Computerized cardiotocography analysis during labor - A state-of-the-art review

Integration of clinical features in a computerized cardiotocography system to predict severe newborn acidemia

BACKGROUND

Cardiotocography (CTG), used during labor to assess fetal wellbeing, is subject to interobserver variability. Computerized CTG is a promising tool to improve fetal hypoxia detection.

OBJECTIVE

To assess if adding clinical features improves the performance of a computerized CTG system to predict severe newborn acidemia (blood cord pH below 7.05).

METHODS

A retrospective multicentric database was built using the data from two sources (the open-source CTU-UHB database and the data from Beaujon university hospital). Four CTG features were extracted from the fetal heart rate (FHR) signal (minimum and maximum value of the baseline, area covered by the accelerations and decelerations). Clinical features were also collected. Severe fetal acidemia was defined by arterial pH < 7.05 on umbilical cord sample. Risk factors for severe acidemia were sought by comparing cases with severe newborn acidemia to the rest of the cohort. We evaluated the accuracy of the model using both CTG and clinical features using area under the curve (AUC) in a cross-center, cross-validation approach.

RESULTS

The datasets contained 1264 cases including 100 cases with severe acidemia. In univariate analysis, hypertensive disorders and other clinical features showed no significant difference, except for meconium-stained amniotic fluid (p = 0.03). Multivariate analysis revealed that a high deceleration area (OR = 1.09 [1.04--1.11]) and apparition of meconium amniotic fluid increased the risk of newborn acidemia (OR = 2.10[1.24-3.49]). In a k-fold cross-validation approach, DeepCTG®1.5 reached an AUC of 0.77, compared to 0.74 when using CTG features only.

CONCLUSION

The CTG features have a good accuracy to predict severe newborn acidemia, confirming existing literature. Integrating clinical features tends to enhance the accuracy. Further research will aim at using more advanced machine learning models to combine the features more efficiently.

Intrapartum electronic fetal heart rate monitoring to predict acidemia at birth with the use of deep learning

BACKGROUND

Electronic fetal monitoring is used in most US hospital births but has significant limitations in achieving its intended goal of preventing intrapartum hypoxic-ischemic injury. Novel deep learning techniques can improve complex data processing and pattern recognition in medicine.

OBJECTIVE

This study aimed to apply deep learning approaches to develop and validate a model to predict fetal acidemia from electronic fetal monitoring data.

STUDY DESIGN

The database was created using intrapartum electronic fetal monitoring data from 2006 to 2020 from a large, multisite academic health system. Data were divided into training and testing sets with equal distribution of acidemic cases. Several different deep learning architectures were explored. The primary outcome was umbilical artery acidemia, which was investigated at 4 clinically meaningful thresholds: 7.20, 7.15, 7.10, and 7.05, along with base excess. The receiver operating characteristic curves were generated with the area under the receiver operating characteristic assessed to determine the performance of the models. External validation was performed using a publicly available Czech database of electronic fetal monitoring data.

RESULTS

A total of 124,777 electronic fetal monitoring files were available, of which 77,132 had <30% missingness in the last 60 minutes of the electronic fetal monitoring tracing. Of these, 21,041 were matched to a corresponding umbilical cord gas result, of which 10,182 were time-stamped within 30 minutes of the last electronic fetal monitoring reading and composed the final dataset. The prevalence rates of the outcomes in the data were 20.9% with a pH of <7.2, 9.1% with a pH of <7.15, 3.3% with a pH of <7.10, and 1.3% with a pH of <7.05. The best performing model achieved an area under the receiver operating characteristic of 0.85 at a pH threshold of <7.05. When predicting the joint outcome of both pH of <7.05 and base excess of less than -10 meq/L, an area under the receiver operating characteristic of 0.89 was achieved. When predicting both pH of <7.20 and base excess of less than -10 meq/L, an area under the receiver operating characteristic of 0.87 was achieved. At a pH of <7.15 and a positive predictive value of 30%, the model achieved a sensitivity of 90% and a specificity of 48%.

CONCLUSION

The application of deep learning methods to intrapartum electronic fetal monitoring analysis achieves promising performance in predicting fetal acidemia. This technology could help improve the accuracy and consistency of electronic fetal monitoring interpretation.

DeepCTG® 2.0: Development and validation of a deep learning model to detect neonatal acidemia from cardiotocography during labor

Cardiotocography (CTG) is the main tool available to detect neonatal acidemia during delivery. Presently, obstetricians and midwives primarily rely on visual interpretation, leading to a significant intra-observer variability. In this paper, we build and evaluate a convolutional neural network to detect neonatal acidemia from the CTG signals during delivery on a multicenter database with 27662 cases in five centers, including 3457 and 464 cases of moderate and severe neonatal acidemia respectively (defined by a fetal pH at birth between 7.05 and 7.20, and lower than 7.05 respectively). To use all the available records, the convolutional layers are pretrained on a task which consists in predicting several features known to be associated with neonatal acidemia from the raw CTG signals. In a cross-center evaluation, the AUC varies from 0.74 to 0.83 between the centers for the detection of severe acidemia, showing the ability of deep learning models to generalize from one dataset to the other and paving the way for more accurate models trained on larger databases. The model can still be significantly improved, by adding clinical variables to account for risk factors of acidemia that may not appear in the CTG signals. Further research will also be led to integrate the model in a tool that could assist humans in the interpretation of CTG.

