Mobile App Predicts Future Depression in Pregnant People

June 13, 2024

Tamar Krishnamurti, associate professor of medicine, School of Medicine, and of clinical and translational science, University of Pittsburgh. (Courtesy photo)

Depression is a leading complication during pregnancy with about 15% of patients reporting symptoms at some point during their pregnancy. But now, a simple first-trimester survey delivered through the MyHealthyPregnancy app can help predict the onset of moderate to severe depression.

Perinatal depression is linked with poor outcomes for mom and baby, including higher rates of preterm delivery, delayed infant development and problems with mother-child bonding. While a history of depression is a strong predictor of perinatal depression, this tool could help identify others who become depressed for the first time during pregnancy.

“We already have great screening tools for active depression, but our approach is unique because it predicts who is likely to develop depression in the future,” says lead author Tamar Krishnamurti, associate professor of medicine at Pitt, investigator at Magee-Womens Research Institute, and developer of MyHealthyPregnancy. “If we can identify people before symptoms emerge, we might be able to tailor preventive care and offer tools and support to address underlying triggers of depression.”

The new Archives of Women’s Mental Health study, led by University of Pittsburgh and UPMC researchers, analyzed data from 944 patients with no prior history of depression. During the first trimester, participants completed a survey that included questions about demographics, medical history, psychosocial factors (stress and sadness), and pregnancy-specific stressors (concerns about labor and delivery). A subset of these participants also completed additional survey questions that addressed health-related social factors like food insecurity. All participants also completed verified depression screenings once per trimester.

Of the six machine-learning models tested, the best predictive model (89% accuracy) used 14 variables, including anxiety history, partnered status, psychosocial factors and pregnancy-specific stressors. The team also worked with providers and perinatal individuals to review and refine the model to reflect professional and lived experiences. When including health-related social factors, food insecurity emerged as an important risk factor for depression, overpowering race and income, and increased the model’s predictive accuracy to 93%.

“We can ask people a small set of questions and get a good sense of whether they’ll become depressed,” said Krishnamurti. “Strikingly, a lot of risk factors for future depression are things that are modifiable—such as sleep quality, concerns about labor and delivery and, importantly, access to food—meaning that we can and should do something about them.”

Krishnamurti and her team are now developing ways to integrate these screening questions into clinical workflows and finding ways for clinicians to have conversations with patients about depression risk.

“For this information to be empowering and not anxiety-inducing, it’s important that it’s easy to understand and actionable,” says Krishnamurti. “Our focus now is not just on refining our ability to predict depression but also on improving and personalizing interventions so that they are most effective for any given individual.”

Interventions could include connecting patients with resources in their area, recommending in-person material support groups to address pregnancy-related stressors or offering virtual, app-based therapy options.  

Read more in the press release.