The image is a photo illustration by Mairo Cinquetti.
According to a new study, a chatbot may help reduce the likelihood of an eating disorder. A dialogue with a bot developed by researchers reduced concern over body weight and shape for women at high risk for an eating disorder.
Ellen Fitzsimmons-Craft, an assistant professor of Psychiatry at Washington University School of Medicine, says that previous research shows that digital prevention programs are more effective when they are guided by a human. It is difficult to get funding for programs that prevent mental health conditions. Fitzsimmons-Craft says that the team thought a cheaper, more scaleable version of a program that offers some aspects of moderation in an automated format was a good idea.
The StudentBodies eating disorder prevention program is usually delivered through a website and includes informational content, exercises, and journal prompts. The participants could use the chatbot.
The study recruited female participants through online ads, fliers, and the National Eating Disorder Association online eating disorder screening test, which is available to anyone on the organization's website. Women who did not have an active eating disorder but had risk factors for one, like negative body image or excessive concern about their weight, were randomly assigned to either engage with the chatbot or sit on a wait list. Women who used the bot were encouraged to have two of the eight conversations each week, and the bot offered eight conversations about body image and healthy eating.
Women who talked to the chatbot had a bigger drop in their concerns about their weight and body shape than women who were on the waiting list. The study found that women in the chatbot group were less likely to develop a clinical eating disorder by the end of the six months than women in the waitlist group. Fitzsimmons-Craft says that this could have a great public health impact if we can continue to find ways to spread it.
Even though they are widely used in medical settings to assist with everything from COVID-19 symptom screening to therapy, this is the first study to test the effectiveness of chatbot in healthcare. There is a growing body of work showing the role research can play in healthcare.
Fitzimmons-Craft thinks that the one her team developed could be used in places where people are likely to start showing signs of an eating disorder. People who show risk factors could be directed toward a clinical disorder if the chatbot is designed for them.
Fitzimmons-Craft says that it is possible to identify people who are at risk for an eating disorder through their web search history. The platforms are linked to body image issues for teen girls. Partnering with platforms like Google orInstagram could help flag behaviors that show someone is at risk, and pair them with the bot. She thinks that is worth exploring. It is ripe for identifying individuals who could use help with these issues and intervening on the spot.
Fitzimmons-Craft says that there are other types of mental health issues where prevention is important. They aren't going to be right for everyone, but they're cheap and easy to use. It might be hard to get funding for involved prevention tools for people who don't have an active disorder. She says that at-risk groups could still benefit from being pushed away from a problem. It might be the right thing for someone who doesn't really want or even need help, who was high risk in our study, and who didn't have a clinical problem.