Development, Validation, and Diagnostic Accuracy of the Fetal Lack of Responsiveness Scale for Diagnosis of Severe Perinatal Hypoxia

Background: There are limitations to predicting perinatal asphyxia, as current tools rely almost entirely on fetal cardiotocography (CTG). The fetal lack of responsiveness scale (FLORS) is a new diagnostic alternative based on the physiological phenomena associated with fetal hypoxia. Objectives: The objective of this study was to develop, validate, and assess the diagnostic accuracy of the FLORS for predicting severe perinatal hypoxia (SPH). Study Design: A two-phase retrospective observational cross-sectional analytical study was conducted. Phase 1 involved the formulation and retrospective validation of the FLORS. A total of 366 fetal CTG records were evaluated twice by seven readers. Phase 2 was a collaborative, retrospective, multicenter diagnostic test study that included 37 SPH and 366 non-SPH cases. Results: Phase 1: A numeric, physiology-based scale was developed and refined based on expert opinions. The median time to apply the scale per reading was 38 s. Cronbach's alpha, which is a reliability measure, was significant (p = 0.784). The kappa index for test-retest agreement was moderate to reasonable, with a median value of 0.642. For interobserver agreement, the kappa index per variable was as follows: baseline, 0.669; accelerations, 0.658; variability, 0.467; late/variable decelerations, 0.638; slow response decelerations, 0.617; and trend to change, 0.423. Phase 2, including 37 SPH and 366 non-SPH cases, showed a sensitivity of 62.2% and specificity of 75.4% for the 2-point score, whereas the 3-point score had a sensitivity of 35.1% and specificity of 89.9%. The area under the curve (AUC) was significant at 0.73 (CI 0.645-0.818). Conclusions: FLORS demonstrated significant internal consistency and observer agreement, with a promising sensitivity-specificity balance and significant AUC. Further research is needed to assess its impact on perinatal hypoxia and cesarean delivery.

Assessment of fetal resistance to hypoxia using the Stange test as an adjunct to Apgar scale assessment of neonatal health status

It has been established that the cause of biological death of fetuses in stillbirths and the cause of neonatal encephalopathies in live births is hypoxic brain cell damage in fetuses. Timely cesarean section remains the most effective way to preserve fetal life and health in the face of lethal intrauterine hypoxia. However, there is no universally recognized methodology for assessing fetal adaptation reserves to hypoxia and no methodology for selecting the type of delivery in order to perform a timely cesarean section if necessary. The Apgar score, which has been used since 1952, allows assessment of neonatal health at 1 and 5 minutes after birth, but this assessment is made without taking into account the health of the fetus before delivery. In recent years, it has been established that the outcome of fetal hypoxia is determined not only by its duration, but also by the amount of adaptive reserves available in the fetus to hypoxia. It was found that the duration of fetal immobility during apnea of a pregnant woman is an indicator of fetal resistance to hypoxia. In 2011, a method of assessing fetal resistance to intrauterine hypoxia based on the Stange test was developed in Russia. It has been found that the maximum duration of fetal immobility during maternal apnea is normally more than 30 seconds, while in the presence of fetal signs of fetoplacental insufficiency it does not reach 30 seconds, and in the presence of signs of severe fetoplacental insufficiency it does not reach 10 seconds. Therefore, it was proposed to consider good fetal resistance to hypoxia as an indication for vaginal delivery, and poor fetal resistance to hypoxia as an indication for cesarean section. A technique for assessing fetal resistance to hypoxia is described that has been developed for independent use by every pregnant woman. It is shown that it is sufficient for her to have a stopwatch and to be able to record the maximum period of fetal immobility during voluntary apnea. It is hoped that a measure of fetal resistance to hypoxia could be a meaningful complement to the Apgar score of neonatal health. It is envisioned that the use of a modified Stange test could help physicians prevent stillbirths and neonatal encephalopathies.

Large-scale analysis of interobserver agreement and reliability in cardiotocography interpretation during labor using an online tool

BACKGROUND

While the effectiveness of cardiotocography in reducing neonatal morbidity is still debated, it remains the primary method for assessing fetal well-being during labor. Evaluating how accurately professionals interpret cardiotocography signals is essential for its effective use. The objective was to evaluate the accuracy of fetal hypoxia prediction by practitioners through the interpretation of cardiotocography signals and clinical variables during labor.

MATERIAL AND METHODS

We conducted a cross-sectional online survey, involving 120 obstetric healthcare providers from several countries. One hundred cases, including fifty cases of fetal hypoxia, were randomly assigned to participants who were invited to predict the fetal outcome (binary criterion of pH with a threshold of 7.15) based on the cardiotocography signals and clinical variables. After describing the participants, we calculated (with a 95% confidence interval) the success rate, sensitivity and specificity to predict the fetal outcome for the whole population and according to pH ranges, professional groups and number of years of experience. Interobserver agreement and reliability were evaluated using the proportion of agreement and Cohen's kappa respectively.

