Obstetric Risk Assessment & Cesarean-delivery in Labor Estimation Using Artificial Intelligence

Official title

Obstetric Risk Assessment & Cesarean-delivery in Labor Estimation Using Artificial Intelligence Trial (ORACLE-AI)

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.

Interventions

• Device Software-based, real-time AI dashboard providing continuous risk estimates for unplanned cesarean delivery during labor.
  The intervention is a software-based, real-time clinical decision-support dashboard (ORACLE-AI) integrated into the electronic health record and used during intrapartum care. The system continuously analyzes admission characteristics and dynamic labor data, including serial cervical examinations, uterine activity, and cardiotocography (CTG) annotations, to generate individualized estimates of the probability of unplanned cesarean delivery. Risk estimates are updated automatically every 5-7 minut

Primary outcome measures

• Primary Endpoint: unplanned cesarean delivery rates. [Time frame: From randomization at labor admission to delivery (time of birth), up to 7 days.]

Secondary outcome measures (12)

• Postpartum Hemorrhage [Time frame: From delivery (time of birth) through maternal hospital discharge, up to 30 days.]
• Maternal ICU Admission [Time frame: From delivery (time of birth) through maternal hospital discharge, up to 30 days.]
• Chorioamnionitis [Time frame: From randomization at labor admission through maternal hospital discharge, up to 30 days.]
• Advanced Perineal Tear [Time frame: At delivery (time of birth), within 7 days of randomization.]
• Length of Maternal Hospitalization [Time frame: From delivery (time of birth) through maternal hospital discharge, up to 30 days.]
• Maternal mortality [Time frame: From delivery (time of birth) through maternal hospital discharge, up to 30 days.]
• Neonatal Mortality [Time frame: From birth through neonatal hospital discharge, up to 30 days.]
• Low Apgar Score [Time frame: At 1 minute and 5 minutes after birth.]
• Umbilical Cord Arterial pH < 7.10 [Time frame: At birth.]
• Neonatal Intensive Care Unit Admission [Time frame: From birth through neonatal hospital discharge, up to 30 days.]
• Neonatal Mechanical Ventilation [Time frame: From birth through neonatal hospital discharge, up to 30 days.]
• Length of Neonatal Hospitalization [Time frame: From birth through neonatal hospital discharge, up to 30 days.]

Eligibility criteria

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

Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.

Healthy volunteers: Yes

Study design

Allocation

Randomized

Model

Parallel assignment

Masking

Double blind

Primary purpose

Supportive care

Study locations

Israel · 1 center

• Hadassah Mt. Scopus Hebrew University Medical Center — Jerusalem

Publications

• Huurnink JME, Blix E, Hals E, Kaasen A, Bernitz S, Lavender T, Ahlberg M, Oian P, Hoifodt AI, Miltenburg AS, Pay ASD. Labor curves based on cervical dilatation over time and their accuracy and effectiveness: A systematic scoping review. PLoS One. 2024 Mar 22;19(3):e0298046. doi: 10.1371/journal.pone.0298046. eCollection 2024. PMID 38517902
• Alfirevic Z, Devane D, Gyte GM, Cuthbert A. Continuous cardiotocography (CTG) as a form of electronic fetal monitoring (EFM) for fetal assessment during labour. Cochrane Database Syst Rev. 2017 Feb 3;2(2):CD006066. doi: 10.1002/14651858.CD006066.pub3. PMID 28157275
• Guedalia J, Lipschuetz M, Novoselsky-Persky M, Cohen SM, Rottenstreich A, Levin G, Yagel S, Unger R, Sompolinsky Y. Real-time data analysis using a machine learning model significantly improves prediction of successful vaginal deliveries. Am J Obstet Gynecol. 2020 Sep;223(3):437.e1-437.e15. doi: 10.1016/j.ajog.2020.05.025. Epub 2020 May 17. PMID 32434000
• Wong MS, Wells M, Zamanzadeh D, Akre S, Pevnick JM, Bui AAT, Gregory KD. Applying Automated Machine Learning to Predict Mode of Delivery Using Ongoing Intrapartum Data in Laboring Patients. Am J Perinatol. 2024 May;41(S 01):e412-e419. doi: 10.1055/a-1885-1697. Epub 2022 Jun 25. PMID 35752169
• Burke N, Burke G, Breathnach F, McAuliffe F, Morrison JJ, Turner M, Dornan S, Higgins JR, Cotter A, Geary M, McParland P, Daly S, Cody F, Dicker P, Tully E, Malone FD; Perinatal Ireland Research Consortium. Prediction of cesarean delivery in the term nulliparous woman: results from the prospective, multicenter Genesis study. Am J Obstet Gynecol. 2017 Jun;216(6):598.e1-598.e11. doi: 10.1016/j.ajog. PMID 28213060
• Wakefield BM, Zapf MA, Ende HB. Artificial intelligence in prediction of postpartum hemorrhage: a primer and review. Int J Obstet Anesth. 2025 Aug;63:104694. doi: 10.1016/j.ijoa.2025.104694. Epub 2025 Jun 2. PMID 40527278
• Tsur A, Batsry L, Toussia-Cohen S, Rosenstein MG, Barak O, Brezinov Y, Yoeli-Ullman R, Sivan E, Sirota M, Druzin ML, Stevenson DK, Blumenfeld YJ, Aran D. Development and validation of a machine-learning model for prediction of shoulder dystocia. Ultrasound Obstet Gynecol. 2020 Oct;56(4):588-596. doi: 10.1002/uog.21878. PMID 31587401
• Guedalia J, Sompolinsky Y, Novoselsky Persky M, Cohen SM, Kabiri D, Yagel S, Unger R, Lipschuetz M. Prediction of severe adverse neonatal outcomes at the second stage of labour using machine learning: a retrospective cohort study. BJOG. 2021 Oct;128(11):1824-1832. doi: 10.1111/1471-0528.16700. Epub 2021 Apr 15. PMID 33713380

Identifiers

NCT: NCT07430358 · 0335-25- HMO-CTIL

Primary sources (government registries)

• ClinicalTrials.gov (US NIH)

View this study on ClinicalTrials.gov ↗