ARTIFICIAL INTELLIGENCE IN CARDIOTOCOGRAPHY FOR ASSESSING FETAL WELL-BEING: A NARRATIVE REVIEW OF CURRENT EVIDENCE, CHALLENGES, AND NEXT STEPS

Abstract

Introduction: Cardiotocography (CTG) has long been a key tool for fetal monitoring, yet its interpretation is often limited by interobserver variability. Artificial intelligence (AI) has emerged as a promising solution to enhance accuracy and consistency in the interpretation of CTG patterns.

Discussion: This review explores how AI, particularly machine learning and deep learning, supports CTG classification. Models like random forest and Convolutional Neural Networks (CNN) have shown strong performance in detecting fetal conditions. However, AI is not yet ready to replace clinical judgment due to some limitations in data quality, interpretability, and ethical use of medical information. Hybrid approaches that combine AI with human expertise appear to be the most effective path forward.

Conclusion: AI holds strong potential as a clinical support tool in CTG interpretation. With further development, multimodal integration, and explainable AI approaches, decision-making during labor may be improved in a more accurate and personalized way.