A Review of Expert Systems For Detecting Pregnancy Abnormalities Using Machine Learning Technologies
Abstract
The field of medical diagnosis has made significant progress with the introduction of machine learning techniques. This article presents a comprehensive review of studies in which researchers have developed expert systems for diagnosing pregnancy abnormalities using various machine learning techniques. Emphasizing the crucial role of data for learning and its preprocessing, the publications reviewed in the article compare the accuracy of different machine learning algorithms in this area. The analyzed research has primarily focused on building expert systems to diagnose pregnancy-related pathologies and complications in order to improve outcomes for expectant mothers and their future children. Using a wide range of machine learning approaches, including decision trees, support vector machines, random forest, artificial neural networks, and others, the effectiveness of each algorithm reviewed in this article in accurately predicting pregnancy-related problems was investigated.
One of the key points of this review is the emphasis on the quality and variety of training data. Particular attention was paid to the reliability and completeness of the datasets in analyzing the publications to allow machine learning algorithms to achieve higher diagnostic accuracy. Studies were selected for the review that used parameters recognized by the medical community as indicators of various pathologies for training.
An important criterion for selecting the review publications was the availability of data preprocessing in them to correct missing values, noise and class imbalance. These tasks play an essential role in improving the performance of the developed expert systems. By critically evaluating the methodologies and algorithms used in the reviewed publications, this paper provides valuable information for future research and development in this area.
References
Werbos P. J. Beyond regression: New tools for prediction and analysis in the behavioral sciences / Ph. D.
thesis, Harvard University. Cambridge, MA, 1974.
Maylawati D. S., Ramdhani M. A.,. Zulfikar W. B, Taufik I., Darmalaksana W. Expert system for
predicting the early pregnancy with disorders using artificial neural network // Proc. of 2017 5th Int.
Conf. on Cyber and IT Service Management (CITSM). 8–10 Aug. 2017. Denpasar, Indonesia, 2017. P. 1–6.
doi:10.1109/CITSM.2017.8089243
Raghav H. K. V. S., Devi S. P., Rengaraj N., Thanranikumar E. Prediction of Preterm Pregnancies using
Soft Computing Techniques Neural Networks and Gradient Descent Optimizer // Proc. 2018 Int. Conf.
on Computer Communication and Informatics (ICCCI). 4–6 Jan. 2018. Coimbatore, India, 2018. P. 1–4.
doi:10.1109/ICCCI.2018.8441432
Ruder S. An Overview of Gradient Descent Optimization Algorithms // arXiv:1609.04747v2[cs.LG],
Tahir M., Badriyah T., Syarif I. Neural Networks Algorithm to Inquire Previous Preeclampsia Factors
in Women with Chronic Hypertension During Pregnancy in Childbirth Process // Proc. 2018 Int.
Electronics Symposium on Knowledge Creation and Intelligent Computing (IES-KCIC). 23–30 Oct. 2018.
Bali, Indonesia, 2018. P. 51–55. doi:10.1109/KCIC.2018.8628588
Neocleous C. K., Anastasopoulos P., Nikolaides K. H., Schizas C. N., Neokleous K. C. Neural networks to
estimate the risk for preeclampsia occurrence // Proc. 2009 Int. Joint Conf. on Neural Networks. 14–19
Jun. 2009. Atlanta, GA, USA, 2009. P. 2221–2225. doi: 10.1109/IJCNN.2009.5178820
Neocleous C., Nikolaides K., Neokleous K., Schizas C. Neural networks to investigate the effects of
smoking and alcohol abuse on the risk for preeclampsia // Proc. 2009 9th International Conference
on Information Technology and Applications in Biomedicine. 5–7 Nov. 2009. P. 1–5. Larnaka, Cyprus,
doi:10.1109/ITAB.2009.5394421
Purwanti E., Preswari I. S., Ernawati E. Early Risk Detection of Pre-eclampsia for Pregnant Women
Using Artificial Neural Network // International Journal of Online and Biomedical Engineering (iJOE).
Vol. 15, № 02. P. 71–71. doi:10.3991/ijoe.v15i02.9680
Janghel R. R., Shukla A., Tiwari R., Tiwari P. Clinical Decision Support System for Fetal Delivery Using
Artificial Neural Network // Proc. of 2009 International Conference on New Trends in Information and
Service Science. 30 Jun – 2 Jul 2009. Beijing, China, 2009. P. 1070–1075. doi:10.1109/niss.2009.66
Kohonen T. Learning vector quantizatio // M. A. Arbib ed., The Handbook of Brain Theory and Neural
Networks. Cambridge, MA, USA: MIT Press, 1995. P. 537–540.
Wanriko S., Hnoohom N., Wongpatikaseree K., Jitpattanakul A., Musigavong O. Risk Assessment
of Pregnancy-induced Hypertension Using a Machine Learning Approach // Proc. of 2021 Joint
International Conference on Digital Arts, Media and Technology with ECTI Northern Section
Conference on Electrical, Electronics, Computer and Telecommunication Engineering. 03–06 Mar
P. 233–237. Cha-am, Thailand, 2021; doi:10.1109/ECTIDAMTNCON51128.2021.9425764
Chawla N. V., Bowyer K. W., Hall L. O., Kegelmeyer W. P. SMOTE: Synthetic Minority Over-sampling
Technique // Journal of Artificial Intelligence Research. 2002. Vol. 16. P. 321–357. doi:10.1613/jair.953.
