Large language models (LLMs) can synthesize vast amounts of information. Luo et al. show that LLMs—especially BrainGPT, an LLM the authors tuned on the neuroscience literature—outperform experts in predicting neuroscience results and could assist scientists in making future discoveries.

The use of antidepressants during pregnancy significantly increased the risk of a child experiencing functional constipation—a common DGBI that may be painful—during their first year of life. “After adjusting for covariates, SSRI/SNRI exposure was associated with an over 3-fold increased risk for functional constipation,” the investigators wrote.

“We found that, at the age of one, 63% of children exposed to antidepressants during pregnancy experienced constipation, compared with 31% of children whose mothers did not take medication,” said study co-author Larissa Takser, MD, professor of pediatrics at the Université de Sherbrooke in Québec. “This finding suggests a potential connection between serotonin levels in utero and gut development, and opens new doors to examine SSRI properties not previously studied.”

The investigators’ collective findings point to a promising avenue of future studies: the gut epithelium as a new and potentially safer target for treating mood disorders, particularly for pregnant women. “Together, these data define a novel potential mechanism for gut-brain communication and identify intestinal epithelial 5-HT as a new and potentially safer therapeutic target for mood regulation,” the authors stated.