Overview
ORACLE-AI is a single-center, open-label, randomized clinical trial comparing primiparous women managed with a real-time machine-learning dashboard against a concurrent control group receiving standard intrapartum care. Participants are randomized 1:1 at the onset of labor. The intervention group has the AI dashboard visible in their electronic health record, while the control group does not. The primary hypothesis is that the use of continuous AI-based risk estimates will be non-inferior to standard care in terms of unplanned cesarean\–delivery rates (uCD), with potential secondary benefits in maternal and neonatal outcomes.
Eligibility
Inclusion Criteria:
- Age ≥ 18 years at the time of consent
- Able and willing to provide written informed consent
- Nulliparous (no prior birth ≥ 24 weeks' gestation)
- Singleton live pregnancy
- Cephalic (vertex) fetal presentation
- Gestational age ≥ 37+0 weeks
- Admitted to the labor ward in labor (cervical dilation ≥ 3 cm with regular contractions) or undergoing induction or augmentation of labor with intent to proceed to vaginal delivery
- Planned trial of labor (no scheduled or elective cesarean delivery)
- Receiving intrapartum care at Hadassah-Hebrew University Medical Center, Mount Scopus campus
Exclusion Criteria:
- Planned or elective cesarean delivery prior to labor admission
- Multifetal gestation
- Non-cephalic fetal presentation
- Gestational age \< 37+0 weeks
- Major fetal anomaly expected to affect labor or neonatal management
- Contraindication to vaginal delivery (e.g., placenta previa, invasive placentation, prior uterine surgery precluding labor)
- Category III fetal heart rate tracing on admission requiring immediate delivery
- Maternal hemodynamic instability or other life-threatening condition necessitating urgent surgical or critical-care intervention
- Inability to provide informed consent due to cognitive impairment, intoxication, or other incapacity
- Concurrent participation in another interventional obstetric study that could confound outcomes or increase risk