Chinnaiyan R., Alex S. Machine Learning Approaches for Early Diagnosis and Prediction of Fetal
Abnormalities //Proc. 2021 Int. Conf. on Computer Communication and Informatics (ICCCI). 27–29 Jan
Coimbatore, India, 2021. P. 1–3. doi:10.1109/ICCCI50826.2021.9402317
Anbu S., Sarmah B. Machine learning approach for predicting womens health risk // Machine learning
approach for predicting womens health risk // Proc. of 2017 4th International Conference on Advanced
Computing and Communication Systems (ICACCS). 6–7 Jan 2017. Coimbatore, India, 2017. P. 1–4.
doi:10.1109/ICACCS.2017.8014588
Chen T., Guestrin C. XGBoost: A Scalable Tree Boosting System // Proc. of the 22nd Int. Conf. on
Knowledge Discovery and Data Mining. 13-17 Aug 2016. San Francisco California, USA, 2016. P. 785–
doi:10.1145/2939672.2939785
Sreekantha D. K. et al. Prediction of difficulties in Intubation using an Expert system // Proc. 2019
IEEE Int. Conf. on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER). 11–12
Aug 2019. Manipal, India, 2019. P. 1–7. doi:10.1109/DISCOVER47552.2019.9007952
Carre˜no J. F., Qiu P. Feature selection algorithms for predicting preeclampsia: A comparative
approach // Proc. of 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).
–19 Dec 2020. Seoul, Korea (South), 2020. P. 2626–2631. doi:10.1109/BIBM49941.2020.9313108
Qiu P., Gentles A. J., Plevritis S. K. Discovering Biological Progression Underlying Microarray Samples //
PLoS Computational Biology. 2011. Vol. 7, № 4. P. e1001123. doi:10.1371/journal.pcbi.1001123
Raza A., Siddiqui H. U. R., Munir K., Almutairi M., Rustam F., Ashraf I. Ensemble learning-based feature
engineering to analyze maternal health during pregnancy and health risk prediction // PLOS ONE.
Vol. 17, № 11. P. e0276525. doi:10.1371/journal.pone.0276525
He K., Zhang X., Ren S., Sun J. Delving Deep into Rectifiers: Surpassing Human-Level Performance
on ImageNet Classification // Proc. of 2015 IEEE International Conference on Computer Vision (ICCV).
–13 Dec 2015. P. 1026-1034. Santiago, Chile, 2015. doi:10.1109/iccv.2015.123 1026–1034
Lea C. et al. Temporal convolutional networks: A unified approach to action segmentation // Proc. 14th
European ConferenceComputer Vision — ECCV 2016. 11–14 Oct. 2016. Amsterdam, The Netherlands,
P. 47–54. doi:10.1007/978-3-319-49409-8_7
Singhal K. et al. Towards Expert-Level Medical Question Answering with Large Language Models //
arXiv:2305.09617[cs.LG], 2023.
Surendiran Dr. R., Aarthi R., Thangamani M., Sugavanam S., Sarumathy R. A Systematic Review using
Machine Learning Algorithms for Predicting Preterm Birt // International Journal of Engineering
Trends and Technology. 2022. Vol. 70, № 5. P. 46–59. doi:10.14445/22315381/IJETT-V70I5P207
Sharifi-Heris Z., Laitala J., Arola A., Rahmani A. M., Bender M. Machine Learning Approach for Preterm
Birth Prediction Using Health Records: Systematic Review // JMIR Med Inform. 2022. Vol. 10, № 4.
P. e33875. doi:10.2196/33875
Bertini A., Salas R., Chabert S., Sobrevia L., Pardo F. Using Machine Learning to Predict Complications
in Pregnancy: A Systematic Review // Front. Bioeng. Biotechnol. 2012. Vol. 9. P. 780389. doi:10.
/fbioe.2021.780389
Damaraji G. M., Permanasari A. E.,. Hidayah I. A Review of Expert System for Identification Various
Risk in Pregnancy // Proc. of 3rd International Conference on Information and Communications
Technology (ICOIACT). 24–26 Nov 2020. Yogyakarta, Indonesia, 2020. P. 99–104. doi:10.1109/ICOIACT
2020.9332003
Ramla M., Sangeetha S., Nickolas S. Machine Learning for High Risk Pregnancies Pre-Term Birth
Prediction: A Retrospective // International Journal of Engineering and Technology(UAE). 2018. Vol. 7, № 2.22. P. 5–8. doi:10.14419/ijet.v7i2.22.11799.
Столбов А. П. Обезличивание персональных данных в здравоохранении // Врач и информа-
ционные технологии. 2017. № 3. С. 25–36.
Курдюмов Д. А., Кашин А. В., Рябов Н. Ю., Новицкий Р. Э., Гусев А. В. Опыт применения техноло-
гий искусственного интеллекта для развития профилактического здравоохранения на при-
мере кировской области // Менеджер здравоохранения. 2023. № 6. C. 62–69. doi:10.21045/1811-
-2023-6-62-69
Указ Президента Российской Федерации от 10.10.2019 № 490 ≪О развитии искусственного
интеллекта в Российской Федерации≫ [Электронный ресурс] http://publication.pravo.gov.ru/
Document/View/0001201910110003 (дата обращения: 16.11.2023).
This work is licensed under a Creative Commons Attribution 4.0 International License.
