International Science Community Association Research Journal of Computer and Information Technology Sciences 14 1 2026 06 20 Risk Prediction of Fetal Heart Rate from Cardiotocography Using Artificial Intelligence and Machine Learning 23 25 EN Deshmukh Deepak Kumar 1 School of Studies in Computer Science & I.T., Pt. Ravishankar Shukla University, Raipur, Chhattisgarh, India Kumar Sanjay 2 School of Studies in Computer Science & I.T., Pt. Ravishankar Shukla University, Raipur, Chhattisgarh, India Kashyap Mukesh 1 S.o.S. in Computer Science & IT, Pt. Ravishankar Shukla University, Raipur, Chhattisgarh, India Kumar Sanjay 2 S.o.S. in Computer Science & IT, Pt. Ravishankar Shukla University, Raipur, Chhattisgarh, India Jain Swati 3 Govt. J. Yoganandam Chhattisgarh College, Raipur, Chhattisgarh, India Thakkar Binita 1 Department of Computer Science, VIVA College of Arts, Commerce and Science, Virar (W), India Yande Shweta 2 Department of Computer Science, VIVA College of Arts, Commerce and Science, Virar (W), India Patil Anuja 3 Department of Computer Science, VIVA College of Arts, Commerce and Science, Virar (W), India Sharma Neerja 1 Department of Computer Science, CAET, Etawah, UP, India Sharma N.K. 2 Department of Electronics and Communication Engineering, CAET, Etawah, UP, India > Short Review Paper 2025 11 30 2026 06 20 Cardiotocography (CTG), which records the fetal heart rate (FHR) and uterine contractions (UC), is the cornerstone of fetal monitoring during pregnancy and labor. However, its manual interpretation is highly subjective, leading to significant inter and intra-observer variability and high false-positive rates for fetal distress. This review paper synthesizes recent advancements in applying Artificial Intelligence (AI) and Machine Learning (ML) techniques to CTG data to develop objective, accurate, and automated systems for predicting fetal risk. We explore the spectrum of ML algorithms employed, features extracted from CTG signals, performance metrics, and persistent challenges including data scarcity and class imbalance. AI/ML integration holds immense promise for improving clinical decision-making and neonatal outcomes. Copyright@ International Science Community Association