A Strategy for Classification of "Vaginal vs. Cesarean Section" Delivery: Bivariate Empirical Mode Decomposition of Cardiotocographic Recordings

Fast Healthcare Interoperability Resources-Based Support System for Predicting Delivery Type: Model Development and Evaluation Study

BACKGROUND

The escalating prevalence of cesarean delivery globally poses significant health impacts on mothers and newborns. Despite this trend, the underlying reasons for increased cesarean delivery rates, which have risen to 36.3% in Portugal as of 2020, remain unclear. This study delves into these issues within the Portuguese health care context, where national efforts are underway to reduce cesarean delivery occurrences.

OBJECTIVE

This paper aims to introduce a machine learning, algorithm-based support system designed to assist clinical teams in identifying potentially unnecessary cesarean deliveries. Key objectives include developing clinical decision support systems for cesarean deliveries using interoperability standards, identifying predictive factors influencing delivery type, assessing the economic impact of implementing this tool, and comparing system outputs with clinicians' decisions.

METHODS

This study used retrospective data collected from 9 public Portuguese hospitals, encompassing maternal and fetal data and delivery methods from 2019 to 2020. We used various machine learning algorithms for model development, with light gradient-boosting machine (LightGBM) selected for deployment due to its efficiency. The model's performance was compared with clinician assessments through questionnaires. Additionally, an economic simulation was conducted to evaluate the financial impact on Portuguese public hospitals.

RESULTS

The deployed model, based on LightGBM, achieved an area under the receiver operating characteristic curve of 88%. In the trial deployment phase at a single hospital, 3.8% (123/3231) of cases triggered alarms for potentially unnecessary cesarean deliveries. Financial simulation results indicated potential benefits for 30% (15/48) of Portuguese public hospitals with the implementation of our tool. However, this study acknowledges biases in the model, such as combining different vaginal delivery types and focusing on potentially unwarranted cesarean deliveries.

CONCLUSIONS

This study presents a promising system capable of identifying potentially incorrect cesarean delivery decisions, with potentially positive implications for medical practice and health care economics. However, it also highlights the challenges and considerations necessary for real-world application, including further evaluation of clinical decision-making impacts and understanding the diverse reasons behind delivery type choices. This study underscores the need for careful implementation and further robust analysis to realize the full potential and real-world applicability of such clinical support systems.

Machine learning on cardiotocography data to classify fetal outcomes: A scoping review

INTRODUCTION

Uterine contractions during labour constrict maternal blood flow and oxygen delivery to the developing baby, causing transient hypoxia. While most babies are physiologically adapted to withstand such intrapartum hypoxia, those exposed to severe hypoxia or with poor physiological reserves may experience neurological injury or death during labour. Cardiotocography (CTG) monitoring was developed to identify babies at risk of hypoxia by detecting changes in fetal heart rate (FHR) patterns. CTG monitoring is in widespread use in intrapartum care for the detection of fetal hypoxia, but the clinical utility is limited by a relatively poor positive predictive value (PPV) of an abnormal CTG and significant inter and intra observer variability in CTG interpretation. Clinical risk and human factors may impact the quality of CTG interpretation. Misclassification of CTG traces may lead to both under-treatment (with the risk of fetal injury or death) or over-treatment (which may include unnecessary operative interventions that put both mother and baby at risk of complications). Machine learning (ML) has been applied to this problem since early 2000 and has shown potential to predict fetal hypoxia more accurately than visual interpretation of CTG alone. To consider how these tools might be translated for clinical practice, we conducted a review of ML techniques already applied to CTG classification and identified research gaps requiring investigation in order to progress towards clinical implementation.

MATERIALS AND METHOD

We used identified keywords to search databases for relevant publications on PubMed, EMBASE and IEEE Xplore. We used Preferred Reporting Items for Systematic Review and Meta-Analysis for Scoping Reviews (PRISMA-ScR). Title, abstract and full text were screened according to the inclusion criteria.

