A Machine Learning Approach for the Prediction of Fetal Health using CTG

Pradhan, Astik Kumar; Rout, Jitendra Kumar; Maharana, Aurobinda Bharat; Balabantaray, Bunil Kumar; Ray, Niranjan Kumar

doi:10.1109/ocit53463.2021.00056

Cited by 11 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that, based on the same dataset, [27] found that, in terms of accuracy, Random Forest algorithm also performs better than the logistic regression, kNN and Gradient Boosting Machine. In the following, we investigate the performance of each algorithm based on one (not necessarily the optimal one) randomly chosen iteration out of the 500.…”

Section: Performance Assessment Of Classifiersmentioning

confidence: 82%

Online Nonparametric Supervised Learning for Massive Data

Chaouch,

Al-Hamed

2024

Preprint

View full text Add to dashboard Cite

Despite their benefits in terms of simplicity, low computational cost and data requirement, parametric machine learning algorithms, such as linear discriminant analysis, quadratic discriminant analysis or logistic regression, suffer from serious drawbacks including linearity, poor fit of features to the usually imposed normal distribution and high dimensionality. Batch kernel-based nonparametric classifier, which overcomes the linearity and normality of features constraints, represents an interesting alternative for supervised classification problem. However, it suffers from the well-known ''curse of dimension". The problem can be alleviated by the explosive sample size in the era of big data, while large-scale data size presents some challenges in the storage of data and the calculation of the classifier. These challenges make the classical batch nonparametric classifier no longer applicable. This motivates us to develop a fast algorithm adapted to the real-time calculation of the nonparametric classifier in massive as well as streaming data frameworks. This online classifier includes two steps. First, we consider an online principle components analysis to reduce the dimension of the features with a very low computation cost. Then, a stochastic approximation algorithm is deployed to obtain a real-time calculation of the nonparametric classifier. The proposed methods are evaluated and compared to some commonly used machine learning algorithms for real-time fetal well-being monitoring. The study revealed that, in terms of accuracy, the offline (or Batch), as well as, the online classifiers are serious competitors to the random forest algorithm. Moreover, we show that the online classifier gives the best trade-off accuracy/computation cost compared to the offline classifier.

show abstract

Section: Performance Assessment Of Classifiersmentioning

confidence: 82%

Online Nonparametric Supervised Learning for Massive Data

Chaouch,

Al-Hamed

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In contrast to previous approaches [8][9][10][11][12][13], we leveraged deep learning to enable end-to-end prediction of fetal hypoxia, taking into account temporal and contextual cues often overlooked by feature-based methods. The robustness of our model highlights the compatibility of our approach with intermittent CTG monitoring settings, particularly in low-resource environments where intermittent monitoring is standard practice.…”

Section: Discussionmentioning

confidence: 99%

“…Machine learning algorithms to classify abnormal CTGs from tabulated rules-based extraction of diagnostic features have shown promise for improving clinical decision support [7][8][9][10][11][12]. However, they reduce rich CTG signal information to a few numbers which ignore important temporal and contextual cues such as the relative timing of delivery, maternal risk factors, etc.…”

Section: Introductionmentioning

confidence: 99%

Development and Evaluation of Deep Learning Models for Cardiotocography Interpretation

Chiou,

Young-Lin,

Kelly

et al. 2024

Preprint

View full text Add to dashboard Cite

The inherent variability in the visual interpretation of cardiotocograms (CTGs) by obstetric clinical experts, both intra- and inter-observer, presents a substantial challenge in obstetric care. In response, we investigate automated CTG interpretation as a potential solution to enhance the early detection of fetal hypoxia during labor, which has the potential to reduce unnecessary operative interventions and improve overall maternal and neonatal care. This study employs deep learning techniques to reduce the subjectivity associated with visual CTG interpretation. Our results demonstrate that using objective umbilical cord blood pH outcome measurements, rather than clinician-defined Apgar scores, yields more consistent and robust model performance. Additionally, through a series of ablation studies, we explore the impact of temporal distribution shifts on the performance of these deep learning models. We examine tradeoffs between performance and fairness, specifically evaluating performance across demographic and clinical subgroups. Finally, we discuss the practical implications of our findings for the real-world deployment of such systems, emphasizing their potential utility in medical settings with limited resources.

show abstract

“…Pradhan et al aimed to investigate how well ML models perform in predicting fetal health using CTG dataset (45). They used different classifiers such as LR, KNN, RF and GB and evaluated their performance in terms of accuracy, precision, recall and F 1 score.…”

Section: Fasihi Et Al Have Proposed a One-dimensional Convolutional N...mentioning

confidence: 99%

Artificial Intelligence in Fetal Health Diagnosis: A Systematic Literature Review

Kuzu,

Santur

2023

TUSEB

View full text Add to dashboard Cite

Obstetricians commonly use Non-Stress Test to evaluate fetal well-being during the antepartum and intrapartum periods by measuring fetal heart rate and uterine contractions of the mother. Non-Stress Test is also used to diagnose fetal distress at an early stage. Early diagnosis and treatment can increase the fetus's survival rate and improve their quality of life. The fetal heart rate and uterine contraction signals obtained from the Non-Stress Test are recorded on a paper called a trace. Obstetricians interpret the trace to make decisions about the fetus's condition. However, traditional analysis of Non-Stress Test takes time, and there are differences in interpretation among experts. Newly qualified doctors and midwives are more prone to making mistakes and incorrect decisions. To overcome the differences in the interpretation of Non-Stress Test analysis and to automate the process to minimize diagnostic errors, machine learning and deep learning models have been increasingly used in recent years. In this study, the literature of the past five years is researched, and numerical expressions, tables, and graphs related to this are presented.

show abstract

A Machine Learning Approach for the Prediction of Fetal Health using CTG

Cited by 11 publications

References 12 publications

Online Nonparametric Supervised Learning for Massive Data

Online Nonparametric Supervised Learning for Massive Data

Development and Evaluation of Deep Learning Models for Cardiotocography Interpretation

Artificial Intelligence in Fetal Health Diagnosis: A Systematic Literature Review

Contact Info

Product

Resources

About