10.01.2025

A newly developed AI-powered tool, PlacentaVision, could improve neonatal and maternal care by analyzing placentas immediately after birth. This advancement addresses a frequently overlooked issue: the discarding of placentas without examination.

PlacentaVision analyzes photographs of placentas to identify abnormalities associated with serious conditions, such as neonatal sepsis. This condition affects millions of newborns annually, often leading to severe complications or death if not treated promptly.

Image: Placenta shortly after birth on a white background

Development of the AI tool for placental analysis, including a unified model for multiple tasks, pathology reports, robustness assessment, and cross-country validation.

Products and exhibitors on this topic

Exhibitors and products related to this topic can be found in the database of COMPAMED:

Further exciting articles from the COMPAMED-tradefair.com editorial team:

Dr. Jeffery Goldstein, director of perinatal pathology at Northwestern University, highlighted the importance of the tool: “When the neonatal intensive care unit is treating a sick kid, even a few minutes can make a difference in medical decision making. With a diagnosis from these photographs, we can have an answer days earlier than we would in our normal process.”

PlacentaVision could prove particularly beneficial in:

Low-resource settings: Helping doctors without access to pathology labs quickly identify issues.

Well-equipped hospitals: Allowing healthcare providers to prioritize placentas requiring detailed examination, optimizing time and resources.

Bridging the gap in global health care

The study was led by Alison D. Gernand, associate professor at Penn State College of Health and Human Development. She emphasized the critical need for examining placentas: “Discarding the placenta without examination is a common but often overlooked problem. It is a missed opportunity to identify concerns and provide early intervention that can reduce complications and improve outcomes for both the mother and the baby.”

The tool offers solutions in diverse healthcare settings:

Administering antibiotics promptly to mothers and newborns in case of infection.

Reducing the gap in diagnostic capabilities between high- and low-resource areas.

Advancing AI for placental analysis

PlacentaVision was built using cross-modal contrastive learning, aligning visual data (placental images) with textual data (pathological reports). Researchers collected and analyzed a 12-year dataset, simulating various imaging conditions to ensure the model’s robustness. This tool’s versatility was further validated across different populations.

The next steps involve developing a mobile app for healthcare professionals. This app will:

Require minimal training.

Provide immediate diagnostic feedback.

Enhance clinical decision-making, especially in under-resourced areas.

The team aims to expand the tool’s capabilities, integrating additional clinical data and placental features to improve predictions. Testing in diverse settings will ensure reliable performance.

MEDICA-tradefair.com; Source: Northwestern University

More about Northwestern University at: www.northwestern.edu