November 3, 2026 · American journal of obstetrics & gynecology MFM · DOI: 10.1016/j.ajogmf.2026.102189

HypoxIA: A bicenter study of machine learning-based prediction of fetal hypoxia using fetal heart rate and obstetric features.

Listen to this summary

This bicenter study of 3,574 singleton deliveries asked whether a machine learning model combining intrapartum cardiotocography (CTG) signals with routine clinical data could predict neonatal acidemia (umbilical arterial pH <7.15) and severe acidemia (pH <7.05). The model performed best for severe acidemia (AUC 0.78 in the final hour before birth) and, at the same false-positive rate as clinical practice, achieved higher sensitivity than clinical intervention for severe acidemia. Explainability analysis showed that CTG-derived features drove predictions while clinical variables added little, suggesting explainable AI may support CTG interpretation during labor.

Pauline Olgiati, Romain Bardon, Gaël Bueno-Barthe, Françoise Vendittelli, Didier Riethmuller, David Desseauve

This is one of 33,000+ journals available on OSLR. Try it free for 14 days.

Free 14-day trial. 33,000+ journals. Cancel anytime.

14-day free trial. No commitment.

“

"Oslr has become part of my weekly routine on my day off. The clinical relevance of the summaries is outstanding — I'd rate it 9/10. Being able to consume research hands-free is a huge advantage for busy physicians."

Dr. Jennifer Thompson

Dr. Jennifer Thompson

Portland, OR

Stay current without falling behind

33,000+ journals. 3-minute audio summaries. Free for 14 days.

Download on the App StoreGet it on Google Play