New study finds health chatbot decreases uncertainty among patients

The JAMA study also found that patients employing Buoy Health's tool reduced the level of urgency they originally associated with their condition.
By Laura Lovett
11:49 am

While the default in amateur diagnostics has become a quick Google search, increasingly innovators are looking to curb potential health misinformation pitfalls. New research published last week by JAMA found that Buoy Health's free chatbot helped decrease the rate of uncertainty among patients. 

The study also found that patients using the platform were more likely to decrease their intended level of care after using the technology. 

"We're excited to have our results published — clearing patient confusion and reducing unnecessary ER/urgent care visits have big implications as healthcare costs continue to rise,” Dr. Andrew Le, CEO and cofounder of Buoy Health told MobiHealthNews in an email. “That said, we will be working on follow-on studies, always focused on proving our outcomes and safety. We believe in peer-reviewed science and will continue to pursue transparency."


Researchers found that the rate of uncertainty among patients about their health concern decreased from 34% to 21% after using the technology. Overall, 32% of users reduced the urgency of their intended level of care, 65% reported that the urgency of their care remained the same and 4% increased the urgency of care. 

Reproductive health was the top reason that patients used the service (18%), followed by general (17%) and gastrointestinal (15%) conditions.


Researchers looked at a data set of 158,083 interactions with Buoy Health. Patients could tap into the free chatbot and list any concerns or symptoms. At the beginning of the encounter users were asked their intended level of care, which gave users a list of seven options including emergency room care, urgent care, primary care, telemedicine, self-treatment, wait and watch and uncertain. Users were asked the same question again at the end of their visit.

“We used descriptive statistics to examine intended behavior by comparing patients’ preencounter and post-encounter intent level of care,” researchers wrote in the study. “To assess the tool’s association with care seeking, we removed uncertain responses and examined whether their intended level of care increased or decreased." 


Healthcare chatbots are becoming an increasingly popular way for patients to get a quick triage at home, and in the past few years Buoy has made some high-profile partnerships.

Last February it announced that its Cooperate Health and Benefits Program will include specialized knowledge and service support from Workit Health, Hing Health, LetsGetChecked, Healthcare Bluebook and CirrusMD. 

It is also working with Boston Children’s Hospital to create a white-labeled version of its product for the health center’s website, use data from that version to improve its product’s pediatric expertise and even get help from doctors at the Boston health center to evaluate its algorithms.

But Buoy is far from the only healthcare chatbot. One of the other big players in the field is Babylon Health, an AI-enabled triage chatbot. Babylon has teamed up with several government health systems including the UK’s NHS and Rwanda’s health service. Babylon Health is now lining up strategic partners as it targets a US launch of its triage chatbot service sometime this month. 

However, Babylon has had its critics, specifically, the company came under fire after it announced its AI could outperform UK medical students — leading to a backlash from the Royal College of General Practitioners. 


“The study suggests that virtual triage tools are associated with patients’ intended behavior when seeking care based on triage questions,” authors of the study wrote. “Reduced urgency of intended level of care for many interactions is different from many other direct-to-consumer telehealth solutions, which have reported the same or an increased demand for care services.” 

More regional news


The latest news in digital health delivered daily to your inbox.

Thank you for subscribing!
Error! Something went wrong!