AI helps pathologists find signs of preeclampsia, advancing diagnosis and treatment
MedicinePublic HealthBiomedical Engineering
THE AI ANGLE
Screening placental blood vessels and calculating explainable cellular morphology scores to flag preeclampsia riskResearchers at Carnegie Mellon University and UPMC developed an explainable machine learning model to detect decidual vasculopathy, a placental blood vessel disease linked to postpartum preeclampsia. By analyzing the spatial organization of extravillous trophoblast cells and red blood cells, the algorithm generates a morphology separation score to explain its findings and flag high-risk cases for specialist review. This tool addresses a critical public health bottleneck caused by a shortage of perinatal pathologists, which currently leaves fewer than 20% of U.S. placentas screened after delivery.
THE TEACHING ANGLE
Instructors can explore how engineering explainable metrics—such as morphology separation scores—helps resolve the tension between deploying automated screening tools to relieve workforce shortages and maintaining clinical trustworthiness without relying on 'black box' algorithms.Read the original at medicalxpress.com Generate teaching or study materials
More in Medicine
- Report covers advances in surgical robots, deploying warehouse automation in the real worldThe Robot Report · September 15, 2026
- AI models enable cross-species mapping of cell biologyPhys.org — Biology · September 15, 2026
- Patient identity is the missing control in healthcare AIHealthcare Dive · September 14, 2026