Early Detection of Intrauterine Fetal Demise: History
View Latest Version
Please note this is an old version of this entry, which may differ significantly from the current revision.
Contributor:
Jayakumar Kaliappan
,
Apoorva Reddy Bagepalli
,
Shubh Almal
,
Rishabh Mishra
,
Yuh-Chung Hu
,
Kathiravan Srinivasan

Intrauterine fetal demise in women during pregnancy is a major contributing factor in prenatal mortality and is a major global issue in developing and underdeveloped countries. When an unborn fetus passes away in the womb during the 20th week of pregnancy or later, early detection of the fetus can help reduce the chances of intrauterine fetal demise.

  • CTG (Cardiotocography) data
  • fetal health classification
  • machine learning

1. Introduction

Women go through a lot during their pregnancy. It is a very vital stage in a woman’s life, and the happiness brought by a newborn child is immeasurable at times. However, there are instances where a fetal demise occurs in the womb. Numerous causes, including intrapartum difficulties, hypertension, diabetes, infection, congenital and genetic abnormalities, and placental malfunction, contribute to such events [1][2]. According to a study conducted on 6942 deliveries, 250 intrauterine fetal deaths were reported. Anaemia, pregnancy-induced hypertension, illiteracy, and low socioeconomic position were the leading causes of these fetal fatalities. As per WHO statistics, globally, 2 million stillbirths occur every year, which is one death every 6 s. Among medical problems, the study discovered that hypertension and anemia were related to a greater likelihood of stillbirth. Pregnancy-induced hypertension was responsible for 19.6% of cases, antepartum hemorrhage was responsible for 12% of cases, labour trauma and stress were responsible for 34% of cases, maternal medical conditions were responsible for 12.8% of cases, fetal growth retardation was responsible for 5.2% of cases, congenital malformation was responsible for 8% of cases, prematurity was responsible for 2.8% of cases, and unknown etiology was responsible for 5.6% of cases [3]. Maintaining the proper health of the fetus plays an important part in the chance of survivability of the fetus. Cardiotocographic (CTG) data is utilized by medical professionals in order to predict the health of the fetus; however, due to the increasing frequency of examinations and the shortage of medical professionals, it becomes challenging to decide which patient should be granted priority or which patient needs proper intensive care.

