Fetal monitoring usually refers to monitoring fetal heart rate (FHR) for detection fetal well-being. This is important activity carried out by doctors during prepartum, intrapartum phase as per health requirement of patient. Fetal monitoring is required to reduce chances of fetal to become hypoxic (when fetal is deprived from sufficient oxygen) that can cause fetal brain injury and even fetal death. Fetal monitoring plays important role in reducing mortality and morbidity rate. The most common noninvasive fetal monitoring device is cardiotocograph (CTG). CTG captures FHR based on Doppler ultrasound principle and uterine contractions (UC) based on pressure transducers. The present study highlights accuracy limitations of CTG and proposes more accurate noninvasive fetal ECG (NIfECG) as data acquisition methods to acquire FHR and electrohysterogram (EHG) to capture UC. CTG interpretation is one of the decision-making parameters used by doctors for early intervention like caesarian section. CTG interpretation often suffers from inter-observer and intra-observer agreement of CTG patterns which are non-reassuring. To overcome this limitation, computerized analysis can be useful. The present study also discusses usage of machine learning to detect fetal compromise. Further, in addition to FHR and UC analysis, we also propose to use ST waveform analysis to improve results. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.