What question did this study set out to answer?

June 18, 2026Open Access

Artificial Intelligence in Obstetrics and Gynecologic Surgery Advancing Precision, Safety, and Patient-Centered Women's Healthcare

Key Points

This review aims to evaluate AI applications in obstetrics and gynecologic surgery and their clinical performance.
Conducted a systematic literature search across multiple databases for studies from 2018 to 2025.
Performed statistical meta-analysis on performance metrics like sensitivity and specificity across 147 studies.
Analyzed algorithm performance and market trends using descriptive and comparative statistics.
AI showed 94% sensitivity and 92% specificity for fetal heart defect detection.
Random Forest algorithms achieved 94.44% accuracy for cesarean section prediction with an AUC of 97.99%.
Robotic-assisted surgery had a 4.7% complication rate versus 12.3% for laparoscopic surgeries.

Abstract

Background: Artificial intelligence (AI) is rapidly transforming healthcare delivery, with significant implications for obstetrics and gynecology. The integration of machine learning, deep learning, and computer vision technologies offers unprecedented opportunities to enhance diagnostic accuracy, optimize surgical outcomes, and personalize patient care in women's health. Objectives: This comprehensive review examines the current state of AI applications in obstetrics and gynecologic surgery, evaluates its clinical performance through statistical meta-analysis, identifies implementation challenges, and outlines future research directions. Methods: A systematic literature search was conducted across PubMed, Scopus, Web of Science, and IEEE Xplore databases for studies published between 2018 and 2025. Statistical analysis was performed on aggregated performance metrics including sensitivity, specificity, AUC, and accuracy across 147 qualifying studies. Descriptive and comparative statistical methods were employed to analyze market trends and algorithm performance. Results: AI systems demonstrated exceptional diagnostic performance across OB/GYN applications: fetal heart defect detection (sensitivity 94%, specificity 92%), cervical cancer screening (accuracy 96%, AUC 0. 947), preeclampsia prediction (AUC 0. 920), and ovarian tumor classification (AUC 0. 910). The global AI healthcare market is projected to reach 744. 34 billion by 2035 (CAGR 35. 02%). Random Forest algorithms outperformed other machine learning models for cesarean section prediction with 94. 44% accuracy and AUC of 97. 99%. Robotic-assisted gynecologic surgery showed 4. 7% complication rates compared to 12. 3% for laparoscopic approaches. Conclusions: AI technologies demonstrate substantial potential to advance precision, safety, and patient-centered care in obstetrics and gynecology. However, addressing challenges related to algorithmic bias, data standardization, regulatory frameworks, and clinical integration remains essential for realizing the full transformative potential of AI in women's healthcare.

Read Full Paperexternally

Mark Helpful

Bookmark

Relay

View Full Paper