2. Early Detection of Intrauterine Fetal Demise

Dilip Kumar Sharma [3] worked on Support Vector Machine, Random Forest, Multilayer Perceptron, and K-Nearest Neighbors to predict fetal health using data from CTG [1]. They discovered that fetal heart rate deceleration is an important marker in determining health status through Correlation Analysis and Regression Analysis. Nabillah Rahmayanti et al. performed a study that employed deep learning techniques to extract high-level features from a dataset in order to categorize fetal health using CTG data. Fetal health was categorized using a number of different machine-learning algorithms, such as Artificial Neural Networks (ANN), K-Nearest Neighbor algorithm (KNN), Light Gradient Boosting Machine (LGBM), Long Short-Term Memory (LSTM), Random Forest (RF), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGB) [2]. Jiaming L Xiaoxiang Liu deployed twelve distinct machine learning models that were trained on the CTG dataset. The Blender model was constructed using the soft voting integration approach from the top four models, and it was contrasted with the stacking model. It fared quite well in tests of other classification models [4]. Ilias Tougui et al. investigated two cross-validation methodologies, subject-wise and record-wise techniques, to demonstrate the influence of machine learning algorithms such as Support Vector Machine and Random Forest trained to detect Parkinson’s disease [5]. To analyze and classify prenatal health problems, Jayashree Piri et al. suggested an association-based classification model. The author used several association rules to improve the classifier’s accuracy, obtaining an accuracy around 83–84% [6]. D. Tran, S. Cooke, P.J. Illingworth, and D.K. Gardner showed that deep learning has the same potential to improve clinical IVF by using the time-lapse video to predict fetal heart pregnancy. This research’s retrospective analysis has shown that IVY is a useful tool for predicting embryo implantation rate [7].
Anand Sontakke et al. classified cardiotocography signals using machine learning, performing 10-fold cross-validation and spot-checking on the dataset and analyzing the results [8]. The classification of the fetus state was carried out by Andrew Maranho et al. using the data from cardiotocography and machine learning algorithms. A lightgbm model that had been post-processed using cross-validation ensembling and adjusted with Gaussian process regression was used after a baseline random forest model [9]. Machine learning methods were used in the research of Md. Tamjid Rayhan, et al. on the automatic diagnosis of fetal health status using cardiotocography data [10]. In their study of five different machine learning algorithms, Eva Malacova and Sawitchaya Tippaya classified binary data as childbirth vs. live delivery. The classifiers included multilayer perceptron (MLP) neural networks, random forest, classification and regression trees (CART), and extreme gradient boosting (XGBoost) [11]. Naveen Reddy Navuluri researched fetal health prediction using classification techniques. In this research, four machine learning models were presented. The SVM model provided the best outcome with the highest accuracy among the four machine learning models [12]. Mario W.L Morerira et al. performed hypertensive disorder prediction in high-risk pregnancy groups using tree-based techniques ID3 and NBTree. Fmeasure, kappa static and ROC were used to assess its performance [13].
Efficient fetal acidosis detection using the relevant subset of features with sparse support vector machine classification was performed by Jiri Spilka et al. and it achieved better classification results [14]. The feature selection was carried out by Ragunath Dey et al. utilising a crowding distance-based multi-objective genetic algorithm (MOGA-CD). Using chi-square and ANOVA, the most important factors that determine the fetus’s health are assessed. The correlation matrix provides the connection strength between the characteristics and the target attribute [15]. Prakriti Dwivedi et al. classified the primary factors influencing fetal health status using cardiotocography measurements [16]. The fetal heart rate and uterine contractions are obtained respectively during cardiotocography, and the dataset was accessible at UCI. Three classification algorithms—Decision Tree (DT), Support Vector Machine (SVM), and Naïve Bayes—were applied to this dataset by Kanika Agrawal (NB) [17]. Using a convolutional neural network, Jianqiang Li et al. conducted research on the automatic classification of fetal heart rate. To categorize the fetal heart rate recordings and obtain the requisite accuracy, this research employed its own model as well as statistical techniques such as SVM and MLP [18]. Adem Kuzu and Yunus Santur conducted fetal health pattern classification using ensemble learning. Obstetricians can utilize CTG data to determine whether a fetus is healthy and when medical intervention is required. The goal of their study was to eliminate discrepancies by evaluating CTG data with neural networks [19].

