ML-Based Interpretation of Cardiotocography Data: Current State and Future Research

To evaluate the health and well-being of an unborn child throughout pregnancy, fetal risk prediction is a crucial component of prenatal care. The evaluation of potential risks and issues related to fetal development may now be done by healthcare professionals using a variety of instruments and methodologies due to developments in medical technology and research. One way to predict fetal risk is with a machine learning algorithm using Cardiotocographic (CTG) data. Massive amounts of medical data can be analyzed using machine learning algorithms to aid clinicians in making more precise diagnoses. The objective of this study was to provide the current state and future research in the field of ML-based interpretation of CTG data by mapping current knowledge in the field. The search was performed on Science Direct, SCOPUS, IEEE, and ProQuest databases. RepOrting standards for Systematic Evidence Syntheses (ROSES) in environmental research guidelines were followed. After screening process, we obtained 42 recent studies that examined the application of machine learning algorithms for interpreting CTG tracings. Future research should focus on a larger and more diverse dataset, comparative evaluations, real-world clinical testing, and developing models that combine accuracy with interpretability.