CTGNet: Automatic Analysis of Fetal Heart Rate from Cardiotocograph Using Artificial Intelligence

Abstract

This study investigates the efficacy of analyzing fetal heart rate (FHR) signals based on Artificial Intelligence to obtain a baseline calculation and identify accelerations/decelerations in the FHR through electronic fetal monitoring during labor.Methods: A total of 43,888 cardiotocograph(CTG) records of female patients in labor from January 2012 to December 2020 were collected from the NanFang Hospital of Southern Medical University. After filtering the data, 2341 FHR records were used for the study. The ObVue fetal monitoring system, manufactured by Lian-Med Technology Co. Ltd., was used to monitor the FHR signals for these pregnant women from the beginning of the first stage of labor to the end of delivery. Two obstetric experts together annotated the FHR signals in the system to determine the baseline as well as accelerations/ decelerations of the FHR. Our cardiotocograph network (CTGNet) as well as traditional methods were then used to automatically analyze the baseline and acceleration/deceleration of the FHR signals. The results of calculations were compared with the annotations provided by the obstetric experts, and ten-fold cross-validation was applied to evaluate them. The root-mean-square difference (RMSD) between the baselines, acceleration F-measure (Acc.F-measure), deceleration F-measure (Dec.F-measure), coefficient of synthetic inconsistency (SI) and the morphological analysis discordance index (MADI) were used as evaluation metrics. The data were analyzed by using a paired t-test.Results: The proposed CTGNet was superior to the best traditional method, proposed by Mantel, in terms of the RMSD.BL (1.7935 ± 0.8099 vs. 2.0293 ± 0.9267, t = À3.55 , P = 0.004),

Editorial: New technologies improve maternal and newborn safety

“…Despite their widespread use, these signals often encounter interference from fetal or maternal movements and may diminish in quality as maternal body mass index increases. This limitation in CTG data reliability poses a substantial challenge in meeting the performance criteria necessary for its extensive clinical deployment ( 7 , 9 , 28 – 32 ). This challenge underscores the urgent need for innovative monitoring techniques such as the non-invasive fetal electrocardiogram ( 33 ) and electrohysterogram ( 34 ) to improve the fundamental data quality vital for developing automated systems.…”

Fetal Hypoxia Detection Using Machine Learning: A Narrative Review

“…Additionally, Zhong et al [22] examined the effectiveness of using AI to analyze FHR signals to calculate a baseline value, spot accelerations, and decelerations using electronic fetal monitoring during labor. In addition, the dataset is The NanFang Hospital of Southern Medical University provided a total of 43,888 CTG recordings of female patients undergoing deliveries.…”

How synergy between mechanistic and statistical models is impacting research in atrial fibrillation

“…However, it is a difficult task to reduce hundreds of thousands of multiscale simulation data to meaningful predictive biomarkers, and clinical biomarkers or quantitative measures of structural remodeling derived from raw imaging data were not considered in mechanistic modeling. Statistical models are ideal for identifying meaningful predictive biomarkers in high-dimensional simulation and clinical data ( Corral-Acero et al, 2020 ; Liu et al, 2021 ; Zeng et al, 2021 ; Zhong et al, 2022 ). Therefore, digital twin techniques have value in evidence generation, diagnosis and treatment.…”