This entry is adapted from the peer-reviewed paper 10.3390/diagnostics13101692

References

  1. Mehbodniya, A.; Lazar, A.J.P.; Webber, J.; Sharma, D.K.; Jayagopalan, S.; Singh, P.; Rajan, R.; Pandya, S.; Sengan, S. Fetal health classification from cardiotocographic data using machine learning. Expert Syst. 2022, 39, e12899.
  2. Rahmayanti, N.; Pradani, H.; Pahlawan, M.; Vinarti, R. Comparison of machine learning algorithms to classify fetal health using cardiotocogram data. Procedia Comput. Sci. 2022, 197, 162–171.
  3. Sharma, S.; Sidhu, H.; Kaur, S. Analytical study of intrauterine fetal death cases and associated maternal conditions. Analytical study of intrauterine fetal death cases and associated maternal conditions. Int. J. Appl. Basic Med. Res. 2016, 6, 11–13.
  4. Li, J.; Liu, X. Fetal health classification based on machine learning. In Proceedings of the 2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), Nanchang, China, 26–28 March 2021; pp. 899–902.
  5. Tougui, I.; Jilbab, A.; El Mhamdi, J. Impact of the choice of cross-validation techniques on the results of machine learning-based diagnostic applications. Healthc. Inform. Res. 2021, 27, 189–199.
  6. Piri; Jayashree; Mohapatra, P. Exploring fetal health status using an association based classification approach. In Proceedings of the 2019 International Conference on Information Technology (ICIT), Bhubaneswar, India, 19–21 December 2019; pp. 166–171.
  7. Tran, D.; Cooke, S.; Illingworth, P.J.; Gardner, D.K. Deep learning as a predictive tool for fetal heart pregnancy following time-lapse incubation and blastocyst transfer. Hum. Reprod. 2019, 34, 1011–1018.
  8. Sontakke, S.A.; Lohokare, J.; Dani, R.; Shivagaje, P. Classification of cardiotocography signals using machine learning. In Intelligent Systems and Applications, Proceedings of the 2018 Intelligent Systems Conference (IntelliSys), London, UK, 6–7 September 2018; Springer International Publishing: Berlin/Heidelberg, Germany, 2019; Volume 2, pp. 439–450.
  9. Ventura Dadario, A.M.; Espinoza, C.; Araújo Nogueira, W. Classification of Fetal State through the application of Machine Learning techniques on Cardiotocography records: Towards Real World Application. medRxiv 2021.
  10. Rayhana, T.; Arefina, A.S.; Chowdhury, S.A. Automatic detection of fetal health status from cardiotocography data using machine learning algorithms. J. Bangladesh Acad. Sci. 2021, 45, 155–167.
  11. Malacova, E.; Tippaya, S.; Bailey, H.D.; Chai, K.; Farrant, B.M.; Gebremedhin, A.T.; Leonard, H.; Marinovich, M.L.; Nassar, N.; Phatak, A.; et al. Stillbirth risk prediction using machine learning for a large cohort of births from Western Australia, 1980–2015. Sci. Rep. 2020, 10, 5354.
  12. Navuluri, N.R. Fetal Health Prediction using Classification Techniques. Int. J. Eng. Res. Technol. 2021, 10, 383–386.
  13. Moreira, M.W.L.; Rodrigues, J.J.; Oliveira, A.M.; Saleem, K.; Neto, A.J.V. Predicting hypertensive disorders in high-risk pregnancy using the random forest approach. In Proceedings of the 2017 IEEE International Conference on Communications (ICC), Paris, France, 21–25 May 2017; pp. 1–5.
  14. Abry, P.; Spilka, J.; Leonarduzzi, R.; Chudáček, V.; Pustelnik, N.; Doret, M. Sparse learning for Intrapartum fetal heart rate analysis. Biomed. Phys. Eng. Express 2018, 4, 034002.
  15. Piri, J.; Mohapatra, P.; Dey, R. Fetal health status classification using moga-cd based feature selection approach. In Proceedings of the 2020 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT), Bangalore, India, 2–4 July 2020; pp. 1–6.
  16. Dwivedi, P.; Khan, A.A.; Mugde, S.; Sharma, G. Diagnosing the major contributing factors in the classification of the fetal health status using cardiotocography measurements: An automl and xai approach. In Proceedings of the 2021 13th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), Pitesti, Romania, 1–3 July 2021; pp. 1–6.
  17. Agrawal, K.; Mohan, H. Cardiotocography analysis for fetal state classification using machine learning algorithms. In Proceedings of the 2019 International Conference on Computer Communication and Informatics (ICCCI), Coimbatore, India, 23–25 January 2019; pp. 1–6.
  18. Li, J.; Chen, Z.-Z.; Huang, L.; Fang, M.; Li, B.; Fu, X.; Wang, H.; Zhao, Q. Automatic classification of fetal heart rate based on convolutional neural network. IEEE Internet Things J. 2018, 6, 1394–1401.
  19. KUZU, A.; SANTUR, Y. Fetal Health Pattern Classification Using Ensemble Learning. In Proceedings of the 3rd International Conference on Applied Engineering and Natural Sciences, Konya, Turkey, 10–13 November 2022.
More
© Text is available under the terms and conditions of the Creative Commons Attribution (CC BY) license; additional terms may apply. By using this site, you agree to the Terms and Conditions and Privacy Policy.
This entry is offline, you can click here to edit this entry!
Video Production Service
Feedback