RESULTS

We included 36 studies that used signal processing and ML techniques to classify CTG. Most studies used an open-access CTG database and predominantly used fetal metabolic acidosis as the benchmark for hypoxia with varying pH levels. Various methods were used to process and extract CTG signals and several ML algorithms were used to classify CTG. We identified significant concerns over the practicality of using varying pH levels as the CTG classification benchmark. Furthermore, studies needed to be more generalised as most used the same database with a low number of subjects for an ML study.

CONCLUSION

ML studies demonstrate potential in predicting fetal hypoxia from CTG. However, more diverse datasets, standardisation of hypoxia benchmarks and enhancement of algorithms and features are needed for future clinical implementation.

Intelligent antepartum fetal monitoring via deep learning and fusion of cardiotocographic signals and clinical data

Purpose

Cardiotocography (CTG), which measures uterine contraction (UC) and fetal heart rate (FHR), is a crucial tool for assessing fetal health during pregnancy. However, traditional computerized cardiotocography (cCTG) approaches have non-negligible calibration errors in feature extraction and heavily rely on the expertise and prior experience to define diagnostic features from CTG or FHR signals. Although previous works have studied deep learning methods for extracting CTG or FHR features, these methods still neglect the clinical information of pregnant women.

Methods

In this paper, we proposed a multimodal deep learning architecture (MMDLA) for intelligent antepartum fetal monitoring that is capable of performing automatic CTG feature extraction, fusion with clinical data and classification. The multimodal feature fusion was achieved by concatenating high-level CTG features, which were extracted from preprocessed CTG signals via a convolution neural network (CNN) with six convolution layers and five fully connected layers, and the clinical data of pregnant women. Eventually, light gradient boosting machine (LGBM) was implemented as fetal status assessment classifier. The effectiveness of MMDLA was evaluated using a dataset of 16,355 cases, each of which includes FHR signal, UC signal and pertinent clinical data like maternal age and gestational age.

Results

With an accuracy of 90.77% and an area under the curve (AUC) value of 0.9201, the multimodal features performed admirably. The data imbalance issue was also effectively resolved by the LGBM classifier, with a normal-F1 value of 0.9376 and an abnormal-F1 value of 0.8223.

Conclusion

In summary, the proposed MMDLA is conducive to the realization of intelligent antepartum fetal monitoring.

Data-driven nonstationary signal decomposition approaches: a comparative analysis

Signal decomposition (SD) approaches aim to decompose non-stationary signals into their constituent amplitude- and frequency-modulated components. This represents an important preprocessing step in many practical signal processing pipelines, providing useful knowledge and insight into the data and relevant underlying system(s) while also facilitating tasks such as noise or artefact removal and feature extraction. The popular SD methods are mostly data-driven, striving to obtain inherent well-behaved signal components without making many prior assumptions on input data. Among those methods include empirical mode decomposition and variants, variational mode decomposition and variants, synchrosqueezed transform and variants and sliding singular spectrum analysis. With the increasing popularity and utility of these methods in wide-ranging applications, it is imperative to gain a better understanding and insight into the operation of these algorithms, evaluate their accuracy with and without noise in input data and gauge their sensitivity against algorithmic parameter changes. In this work, we achieve those tasks through extensive experiments involving carefully designed synthetic and real-life signals. Based on our experimental observations, we comment on the pros and cons of the considered SD algorithms as well as highlighting the best practices, in terms of parameter selection, for the their successful operation. The SD algorithms for both single- and multi-channel (multivariate) data fall within the scope of our work. For multivariate signals, we evaluate the performance of the popular algorithms in terms of fulfilling the mode-alignment property, especially in the presence of noise.

