential to significantly help with overburdened systems, not enough people know about them.

AI-powered symptom checkers could reduce the number of individuals visiting in-person clinics, reducing their burden caused by the pandemic. The symptom checkers are a way to digitally self-assess a person’s COVID-19 risk, and whether or not they should seek urgent care.

However, a recent study conducted by investigators from the University of California, San Francisco, has found that not many people know of these tool’s existence. Results from the study were published in the journal BMJ Innovations.

"One of the findings was that users wanted more personalization and were less trusting of tools that gave the same results to everyone," Stephanie Aboueid, a PhD candidate in the School of Public Health and Health Systems said. "The UCSF system was able to reduce the number of visits while taking into account underlying conditions along with the symptom checks and booking follow-up appointments when needed."

For the study, investigators use a mixed-methods approach. One part of the study was an interview with 22 university students, with the second part being a survey on general symptom checkers.

Findings from the study demonstrated that of the 22 interviewees, 9 of them had never heard of the symptom checking tools. From the survey, investigators discovered that 88% of participants had not used a tool within the last year.

Additionally, findings from a smaller qualitative study suggested that three-quarters of people who had used symptom checkers issued by the government were satisfied with them, while the majority of those who used non-government issued checkers did not trust their credibility.

"Young adults are usually eager adopters of technology, so we were a little surprised by this finding," Aboueid said. "Symptom checkers have the potential to reduce the burden on health-care systems and the risk of person-to-person infection, so we wanted to find out how to improve these platforms so more people use them."