AI model AutoHyPE detects maternal hypertension using fetal ultrasound data

Researchers have developed AutoHyPE, a novel hierarchical attention network designed to detect maternal hypertension by analyzing fetal hemodynamics from ultrasound recordings. This system utilizes prototype-based contrastive learning and a multi-view strategy to improve representation robustness, achieving an AUROC of 0.80 in detecting maternal hypertension. The findings suggest that fetal cardiac activity can encode indicators of maternal hypertension, potentially enabling continuous, objective monitoring of maternal health with existing ultrasound technology. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Introduces a novel AI approach for continuous, objective maternal health monitoring using ultrasound data.

RANK_REASON Academic paper detailing a new model and its performance on a specific task. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• AutoHyPE
• Guatemala
• arXiv

• paper
• other