Deep learning models detect prenatal stress from ECG signals

Researchers have developed a novel method for detecting prenatal stress using self-supervised deep learning on electrocardiography (ECG) data. The system, trained on the FELICITy 1 cohort, demonstrated high accuracy in classifying stress levels from maternal, fetal, and abdominal ECG signals. External validation on the FELICITy 2 cohort showed promising results, with signal quality-based channel selection proving more effective than averaging. AI

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

IMPACT Introduces a new objective method for assessing prenatal stress, potentially improving monitoring and intervention strategies in obstetrics.

RANK_REASON Academic paper detailing a new deep learning approach for a specific medical application.

Read on arXiv cs.LG →

• arXiv
• FELICITy 1
• ResNet-34
• SimCLR
• FELICITy 2
• ECG
• PSS-10

• paper
• other