Multimodal learning for fetal distress diagnosis using a multimodal medical information fusion framework

Cardiotocography (CTG) monitoring is an important medical diagnostic tool for fetal well-being evaluation in late pregnancy. In this regard, intelligent CTG classification based on Fetal Heart Rate (FHR) signals is a challenging research area that can assist obstetricians in making clinical decisions, thereby improving the efficiency and accuracy of pregnancy management. Most existing methods focus on one specific modality, that is, they only detect one type of modality and inevitably have limitations such as incomplete or redundant source domain feature extraction, and poor repeatability. This study focuses on modeling multimodal learning for Fetal Distress Diagnosis (FDD); however, exists three major challenges: unaligned multimodalities; failure to learn and fuse the causality and inclusion between multimodal biomedical data; modality sensitivity, that is, difficulty in implementing a task in the absence of modalities. To address these three issues, we propose a Multimodal Medical Information Fusion framework named MMIF, where the Category Constrained-Parallel ViT model (CCPViT) was first proposed to explore multimodal learning tasks and address the misalignment between multimodalities. Based on CCPViT, a cross-attention-based image-text joint component is introduced to establish a Multimodal Representation Alignment Network model (MRAN), explore the deep-level interactive representation between cross-modal data, and assist multimodal learning. Furthermore, we designed a simple-structured FDD test model based on the highly modal alignment MMIF, realizing task delegation from multimodal model training (image and text) to unimodal pathological diagnosis (image). Extensive experiments, including model parameter sensitivity analysis, cross-modal alignment assessment, and pathological diagnostic accuracy evaluation, were conducted to show our models’ superior performance and effectiveness.

Detecting High-Risk Factors and Early Diagnosis of Diabetes Using Machine Learning Methods

Diabetes is a chronic disease that can cause several forms of chronic damage to the human body, including heart problems, kidney failure, depression, eye damage, and nerve damage. There are several risk factors involved in causing this disease, with some of the most common being obesity, age, insulin resistance, and hypertension. Therefore, early detection of these risk factors is vital in helping patients reverse diabetes from the early stage to live healthy lives. Machine learning (ML) is a useful tool that can easily detect diabetes from several risk factors and, based on the findings, provide a decision-based model that can help in diagnosing the disease. This study aims to detect the risk factors of diabetes using ML methods and to provide a decision support system for medical practitioners that can help them in diagnosing diabetes. Moreover, besides various other preprocessing steps, this study has used the synthetic minority over-sampling technique integrated with the edited nearest neighbor (SMOTE-ENN) method for balancing the BRFSS dataset. The SMOTE-ENN is a more powerful method than the individual SMOTE method. Several ML methods were applied to the processed BRFSS dataset and built prediction models for detecting the risk factors that can help in diagnosing diabetes patients in the early stage. The prediction models were evaluated using various measures that show the high performance of the models. The experimental results show the reliability of the proposed models, demonstrating that k-nearest neighbor (KNN) outperformed other methods with an accuracy of 98.38%, sensitivity, specificity, and ROC/AUC score of 98%. Moreover, compared with the existing state-of-the-art methods, the results confirm the efficacy of the proposed models in terms of accuracy and other evaluation measures. The use of SMOTE-ENN is more beneficial for balancing the dataset to build more accurate prediction models. This was the main reason it was possible to achieve models more accurate than the existing ones.

A Clinical Decision Support System (CDSS) for Unbiased Prediction of Caesarean Section Based on Features Extraction and Optimized Classification

Nowadays, caesarean section (CS) is given preference over vaginal birth and this trend is rapidly rising around the globe, although CS has serious complications such as pregnancy scar, scar dehiscence, and morbidly adherent placenta. Thus, CS should only be performed when it is absolutely necessary for mother and fetus. To avoid unnecessary CS, researchers have developed different machine-learning- (ML-) based clinical decision support systems (CDSS) for CS prediction using electronic health record of the pregnant women. However, previously proposed methods suffer from the problems of poor accuracy and biasedness in ML. To overcome these problems, we have designed a novel CDSS where random oversampling example (ROSE) technique has been used to eliminate the problem of minority classes in the dataset. Furthermore, principal component analysis has been employed for feature extraction from the dataset while, for classification purpose, random forest (RF) model is deployed. We have fine-tuned the hyperparameter of RF using a grid search algorithm for optimal classification performance. Thus, the newly proposed system is named ROSE-PCA-RF and it is trained and tested using an online CS dataset available on the UCI repository. In the first experiment, conventional RF model is trained and tested on the dataset while in the second experiment, the proposed model is tested. The proposed ROSE-PCA-RF model improved the performance of traditional RF by 4.5% with reduced time complexity, while only using two extracted features through the PCA. Moreover, the proposed model has obtained 96.29% accuracy on training data while improving the accuracy of 97.12% on testing data.