RESULTS

The overall ability to predict a pH level below 7.15 yielded a success rate of 0.58 (95% CI 0.56-0.60), a sensitivity of 0.58 (95% CI 0.56-0.60) and a specificity of 0.63 (95% CI 0.61-0.65). No significant difference in the success rates was observed with respect to profession and number of years of experience. The success rate was higher for the cases with a pH level below 7.05 (0.69) and above 7.20 (0.66) compared to those falling between 7.05 and 7.20 (0.48). The proportion of agreement between participants was good (0.82), with an overall kappa coefficient indicating substantial reliability (0.63).

CONCLUSIONS

The use of an online tool enabled us to collect a large amount of data to analyze how practitioners interpret cardiotocography data during labor. Despite a good level of agreement and reliability among practitioners, the overall accuracy is poor, particularly for cases with a neonatal pH between 7.05 and 7.20. Factors such as profession and experience level do not present notable impact on the accuracy of the annotations. The implementation and use of a computerized cardiotocography analysis software has the potential to enhance the accuracy to detect fetal hypoxia, especially for ambiguous cardiotocography tracings.

Conventional Cardiotocography versus Computerized CTG Analysis and Perinatal Outcomes: a Systematic Review

Introduction: Cardiotocography (CTG) constitutes a major and generally used tool for the assessment of fetal well-being. Subjectivity is the main difficulty in the interpretation of CTG. Inter- and intra-observer variability are substantival features of the interpretation of CTGs. An auspicious answer for reduction of inter- and intra-observer variability is the computerized analysis of fetal heart rate (FHR). Moreover, computerized analysis contributes to the reduction of adverse maternal and fetal outcomes. Objective: The aim of the present review was to compare the visual and computerized analysis of CTG for establishing whether computerized CTG was related to better perinatal outcomes. Materials and methods: Three electronic medical related databases (PubMed, Scopus and Cochrane) were searched from May to June 2023 in order to find randomized controlled trials (RCTs) in English. Studies were evaluated for their methodological quality with the CONSORT checklist. The target population comprised pregnant or intrapartum women into cardiotocographic monitoring. The intervention was represented by the visual analysis of CTG, and the comparison intervention by the computerized analysis of CTG. Primary outcomes included adverse perinatal outcomes. Results: A total of 47 studies relevant with the topic were examined. However, only five articles met all inclusion and methodological criteria; four of those demonstrated that computerized analysis had no significant reduction in the rate of metabolic acidosis or obstetric interventions, and one study found a lower incidence of adverse perinatal outcome with conventional CTG (with fetal blood sampling). However, all reviews propose further development of decision-support software and more large-scale RCTs in the future. Conclusion: The computerized analysis of FHR is a promising solution for the reduction of adverse perinatal outcomes and elimination of inter- and intra-observer variability.

DeepCTG® 1.0: an interpretable model to detect fetal hypoxia from cardiotocography data during labor and delivery

Introduction

Cardiotocography, which consists in monitoring the fetal heart rate as well as uterine activity, is widely used in clinical practice to assess fetal wellbeing during labor and delivery in order to detect fetal hypoxia and intervene before permanent damage to the fetus. We present DeepCTG® 1.0, a model able to predict fetal acidosis from the cardiotocography signals.

Materials and methods

DeepCTG® 1.0 is based on a logistic regression model fed with four features extracted from the last available 30 min segment of cardiotocography signals: the minimum and maximum values of the fetal heart rate baseline, and the area covered by accelerations and decelerations. Those four features have been selected among a larger set of 25 features. The model has been trained and evaluated on three datasets: the open CTU-UHB dataset, the SPaM dataset and a dataset built in hospital Beaujon (Clichy, France). Its performance has been compared with other published models and with nine obstetricians who have annotated the CTU-UHB cases. We have also evaluated the impact of two key factors on the performance of the model: the inclusion of cesareans in the datasets and the length of the cardiotocography segment used to compute the features fed to the model.

Results

The AUC of the model is 0.74 on the CTU-UHB and Beaujon datasets, and between 0.77 and 0.87 on the SPaM dataset. It achieves a much lower false positive rate (12% vs. 25%) than the most frequent annotation among the nine obstetricians for the same sensitivity (45%). The performance of the model is slightly lower on the cesarean cases only (AUC = 0.74 vs. 0.76) and feeding the model with shorter CTG segments leads to a significant decrease in its performance (AUC = 0.68 with 10 min segments).

Discussion

Although being relatively simple, DeepCTG® 1.0 reaches a good performance: it compares very favorably to clinical practice and performs slightly better than other published models based on similar approaches. It has the important characteristic of being interpretable, as the four features it is based on are known and understood by practitioners. The model could be improved further by integrating maternofetal clinical factors, using more advanced machine learning or deep learning approaches and having a more robust evaluation of the model based on a larger dataset with more pathological cases and covering more maternity centers.