Orclever Proceedings of Research and Development

Conducting Maternal Health Risk Analysis with Deep Learning

Burçin Yönel Önem

Gazi University

https://orcid.org/0000-0002-5395-5164

Hacer Karacan

Gazi University

https://orcid.org/0000-0001-6788-008X

DOI: https://doi.org/10.56038/oprd.v4i1.432

Keywords: Derin Öğrenme, Sınıflandırma, Risk Analizi, Anne Sağlığı, TabNet .

---

Abstract

During pregnancy, women are at high risk of complications. These risks often result in miscarriage and death. Women's health during and before pregnancy therefore plays an important role for both mother and child. Health monitoring of mother and baby, before and after birth, is important to minimize risks. In this context, deep learning-based models have been used for a wide range of medical tasks, such as facilitating the prediction of complications using images, health records and time data. In this study, the TabNet model was applied to the tabular dataset used in this study and maternal health risk analysis prediction was performed. The dataset used was provided by the Institute of Electrical and Electronics Engineers (IEEE) data port and this dataset contains 450 records and 130 attributes. In the study conducted with the MSF (Mother's Significant Feature) dataset, risk analysis is performed in 8 different categories. TabNet method, which gives better results in small and tabular datasets, was utilized. The aim of the study is to find higher accuracy rates than the predictions made by classical machine learning using the deep learning model TabNet model and thus to increase the risk prediction rates when performing maternal health risk analysis. As a result of the experiments, it was observed that the accuracy rates increased for the categories of Preterm (+2.2%), Jaundice (+0.55%), C-Section (+5.55%), Vaginal Delivery (+28.6%), while the accuracy rate for full-term birth remained constant. In line with these rates, deep learning will make it easier to accurately predict situations that may pose a risk to maternal and infant health during pregnancy and medically reduce the risk to maternal health.

---

References

M, Bogren. A, Denovan. F, Kent. M, Berg. ve K, Linden. “Impact of the Helping Mothers Survive Bleeding After Birth learning programme on care provider skills and maternal health outcomes in low-income countries- An integrative review”. Woman and Birth, 34(5), 425-434, 2021. DOI: https://doi.org/10.1016/j.wombi.2020.09.008

Y Mercan. ve K,T, Selçuk. “Association between postpartum depression level, social support level and breastfeeding attitude and breastfeeding self-efficacy in early postpartum women”. PloS ONE, 16(4), 2021. DOI: https://doi.org/10.1371/journal.pone.0249538

Our World in Data. “Maternal Mortality”. https://ourworldindata.org/maternal-mortality (20.12.2023).

S, Kaur. et al. "Medical Diagnostic Systems Using Artificial Intelligence (AI) Algorithms: Principles and Perspectives,". IEEE Access, 8, 228049-228069, 2020. DOI: https://doi.org/10.1109/ACCESS.2020.3042273

H, Naaz. ve M, Akram. “Maternal Health Complications During Pregnancy Period: A Sociological Study”. Public Health Research, 12(3), 61-68, 2022.

B, Narayan. ve C, Nelson. “Medical problems in pregnancy”. Clinical Medicine, 17(3), 251-257, 2017. DOI: https://doi.org/10.7861/clinmedicine.17-3-251

T,O, Togunwa. A,O, Babatunde. ve K,R, Abdullah. “Deep hybrid model for maternal health risk classification in pregnancy: synergy of ANN and random forest”. Sec. Medicine and Public Health, 6, 2023. DOI: https://doi.org/10.3389/frai.2023.1213436

Z, Hoodbhoy. M, Noman. A, Shafique. A, Nasim. D, Chowdhury. ve B, Hasan. “Use of machine learning algorithms for prediction of fetal risk using cardiotocographic data”. Int J App Basic Med Res, 9(4), 226-230, 2019. DOI: https://doi.org/10.4103/ijabmr.IJABMR_370_18

A, Raza. H,U,R, Siddiqui. K, Munir. M, Almutairi. F, Rustam. ve I, Ashraf. “Ensemble learning-based feature engineering to analyze maternal health during pregnancy and health risk prediction”. PLoS ONE, 17(11), 2022. DOI: https://doi.org/10.1371/journal.pone.0276525

M, Ahmed. ve M,A, Kashem. “IoT Based Risk Level Prediction Model For Maternal Health Care In The Context Of Bangladesh”. 2nd International Conference on Sustainable Technologies for Industry 4.0 (STI), Dhaka, Bangladesh, 2020. DOI: https://doi.org/10.1109/STI50764.2020.9350320

A, Mrzia. ve M,A, Kashem. IoT Based Risk Level Prediction Model For Maternal Health Care In The Context Of Bangladesh. 2nd International Conference on Sustainable Technologies for Industry 4.0 (STI). 2020

J,M, Bautista. Q,A,I, Quiwa. ve R,S,J, Reyes. Machine Learning Analysis for Remote Prenatal Care. IEEE Region 10 Conference. 2020 DOI: https://doi.org/10.1109/TENCON50793.2020.9293890

I,J, Umoren. F, Chigozirim. A, Silas. ve B, Ekong. Modeling and Prediction of Pregnancy Risk for Efficient Birth Outcomes Using Decision Tree Classification and Regression model.2022

C, Gao. S, Osmundson. D,R,V, Edwards. G,P, Jackson. B,A, Malin. ve Y, Chen. “Deep learning predicts extreme preterm birth from electronic health records”. Journal of Biomedical Informatics, 100, 2019. DOI: https://doi.org/10.1016/j.jbi.2019.103334

R, Bennett. Z,D, Mulla. P, Parikh. A, Hauspurg. ve T, Razzaghi. “An imbalance-aware deep neural network for early prediction of preeclampsia”. PLoS ONE, 17(4), 2022. DOI: https://doi.org/10.1371/journal.pone.0266042

S,D, Sharma. S, Sharma. R, Singh. A, Gehlot. N, Priyadarshi. ve B, Twala. “Stress Detection System for Working Pregnant Women Using an Improved Deep Recurrent Neural Network”. Electronics, 11(18), 2022. DOI: https://doi.org/10.3390/electronics11182862

A,L, Marques. et al., “IoT-Based Smart Health System for Ambulatory Maternal and Fetal Monitoring”. IEEE Internet of Things Journal, 8(23), 16814-16824, 2021. DOI: https://doi.org/10.1109/JIOT.2020.3037759

“Generative Adversarial Networks (GAN) Nedir?”. https://www.yapayzekatr.com/2023/11/03/generative-adversarial-networks-gan-nedir/ (20.12.2023).

S,O, Arık. ve T, Pfiste. “TabNet: Attentive Interpretable Tabular Learning”. The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), 6679-6687, 2021. DOI: https://doi.org/10.1609/aaai.v35i8.16826

A, Martins. ve R, Astudillo. “From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification”. Proceedings of The 33rd International Conference on Machine Learning, 1614-1623, 2016.

S,M,T, Zaman. R, Tasneem. ve T, Shakerin. Intelligent Assisted Living in Pregnancy, Yüksek Lisans Tezi, Brac Universitesi, Bangladesh, 2022.