$3.7M NIH Grant Supports Development of Chatbot to Help New Moms, Babies

New parents have always looked to grandma, a more-experienced friend or books like “What to Expect When You’re Expecting” to navigate the uncertainties of caring for a baby. The next generation of parents could also look to their phones for reliable guidance on hundreds of child care topics, thanks to a chatbot that University of Maryland researchers are developing.

Supported by a $3.7 million grant from the National Institutes of Health, the tech-enabled tool known as Rosie is intended to reduce postpartum depression among new moms and improve infant health with immediate, individualized and accurate information that eliminates the need for new moms to go down a Google rabbit hole late at night while dealing with an unfamiliar situation, and potentially being misled by the resources they find.

The service will be able to provide information about important topics about the first year of life through an app or text interface, said researchers Quynh Nguyen, an associate professor of epidemiology and biostatistics, and Elizabeth Aparicio, assistant professor of behavioral and community health.

Although the app has big-picture aims—addressing racial or socioeconomic disparities in postpartum care, prompting well-baby visit attendance and reducing the number of emergency room visits—it’s designed to be as immediately helpful as its namesake, the Jetsons’ dependable robot maid.

“It'll only return what she requests, so if she says, ‘What does a fever look like in my baby?’ or ‘What immunizations does my baby get for visit five?’ then the chatbot will return just what she's asking for,” said Nguyen, principal investigator on the grant.

Both researchers are mothers, and they came up with the idea while discussing the stressors of new parenthood over coffee. Co-principal investigator Aparicio, whose children are 8 and 10, said she could have benefitted from a service like Rosie.

“I can remember it like it was yesterday, those times in the middle of the night where you're just really stressed out and feel so alone and tired,” she said.

Still in its early stages, the building and development of Rosie is an open-source project, meaning other other researchers could help further develop and use the technology. And, unlike services like Amazon’s Alexa, the researchers are working to make sure that information isn’t collected by for-profit companies.

Nothing like Rosie currently exists, in part because of the interdisciplinary nature of the approach, including experts in computer science, biostatistics, and maternal and child health Nguyen said.

“It takes collaboration between someone who's in the community, it takes somebody who can build the chatbot because it takes computer science programming, and it takes a public health perspective to try to see what outcomes could be moved,” she said. “So you really do have to have an interdisciplinary team to carry out this project and not be siloed, and interdisciplinary teams are still more rare than not.”

In addition to providing advice, Rosie is also being programmed to recognize interactions that indicate postpartum anxiety or depression, in which case the system will offers advice for how to cope at that moment. The researchers will then follow up directly to provide guidance for seeking help to study participants who need it.

“We don’t want people to feel alone or unconnected in those moments,” Aparicio said. “Postpartum anxiety and depression are very, very common, and a lot of people don’t know that. They think ‘Oh, I should just feel joyful and glad. These times are precious, everyone says, enjoy this time.’”

Nguyen and Aparicio will spend the first year of the five-year grant developing the chatbot, including making sure it can answer questions asked in a variety of ways.

Once the chatbot is fully developed, Aparicio and Nguyen will spend the next four years evaluating the outcomes of a treatment group that will have access to Rosie compared to a control group that will not. If the chatbot is found to be effective, the research team will work on scaling up its reach to a broader audience.

Original story written by Katherine Seltzer