Apr 8 2021
Symptom checkers driven by artificial intelligence (AI) can potentially minimize the number of people visiting the in-person clinics during the pandemic. However, according to researchers, people must first know they exist.
Image Credit: Andrii Vodolazhskyi/shutterstock.com
COVID symptom checkers are digital self-assessment tools in which AI is used to help users find their level of COVID-19 risk and evaluate whether they must seek emergent care based on the symptoms they reported. The aim of these tools is also to offer reassurance to people who experience symptoms not associated with COVID-19.
A majority of the platforms, such as Isabel and Babylon, are public-facing tools. However, the University of California, San Francisco (UCSF) has developed one of the first COVID-19 symptom checkers fully combined with the medical records of users, thus enabling instant appointment scheduling.
Researchers from the University of Waterloo performed a mixed-methods study and identified that young adults aged between 18 and 34 years, essentially the first age group to adopt new technologies, were not aware of the occurrence of such platforms.
Young adults are usually eager adopters of technology, so we were a little surprised by this finding. 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.
Stephanie Aboueid, Study Lead Researcher and PhD Candidate, School of Public Health and Health Systems, University of Waterloo
In total, 22 university students were interviewed in the spring and winter of 2020.
Of them, nine were not aware that the tools exist. In winter 2021, the team also performed a survey on general symptom checkers, and the data indicated that 88% (1,365 out of 1,545) of the participants did not use a symptom checker in the previous year.
The results of the smaller qualitative study indicate that three-quarters of those who had used government-issued symptom checkers were satisfied with them.
Those who used symptom checkers not issued by the government found the experience sub-standard and cited a lack of trust and credibility.
One of the findings was that users wanted more personalization and were less trusting of tools that gave the same results to everyone. 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.
Stephanie Aboueid, Study Lead Researcher and PhD Candidate, School of Public Health and Health Systems, University of Waterloo
Apart from more personalization, the team identified that other optimizations of existing symptom checkers are to offer users more information related to the developers of the platform, thus offering more language options, more explanation of the symptoms in lay language, and the option to undergo tests at a closeby location.
Journal Reference:
Aboueid, S., et al. (2021) Use of symptom checkers for COVID-19-related symptoms among university students: a qualitative study. BMJ Innovations. doi.org/10.1136/bmjinnov-2020-000498.