Non-linear Methods Predominant in Fetal Heart Rate Analysis: A Systematic Review

The analysis of fetal heart rate variability has served as a scientific and diagnostic tool to quantify cardiac activity fluctuations, being good indicators of fetal well-being. Many mathematical analyses were proposed to evaluate fetal heart rate variability. We focused on non-linear analysis based on concepts of chaos, fractality, and complexity: entropies, compression, fractal analysis, and wavelets. These methods have been successfully applied in the signal processing phase and increase knowledge about cardiovascular dynamics in healthy and pathological fetuses. This review summarizes those methods and investigates how non-linear measures are related to each paper's research objectives. Of the 388 articles obtained in the PubMed/Medline database and of the 421 articles in the Web of Science database, 270 articles were included in the review after all exclusion criteria were applied. While approximate entropy is the most used method in classification papers, in signal processing, the most used non-linear method was Daubechies wavelets. The top five primary research objectives covered by the selected papers were detection of signal processing, hypoxia, maturation or gestational age, intrauterine growth restriction, and fetal distress. This review shows that non-linear indices can be used to assess numerous prenatal conditions. However, they are not yet applied in clinical practice due to some critical concerns. Some studies show that the combination of several linear and non-linear indices would be ideal for improving the analysis of the fetus's well-being. Future studies should narrow the research question so a meta-analysis could be performed, probing the indices' performance.

A Comprehensive Review of Techniques for Processing and Analyzing Fetal Heart Rate Signals

The availability of standardized guidelines regarding the use of electronic fetal monitoring (EFM) in clinical practice has not effectively helped to solve the main drawbacks of fetal heart rate (FHR) surveillance methodology, which still presents inter- and intra-observer variability as well as uncertainty in the classification of unreassuring or risky FHR recordings. Given the clinical relevance of the interpretation of FHR traces as well as the role of FHR as a marker of fetal wellbeing autonomous nervous system development, many different approaches for computerized processing and analysis of FHR patterns have been proposed in the literature. The objective of this review is to describe the techniques, methodologies, and algorithms proposed in this field so far, reporting their main achievements and discussing the value they brought to the scientific and clinical community. The review explores the following two main approaches to the processing and analysis of FHR signals: traditional (or linear) methodologies, namely, time and frequency domain analysis, and less conventional (or nonlinear) techniques. In this scenario, the emerging role and the opportunities offered by Artificial Intelligence tools, representing the future direction of EFM, are also discussed with a specific focus on the use of Artificial Neural Networks, whose application to the analysis of accelerations in FHR signals is also examined in a case study conducted by the authors.

Reliable Prediction Models Based on Enriched Data for Identifying the Mode of Childbirth by Using Machine Learning Methods: Development Study

Background

The use of artificial intelligence has revolutionized every area of life such as business and trade, social and electronic media, education and learning, manufacturing industries, medicine and sciences, and every other sector. The new reforms and advanced technologies of artificial intelligence have enabled data analysts to transmute raw data generated by these sectors into meaningful insights for an effective decision-making process. Health care is one of the integral sectors where a large amount of data is generated daily, and making effective decisions based on these data is therefore a challenge. In this study, cases related to childbirth either by the traditional method of vaginal delivery or cesarean delivery were investigated. Cesarean delivery is performed to save both the mother and the fetus when complications related to vaginal birth arise.

Objective

The aim of this study was to develop reliable prediction models for a maternity care decision support system to predict the mode of delivery before childbirth.

