A recent systematic review published in the Indian Journal of Pediatrics in October 2026 highlights the transformative power of artificial intelligence (AI) and machine learning (ML) in predicting fetal growth restriction (FGR). Across 27 evaluated studies, AI models achieved impressive diagnostic accuracies from 78.9% to 93.3% and area under the receiver operating characteristic curve (AUC) values between 0.71 and 0.91.

Although early identification of intrauterine growth restriction (IUGR) or small for gestational age (SGA) fetuses remains vital for optimizing perinatal outcomes, conventional clinical monitoring techniques suffer from ongoing predictive limitations and substantial methodological heterogeneity across published literature. Addressing this critical diagnostic gap, researchers Krishna Rao Gurugubelli, Vishnu Bhat Ballambattu, and Sandhya Karra conducted a comprehensive systematic synthesis aimed at evaluating the predictive capability and diagnostic accuracy of artificial intelligence models in precision obstetrics.

Therefore, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines, researchers searched major databases through June 2026, evaluating 27 studies across clinical, imaging, biophysical, and molecular modalities. Using the Prediction Model Risk of Bias Assessment Tool (PROBAST), the team assessed primary predictive accuracy endpoints and risk of bias across key study domains.

Key Clinical Findings of the Review:

  • Promising Diagnostic Accuracy: Analysis demonstrated overall diagnostic classification accuracies ranging from 78.9% to 93.3% across evaluated machine learning algorithms.
  • Robust Discriminative Efficacy: Review metrics revealed strong discrimination capability, yielding area under the receiver operating characteristic curve indices spanning 0.71 to 0.91.
  • Multimodal Data Superiority: Synthesis established that integrative models combining clinical, imaging, and molecular parameters consistently outperformed single-modality approaches.
  • Analytical Quality Variability: Assessment using PROBAST indicated low risk of bias across participant, predictor, and outcome domains, whereas analytical domains raised concerns across nine low-risk, 14 moderate-risk, and four high-risk studies.

The results suggest that artificial intelligence and machine learning models demonstrate promising performance for fetal growth restriction detection, with integrated multimodal data approaches achieving classification accuracies of 78.9% to 93.3% and area under the receiver operating characteristic curve values of 0.71 to 0.91 to represent a major advance in precision obstetrics.

The findings imply that clinicians might consider utilizing multimodal artificial intelligence algorithms as complementary tools alongside conventional diagnostic modalities to enhance early risk stratification and diagnostic precision in obstetric care.

While these clinical outcomes are encouraging, current evidence is constrained by substantial study heterogeneity, limited external validation, and analytical methodological issues, indicating that prospective multicenter studies, standardized reporting protocols, and real-world implementation research are needed to facilitate routine clinical adoption.

Reference

Gurugubelli KR, Ballambattu VB, Karra S. Artificial Intelligence in Prediction and Diagnosis of Fetal Growth Restriction: A Systematic Review. Indian J Pediatr. 2026; Published online October 12, 2026.


Tags:    
Article Source : Indian Journal of Pediatrics

Disclaimer: This website is primarily for healthcare professionals. The content here does not replace medical advice and should not be used as medical, diagnostic, endorsement, treatment, or prescription advice. Medical science evolves rapidly, and we strive to keep our information current. If you find any discrepancies, please contact us at corrections@medicaldialogues.in. Read our Correction Policy here. Nothing here should be used as a substitute for medical advice, diagnosis, or treatment. We do not endorse any healthcare advice that contradicts a physician's guidance. Use of this site is subject to our Terms of Use, Privacy Policy, and Advertisement Policy. For more details, read our Full Disclaimer here.

NOTE: Join us in combating medical misinformation. If you encounter a questionable health, medical, or medical education claim, email us at factcheck@medicaldialogues.in for evaluation.

Our comments section is governed by our Comments Policy . By posting comments at Medical Dialogues you automatically agree with our Comments Policy , Terms And Conditions and Privacy Policy .