Machine learning model helps identify patients at risk of postpartum depression
Peer-Reviewed Publication
Updates every hour. Last Updated: 9-Aug-2025 11:11 ET (9-Aug-2025 15:11 GMT/UTC)
Postpartum depression (PPD) affects up to 15 percent of individuals after childbirth. Early identification of patients at risk of PPD could improve proactive mental health support. Mass General Brigham researchers developed a machine learning model that can evaluate patients’ PPD risk using readily accessible clinical and demographic factors. Findings demonstrating the model’s promising predictive capabilities are published in the American Journal of Psychiatry.
Results from a recent multi-center, randomized, controlled trial demonstrate that testosterone gel does not improve physical function compared to exercise alone in older women recovering from a hip fracture. The STEP-HI study was published in JAMA Open and is the largest such study of testosterone administration to women following a fracture of the hip.
Virginia Tech researchers at the Fralin Biomedical Research Institute have discovered that microscopic structural changes in the aging heart may help prevent irregular heartbeats. The discovery challenges the idea that all age-related heart changes are harmful.
Researchers have discovered a new molecular process that occurs when donor hearts are preserved in cold storage which contributes to failure after transplant, a study in both humans and animals shows. The team also found a therapy to reduce that damage using medication that is typically prescribed for high blood pressure. This discovery has potential to improve the consistent function of donor hearts and extend the distance they can be safely transported in cold storage.