Methods

This study was conducted in 2 parts for identifying the mode of childbirth: first, the existing data set was enriched and second, previous medical records about the mode of delivery were investigated using machine learning algorithms and by extracting meaningful insights from unseen cases. Several prediction models were trained to achieve this objective, such as decision tree, random forest, AdaBoostM1, bagging, and k-nearest neighbor, based on original and enriched data sets.

Results

The prediction models based on enriched data performed well in terms of accuracy, sensitivity, specificity, F-measure, and receiver operating characteristic curves in the outcomes. Specifically, the accuracy of k-nearest neighbor was 84.38%, that of bagging was 83.75%, that of random forest was 83.13%, that of decision tree was 81.25%, and that of AdaBoostM1 was 80.63%. Enrichment of the data set had a good impact on improving the accuracy of the prediction process, which supports maternity care practitioners in making decisions in critical cases.

Conclusions

Our study shows that enriching the data set improves the accuracy of the prediction process, thereby supporting maternity care practitioners in making informed decisions in critical cases. The enriched data set used in this study yields good results, but this data set can become even better if the records are increased with real clinical data.

Can empirical mode decomposition improve heartbeat detection in fetal phonocardiography signals?

BACKGROUND AND OBJECTIVE

A fetal phonocardiography signal can be hard to interpret and classify due to various sources of additive noise in the womb, spanning from fetal movement to maternal heart sounds. Nevertheless, the non-invasive nature of the method makes it potentially suitable for long-term monitoring of fetal health, especially since it can be implemented on ubiquitous devices such as smartphones. We have employed empirical mode decomposition for the extraction of intrinsic mode functions that would enable the utilization of additional characteristics from the signal.

METHODS

Fetal heart recordings from 7 pregnant women in the 3rd trimester or pregnancy were taken in parallel with a measurement microphone and a portable Doppler device. Signal peaks positions from the Doppler were taken as the locations of S1 heart sounds and subsequently used as classification labels for the microphone signal. After employing a moving window approach for segmentation, more than 7600 observations were stored in the final dataset. The 135 extracted features consisted of typical audio temporal and spectral characteristics, each taken from separate sets of audio signals and intrinsic mode functions. We have used a number of metrics and methods to validate the usability of features, including univariate analysis of feature ranking and importance. Furthermore, we have used machine learning to train a number of classifiers to validate the usability of features based on intrinsic mode functions, taking prediction accuracy as the comparison metric.

RESULTS

Features extracted from intrinsic mode functions combined with audio features significantly improve accuracy in comparison to using only audio features. The improvements of detection accuracy obtained with a selected set of combined features spanned from 3.8% to even 10.3% based on the employed classifier.

CONCLUSIONS

We have utilized empirical mode decomposition as a method of extracting features relevant for fetal heartbeat classification. The results show consistent improvements in detection accuracy when these characteristics are added to a set of conventional audio features. This implies substantial benefits of applying empirical mode decomposition and lays the groundwork for future research on fetal heartbeat detection.

Comparison of Multivariable Logistic Regression and Other Machine Learning Algorithms for Prognostic Prediction Studies in Pregnancy Care: Systematic Review and Meta-Analysis

Background

Predictions in pregnancy care are complex because of interactions among multiple factors. Hence, pregnancy outcomes are not easily predicted by a single predictor using only one algorithm or modeling method.

Objective

This study aims to review and compare the predictive performances between logistic regression (LR) and other machine learning algorithms for developing or validating a multivariable prognostic prediction model for pregnancy care to inform clinicians’ decision making.

Methods

Research articles from MEDLINE, Scopus, Web of Science, and Google Scholar were reviewed following several guidelines for a prognostic prediction study, including a risk of bias (ROB) assessment. We report the results based on the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Studies were primarily framed as PICOTS (population, index, comparator, outcomes, timing, and setting): Population: men or women in procreative management, pregnant women, and fetuses or newborns; Index: multivariable prognostic prediction models using non-LR algorithms for risk classification to inform clinicians’ decision making; Comparator: the models applying an LR; Outcomes: pregnancy-related outcomes of procreation or pregnancy outcomes for pregnant women and fetuses or newborns; Timing: pre-, inter-, and peripregnancy periods (predictors), at the pregnancy, delivery, and either puerperal or neonatal period (outcome), and either short- or long-term prognoses (time interval); and Setting: primary care or hospital. The results were synthesized by reporting study characteristics and ROBs and by random effects modeling of the difference of the logit area under the receiver operating characteristic curve of each non-LR model compared with the LR model for the same pregnancy outcomes. We also reported between-study heterogeneity by using τ² and I².

