Large historic cohorts can be used to develop and optimize computerized cardiotocography monitoring, combining clinical and cardiotocography risk factors. Our simple prototype has demonstrated the principle of using such data to trigger alarms, and compares well with clinical judgment.
Objective Recent studies suggest that phase-rectified signal averaging (PRSA), measured in antepartum fetal heart rate (FHR) traces, may sensitively indicate fetal status; however, its value has not been assessed during labour. We determined whether PRSA relates to acidaemia in labour, and compare its performance to short-term variation (STV), a related computerised FHR feature. Design Historical cohort.Setting Large UK teaching hospital.Population All 7568 Oxford deliveries that met the study criteria from April 1993 to February 2008.Methods We analysed the last 30 minutes of the FHR and associated outcomes of infants. We used computerised analysis to calculate PRSA decelerative capacity (DC PRSA ), and its ability to predict umbilical arterial blood pH ≤ 7.05 using receiver operator characteristic (ROC) curves and event rate estimates (EveREst). We compared DC PRSA with STV calculated on the same traces.Main outcome measure Umbilical arterial blood pH ≤ 7.05.Results We found that PRSA could be measured in all cases. DC PRSA predicted acidaemia significantly better than STV: the area under the ROC curve was 0.665 (95% CI 0.632-0.699) for DC PRSA , and 0.606 (0.573-0.639) for STV (P = 0.007). EveREst plots showed that in the worst fifth centile of cases, the incidence of low pH was 17.75% for DC PRSA but 11.00% for STV (P < 0.001). DC PRSA was not highly correlated with STV.Conclusions DC PRSA of the FHR can be measured in labour, and appears to predict acidaemia more accurately than STV. Further prospective evaluation is warranted to assess whether this could be clinically useful. The weak correlation between DC PRSA and STV suggests that they could be combined in multivariate FHR analyses.
The gold standard to assess whether a baby is at risk of oxygen deprivation during childbirth, is monitoring continuously the fetal heart rate with cardiotocography (CTG). The aim is to identify babies that could benefit from an emergency operative delivery (e.g., Cesarean section), in order to prevent death or permanent brain injury. The long, dynamic and complex CTG patterns are poorly understood and known to have high false positive and false negative rates. Visual interpretation by clinicians is challenging and reliable accurate fetal monitoring in labor remains an enormous unmet medical need. In this work, we applied deep learning methods to achieve data-driven automated CTG evaluation. Multimodal Convolutional Neural Network (MCNN) and Stacked MCNN models were used to analyze the largest available database of routinely collected CTG and linked clinical data (comprising more than 35000 births). We also assessed in detail the impact of the signal quality on the MCNN performance. On a large holdout testing set from Oxford (n = 4429 births), MCNN improved the prediction of cord acidemia at birth when compared with Clinical Practice and previous computerized approaches. On two external datasets, MCNN demonstrated better performance compared to current feature extraction-based methods. Our group is the first to apply deep learning for the analysis of CTG. We conclude that MCNN hold potential for the prediction of cord acidemia at birth and further work is warranted. Despite the advances, our deep learning models are currently not suitable for the detection of severe fetal injury in the absence of cord acidemiaa heterogeneous, small, and poorly understood group. We suggest that the most promising way forward are hybrid approaches to CTG interpretation in labor, in which different diagnostic models can estimate the risk for different types of fetal compromise, incorporating clinical knowledge with data-driven analyses. INDEX TERMS Clinical decision making, deep learning, convolutional neural networks, fetal heart rate, sensitivity, specificity.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.