⌘+K

Pulse Explore Communities Researchers Journals

Home Communities Explore

May 23, 2026Ultrasound in Obstetrics and Gynecology

Bias in AI models for fetal cardiac screening: the consequences of training predominantly on normal anatomy

R. Besson N. Fries Y. Oyelese A. Khalil J. Stirnemann Y. Ville Collaborators

View at Publisher

Ask AI

Bookmark

Share

Key Points

The study aims to investigate how training AI models predominantly on normal fetal anatomy affects diagnostic accuracy.
Examined AI models trained on datasets with majority normal anatomy
Compared model performance on normal and abnormal fetal cardiac images
AI models showed decreased accuracy in identifying abnormal cardiology conditions
Performance impacted significantly when tested on non-normal fetal images

No abstract yet

We only have this paper's title and publication details.

Read it at the source→

Implication

Examines bias in AI models for fetal cardiac screening, suggesting implications for training data.

Abstract

Research data are not shared.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Besson et al. (2026) studied this question.

synapsesocial.com/papers/6a13e83b0e02ee3982d32f55 https://doi.org/10.1002/uog.70236

View at Publisher

Ask AI

Bookmark

Share

Keep reading

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

1From Cardiac Morphology to Fibrotic Systems Biology: Rethinking Prenatal <scp>AI</scp> Models for Hypoplastic Left Heart Syndromereview · 2026
2<scp>AI</scp> ‐Driven Analysis of the Fetal Left Ventricular Outflow TractReview · 2026 · 1 citations
3Automatic Segmentation of 15 Critical Anatomical Labels and Measurements of the Cardiac Axis and Cardiothoracic Ratio in Fetal Four Chambers Using nnU-NetV22024 · 2 citations
4Artificial Intelligence-Based Automated Assessment of the Four-Chamber View in Fetal Cardiac Ultrasound VideosOriginal Research · 2026 · 1 citations
5Role of artificial‐intelligence‐assisted automated cardiac biometrics in prenatal screening for coarctation of aorta2024 · 33 citations

More related papers

Ai-Based Predictive Modeling For Classification Of Fetal Health Conditions2026
Artificial intelligence aided ultrasound imaging of foetal congenital heart disease: A scoping review2025
Artificial Intelligence to Assist in the Screening Fetal Anomaly Ultrasound Scan (PROMETHEUS): A Randomised Controlled Trial2024

More from Ultrasound in Obstetrics and Gynecology

Association of quantitative vascularization of the anterior fornix/cervix region with placenta accreta spectrum and associated intraoperative hemorrhageSun,
Regional growth patterns of fetal corpus callosum at 18–32 weeks' gestation assessed by three‐dimensional transvaginal neurosonographyWed,