EC Gynaecology

Background: Pediatric and Adolescent Gynecology (PAG) manages a spectrum of complex conditions ranging from congenital Mullerian anomalies to early-onset endometriosis. The diagnostic and surgical challenges inherent to this population often result in delayed care. Artificial Intelligence (AI) and digital health technologies have demonstrated significant potential in adult gynecology, yet their application in PAG remains largely unreviewed.

Objective: This narrative review synthesizes the current literature on AI and machine learning (ML) applications specifically relevant to the pediatric and adolescent gynecological population, identifying clinical gaps and future research directions.

Methods: A comprehensive literature search was conducted to identify studies utilizing AI, ML, or deep learning in the context of PAG conditions, including ovarian torsion, adolescent endometriosis, polycystic ovary syndrome (PCOS), central precocious puberty, and Mullerian duct anomalies.

Results: The literature demonstrates emerging AI applications in three primary domains. First, diagnostic imaging algorithms show high predictive accuracy (87 - 97%) in distinguishing pediatric ovarian torsion from appendicitis. Second, ML models utilizing electronic health record (EHR) data show promise in identifying high-risk cohorts for adolescent endometriosis and central precocious puberty, potentially mitigating the documented 7 - 10 years diagnostic delay. Third, early research suggests deep learning may enhance the classification of complex Mullerian anomalies on magnetic resonance imaging (MRI). However, significant gaps remain in the application of AI to surgical outcomes, postoperative fibrosis prediction, and the mitigation of health disparities in the adolescent population.

Conclusion: AI and digital health platforms hold transformative potential for PAG. Future research must prioritize the development of adolescent-specific algorithms, validated through multi-center trials, to enhance diagnostic precision and personalize surgical care.

Keywords: Pediatric and Adolescent Gynecology (PAG); Artificial Intelligence (AI); Machine Learning (ML); Electronic Health Record (EHR); Magnetic Resonance Imaging (MRI)

1. Hillard PJA. “Artificial intelligence (AI) and The Journal of Pediatric and Adolescent Gynecology (JPAG)”. The Journal of Pediatric and Adolescent Gynecology (2025).
2. Cassandra N Simpson., et al. “Combating diagnostic delay of endometriosis in adolescents via education”. Cureus 5 (2021): e15143.
3. Patel DJ., et al. “Artificial intelligence in obstetrics and gynecology”. Cureus 7 (2024): e64725.
4. Otjen JP., et al. “Ovarian torsion: developing a machine-learned algorithm from sonographic features”. Pediatric Radiology 5 (2020): 706-714.
5. Turki A., et al. “Enhancing pediatric adnexal torsion diagnosis: prediction method utilizing machine learning techniques”. Children (Basel)10 (2023): 1612.
6. Zhao Z., et al. “Construction and validation of a machine learning model integrating ultrasound features and inflammatory markers (OVART-ML) for predicting ovarian torsion and ischemic necrosis”. Frontiers in Pediatrics 13 (2025): 1717545.
7. “Machine Learning for Early Diagnosis of Endometriosis (MLEndo)”. ClinicalTrials.gov NCT06147687 (2023).
8. Markov D., et al. “Emerging pathways to non-invasive diagnosis in endometriosis: integrating machine learning, deep learning and multi-omics biomarkers”. Diagnostics12 (2026): 1823.
9. Agirsoy M., et al. “A machine learning approach for non-invasive PCOS diagnosis”. Scientific Reports1 (2025): 33638.
10. Zad Z., et al. “Predicting polycystic ovary syndrome with machine learning algorithms”. Frontiers in Endocrinology 15 (2024): 1298628.
11. Priyanka Pariyawala and Pushpal Y Desai. “Diagnosis of PCOS in adolescent girls using traditional and ensemble machine learning methods”. Research Square Preprint rs-7009734.
12. Dixit R., et al. “Mullerian anomalies: revisiting imaging and classification”. Insights into Imaging1 (2025): 40.
13. Samantha M Pfeifer., et al. “ASRM Müllerian Anomalies Classification 2021”. Fertility and Sterility 5 (2021): 1238-1252.
14. Ramakrishnan KK., et al. “Comparing the diagnostic efficacy of 3D ultrasound and MRI in the classification of Müllerian anomalies”. Cureus10 (2024): e70632.
15. Yilin Chen., et al. “Meta-analysis of machine learning models for the diagnosis of central precocious puberty”. Frontiers in Endocrinology 15 (2024): 1353023.
16. Liyan Pan., et al. “Machine learning identifies girls with central precocious puberty”. JAMIA Open4 (2020): 567-575.