A Machine Learning Approach to Identifying Maternal Risk Factors for Congenital Heart Disease
DOI:
https://doi.org/10.55640/Keywords:
Congenital heart defects, Machine learningAbstract
Objective: This article explores the application of machine learning (ML) models to identify maternal risk factors for congenital heart defects (CHDs) in offspring. CHDs are the most common birth anomalies, affecting approximately 1 in 100 live births, and early risk identification is crucial for improving neonatal outcomes. This study aims to evaluate the performance of various ML algorithms and identify key maternal factors associated with CHD prediction.
Methods: We conducted a review of existing literature, focusing on studies that used ML models for CHD risk prediction. The analysis included various algorithms, from simpler models like Logistic Regression to more complex ensemble methods (Random Forest, Gradient Boosting) and Neural Networks. We also considered critical aspects of the ML pipeline, including data preprocessing, feature selection from maternal electronic health records and environmental registries, and the use of key evaluation metrics such as AUC-ROC, precision, recall, and F1-score to assess clinical utility.
Results: Our analysis indicates that advanced ML models, particularly ensemble methods and Neural Networks, consistently outperform traditional statistical approaches and simpler ML models. These models effectively leverage a wide range of input features, including maternal age, pre-existing medical conditions, and environmental exposures, to achieve superior predictive accuracy and recall. The enhanced performance of these models highlights their potential for identifying at-risk pregnancies, which is essential given the high stakes of false negatives.
Conclusion: Machine learning is a transformative tool for prenatal risk assessment, offering a powerful way to identify maternal risk factors for CHDs. The application of these models can facilitate targeted counseling for parents, optimize prenatal monitoring, and enable planned deliveries at specialized centers. While challenges such as data privacy and model interpretability must be addressed, the integration of ML into clinical practice holds immense promise for improving health outcomes for infants with congenital heart defects.
References
Ali, F. S. A., Al Hammadi, S. A. A., Redouane, A., & Tariq, M. U. (2021). Prediction of congenital heart diseases in children using machine learning. Journal of Management Information and Decision Sciences, 24, 1-34. https://www.abacademies.org/articles/prediction-of-congenital-heart-diseases-in-children-using-machine-learning.pdf
Chang, J. J., Binuesa, F., Caneo, L. F., Turquetto, A. L. R., Arita, E. C. T. C., Barbosa, A. C., Da Silva Fernandes, A. M., Trindade, E. M., Jatene, F. B., Dossou, P., & Jatene, M. B. (2020). Improving preoperative risk-of-death prediction in surgery congenital heart defects using artificial intelligence model: A pilot study. PLoS One, 15(9), e0238199. https://doi.org/10.1371/journal.pone.0238199
Dangare, C., & Apte, S. (2012). A data mining approach for prediction of heart disease using neural networks. International Journal of Computer Engineering and Technology, 3(3). https://ssrn.com/abstract=2175569
Domyati, A., & Memon, Q. (2022). Robust detection of cardiac disease using machine learning algorithms. In Proceedings of the 5th International Conference on Control and Computer Vision (pp. 52-55). https://doi.org/10.1145/3561613.3561622
Desai, H., Jones, C. E., Fogel, J. L., Negrin, K. A., Slater, N. L., Morris, K., Doody, L. R., Engstler, K., Torzone, A., Smith, J., & Butler, S. C. (2023). Assessment and management of feeding difficulties for infants with complex CHD. Cardiology in the Young, 33(1), 1-10. https://doi.org/10.1017/S1047951122004024
Hammoud, A., Karaki, A., Tafreshi, R., Abdulla, S., & Wahid, M. (2024). Coronary heart disease prediction: A comparative study of machine learning algorithms. Journal of Advances in Information Technology, 15(1), 27-32. https://doi.org/10.12720/jait.15.1.27-32
Liu, S., Liu, J., Tang, J., Ji, J., Chen, J., & Liu, C. (2009). Environmental risk factors for congenital heart disease in the Shandong peninsula, China: A hospital-based case-control study. Journal of Epidemiology, 19(3), 122-130. https://doi.org/10.2188/jea.JE20080039
Lo Muzio, F. P., Rozzi, G., Rossi, S., Luciani, G. B., Foresti, R., Cabassi, A., Fassina, L., & Miragoli, M. (2021). Artificial intelligence supports decision making during open-chest surgery of rare congenital heart defects. Journal of Clinical Medicine, 10(22), 5330. https://doi.org/10.3390/jcm10225330
Lopez, D., & Manogaran, G. (2018). Health data analytics using scalable logistic regression with stochastic gradient descent. International Journal of Advanced Intelligence Paradigms, 10(1/2), 118. https://doi.org/10.1504/IJAIP.2018.10010530
Luo, Y., Li, Z., Guo, H., Cao, H., Song, C., Guo, X., & Zhang, Y. (2017). Predicting congenital heart defects: A comparison of three data mining methods. PLoS One, 12(5), e0177811. https://doi.org/10.1371/journal.pone.0177811
Meda, J. T., & Mushiri, T. (2020). Predicting congenital heart diseases using Machine learning. In Proceedings of the 2nd African International Conference on Industrial Engineering and Operations Management (pp. 1716-1725). https://www.ieomsociety.org/harare2020/papers/415.pdf
Mello, C. A., Lewis, R., Brooks-Kayal, A., Carlsen, J., Grabenstatter, H., & White, A. M. (2014). Supervised learning for the neurosurgery intensive care unit using single-layer perceptron classifiers. In Ślȩzak, D., Tan, A.-H., Peters, J. F., & Schwabe, L. (Eds.), Lecture notes in computer science: Vol. 8609. Brain informatics and health: BIH 2014 (pp. 231-241). Springer. https://doi.org/10.1007/978-3-319-09891-3_22
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Dr. Larian D. Venorth, Prof. Elias J. Vance (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain the copyright of their manuscripts, and all Open Access articles are disseminated under the terms of the Creative Commons Attribution License 4.0 (CC-BY), which licenses unrestricted use, distribution, and reproduction in any medium, provided that the original work is appropriately cited. The use of general descriptive names, trade names, trademarks, and so forth in this publication, even if not specifically identified, does not imply that these names are not protected by the relevant laws and regulations.