Gemini Flash 3.6 Versus Human Observers for FIGO-Based Interpretation of Intrapartum Cardiotocography: A Diagnostic Accuracy Study
试验速览
- 阶段
- 不适用
- 状态
- 尚未招募
- 入组人数
- 415
- 主要终点
- Sensitivity of Gemini Flash 3.6 for Identifying Neonates With a 5-Minute Apgar Score Less Than 7
研究概览
简要总结
Cardiotocography (CTG) is the standard method for monitoring fetal heart rate and uterine contractions during labor to detect signs of fetal hypoxia. However, human CTG interpretation is often subjective and subject to high interobserver variability, even among experienced clinicians. Multimodal artificial intelligence (AI) models have emerged as potential diagnostic aids capable of evaluating CTG tracings. This prospective diagnostic accuracy study aims to evaluate the diagnostic performance of Gemini Flash 3.6 in interpreting intrapartum CTG recordings according to the 2015 International Federation of Gynecology and Obstetrics (FIGO) guidelines, and to compare its accuracy directly against independent human expert obstetricians.
Participants include pregnant women admitted in active labor at term with a singleton cephalic pregnancy undergoing continuous CTG monitoring. De-identified digital images of the final 60 minutes of CTG tracing prior to delivery will be independently evaluated by Gemini Flash 3.6 and three expert obstetricians. Each evaluator will classify the tracings into one of three FIGO categories: Normal, Suspicious, or Pathological. All evaluators will be blinded to clinical details, delivery outcomes, and other observers' interpretations.
The primary objective is to assess the diagnostic sensitivity of Gemini Flash 3.6 in identifying neonates with a 5-minute Apgar score less than 7. Secondary objectives include comparing the diagnostic performance of the AI model with that of individual expert obstetricians, measuring interobserver agreement among all raters, and assessing associations with 1-minute Apgar scores and umbilical artery blood gas parameters. The AI model will be used solely as an investigational research tool, and its evaluations will not be available to the clinical team or used to guide patient care.
研究设计
- 研究类型
- Observational
- 观察模型
- Cohort
- 时间视角
- Prospective
入排标准
- 年龄范围
- 18 Years 至 —（Adult, Older Adult）
- 性别
- Female
- 接受健康志愿者
- 否
入选标准
- •Singleton pregnancy
- •Gestational age 37+0 weeks or greater
- •Cephalic fetal presentation
- •Admission to the labor ward in active labor
- •Continuous intrapartum cardiotocography (CTG) monitoring
- •Availability of an interpretable CTG tracing immediately preceding delivery
- •Availability of documented 1-minute and 5-minute Apgar scores
- •Written informed consent obtained prior to enrollment
排除标准
- •Multiple pregnancy
- •Major fetal congenital anomalies
- •Antepartum stillbirth
- •Elective cesarean delivery performed before the onset of labor without an adequate intrapartum CTG tracing
- •CTG tracing with inadequate technical quality, including signal loss of 15% or greater
- •Missing 5-minute Apgar score
- •Technical problems preventing standardized CTG image preparation or interpretation
研究组 & 干预措施
Intrapartum CTG Monitoring Cohort
Women with singleton term pregnancies (gestational age ≥ 37 + 0 weeks) in cephalic presentation admitted to the labor ward in active labor who undergo routine continuous intrapartum cardiotocography (CTG) monitoring immediately preceding delivery. De-identified digital CTG tracings from this cohort are independently evaluated by Gemini Flash 3.6 and three expert obstetricians according to the 2015 FIGO consensus guidelines, and validated against neonatal outcomes including 1-minute and 5-minute Apgar scores as well as umbilical artery blood-gas analysis where available.
结局指标
主要结局
Sensitivity of Gemini Flash 3.6 for Identifying Neonates With a 5-Minute Apgar Score Less Than 7
时间窗: 5 minutes after birth
Sensitivity is defined as the percentage of neonates with a confirmed 5-minute Apgar score less than 7 who are correctly identified as having a "Pathological" CTG tracing by Gemini Flash 3.6. Intrapartum CTG tracings from the final 60 minutes of labor immediately preceding delivery are interpreted according to the 2015 FIGO guidelines. For binary diagnostic performance analysis, a "Pathological" CTG represents a positive test result, while "Normal" and "Suspicious" CTGs represent negative test results. Sensitivity is calculated as \[True Positives / (True Positives + False Negatives)\] \* 100 and reported with a 95% confidence interval.
次要结局
未报告次要终点
研究者
Abdelrhman Ahmed Kamel
Resident of Gynecology and Obstetrics
Assiut University