Results

Of the 2093 records, we included 142 studies for the systematic review and 62 studies for a meta-analysis. Most prediction models used LR (92/142, 64.8%) and artificial neural networks (20/142, 14.1%) among non-LR algorithms. Only 16.9% (24/142) of studies had a low ROB. A total of 2 non-LR algorithms from low ROB studies significantly outperformed LR. The first algorithm was a random forest for preterm delivery (logit AUROC 2.51, 95% CI 1.49-3.53; I²=86%; τ²=0.77) and pre-eclampsia (logit AUROC 1.2, 95% CI 0.72-1.67; I²=75%; τ²=0.09). The second algorithm was gradient boosting for cesarean section (logit AUROC 2.26, 95% CI 1.39-3.13; I²=75%; τ²=0.43) and gestational diabetes (logit AUROC 1.03, 95% CI 0.69-1.37; I²=83%; τ²=0.07).

Conclusions

Prediction models with the best performances across studies were not necessarily those that used LR but also used random forest and gradient boosting that also performed well. We recommend a reanalysis of existing LR models for several pregnancy outcomes by comparing them with those algorithms that apply standard guidelines.

Trial Registration

PROSPERO (International Prospective Register of Systematic Reviews) CRD42019136106; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=136106

Analysis of the fetal cardio-electrohysterographic coupling at the third trimester of gestation in healthy women by Bivariate Phase-Rectified Signal Averaging

INTRODUCTION

The fetal cardio-electrohysterographic coupling (FCEC) is defined as the influence of the uterine electrical activity on fetal heart rate. FCEC has been mainly evaluated by visual analysis of cardiotocographic data during labor; however, this physiological phenomenon is poorly explored during the antenatal period. Here we propose an approach known as Bivariate Phase-Rectified Signal Averaging analysis (BPRSA) to assess such FCEC in the late third trimester of low-risk pregnancies. We hypothesized that BPRSA is a more reliable measure of FCEC than visual analysis and conventional measures such as cross-correlation, coherence, and cross-sample entropy. Additionally, by using BPRSA it is possible to detect FCEC even from the third trimester of pregnancy.

MATERIAL AND METHODS

Healthy pregnant women in the last third trimester of pregnancy (36.6 ± 1.8 gestational weeks) without any clinical manifestation of labor were enrolled in the Maternal and Childhood Research Center (CIMIGen), Mexico City (n = 37). Ten minutes of maternal electrohysterogram (EHG) and fetal heart rate (FHR) data were collected by a transabdominal non-invasive device. The FCEC was quantified by the coefficient of coherence, the maximum normalized cross-correlation, and the cross-sample entropy obtained either from the EHG and FHR raw signals or from the corresponding BPRSA graphs.

RESULTS

We found that by using BPRSA, the FCEC was detected in 92% cases (34/37) compared to 48% cases (18/37) using the coefficient of coherence between the EHG and FHR raw signals. Also, BPRSA indicated FCEC in 82% cases (30/37) compared to 30% cases (11/37) using the maximum normalized cross-correlation. By comparing the analyses, the BPRSA evidenced higher FCEC in comparison to the coupling estimated from the raw EHG and FHR signals.

CONCLUSIONS

Our results support the consideration that in the third trimester of pregnancy, the fetal heart rate is also influenced by uterine activity despite the emerging manifestation of this activity before labor. To quantify FCEC, the BPRSA can be applied to FHR and EHG transabdominal signals acquired in the third trimester of pregnancy.