MATERNOCARE PREDICTION FOR MATERNAL AND CHILD WELL-BEING USING SURVEY DATA AND MACHINE LEARNING APPROACHES

Paper ID: EIJTEM_2024_11_4_170-180

Author's Name: Fatema Tuz Zohora, Pratyay Paul

Volume: 11

Issue: 4

Year: 2024

Page No: 170-180

Abstract:

The fact that high-risk pregnancies provide serious obstacles to maternal and newborn outcomes, mother and child health is a crucial area of attention in healthcare. This study uses survey data from pregnant women to estimate the chances of perilous pregnancies using machine learning techniques. Maternal age, height, weight, obstetric history, anemia status, blood pressure, fetal movement, fetal heart rate and the outcomes of diagnostic tests are among the many characteristics included in the dataset. Predictive models were constructed using three machine learning algorithms, AdaBoost Classifier, Random Forest Classifier and Gradient Boosting Classifier. The Gradient Boosting Classifier outperformed Random Forest (0.95) and AdaBoost (0.93) exhibiting the greatest accuracy (0.97) among them. These findings demonstrate how well machine learning works to accurately detect high-risk pregnancies. The study emphasizes how incorporating these prediction models into maternal health initiatives may help with early identification, setting priorities for medical resources and creating focused treatments.

Keywords: MaternoCare, high-risk, pregnancies, AdaBoost Classifier, Random Forest Classifier, Gradient Boosting Classifier

References:

1. E. A. Turjo and Md. H. Rahman, “Using machine learning approaches to forecasting malnutrition assessing risk factors for malnutrition among women in Bangladesh,” BMC Nutrition, vol. 10, no. 1, Feb. 2024, doi: 10.1186/s40795-023-00808-8.
2. M. A. Sayeed, A. Rahman, A. Rahman, and R. Rois, “Predicting infant mortality in Bangladesh on the interpretability of the using SVM model” JHPN, vol. 43, no. 1, Oct. 2024, doi: 10.1186/s41043-024-00646-9.
3. N. S. Borson, R. M. Rahman and Md. R. Kabir, Z. Zamal “Predict low birth weight and prediction modeling using correlations analysis and machine learning techniques,” (WorldS4), pp. 169–173, Jul. 2020, doi: 10.1109/worlds450073.2020.9210338.
4. T. B. Reza and N. Salma, “Using machine learning algorithms for of low-birth-weight prediction and feature selection,” JHPN, vol. 43, no. 1, Oct. 2024, doi: 10.1186/s41043-024-00647-8.
5. S. Akber et al., “Impact of a mobile health intervention on feeding for young child and infants under 24 months in rural Islamabad,” F1000Research, vol. 8, p. 551, Apr. 2019, doi: 10.12688/f1000research.17037.1.
6. R. A. Putranto, S. Suryono, and J. E. Suseno, “Utilizing cloud computing for baby nutrition status record and anthropometry index,” (ICICoS), vol. 2, pp. 1–6, Oct. 2018, doi: 10.1109/icicos.2018.8621640.
7. G. Saranya, G. Geetha, and M. Safa, using supervised machine learning for E-Antenatal assistance care based on cluster analytics.2017, pp. 1–3. doi: 10.1109/iciota.2017.8073617.
8. R. K. Megalingam, K. Boopathi, S. Sreedevi, K. S. Sarathkumar and G. B. Vishnu, implement mobile ultrasound scan system for rural pregnant women’s health care (using ASTM E1384–07 standard). 2013, pp. 164–169. doi: 10.1109/ghtc-sas.2013.6629909.
9. L. I. Octovia et al, A proposed and review design for Indonesia focus mother and child health nutrition. 2017, pp. 287–290. doi: 10.1109/icici-bme.2017.8537775.
10. T. Rahman, A. Anjum, R. Rahman, and R. R. Khan, an integrated system for support process in developing countries digitizing the Maternal Health and Children. 2019, pp. 1–4. doi: 10.1109/wiecon-ece48653.2019.9019929.
11. L. Swastina, B. Rahmatullah, A. Saad, and H. Khan, “A review on prediction status of children nutrition” IAES, vol. 13, no. 2, p. 1868, Apr. 2024, doi: 10.11591/ijai.v13.i2.pp1868-1877.
12. A. M. Oprescu, G. Miro-Amarante, L. M. Beltran, V. E. Rey, L. Garcia-Diaz and Mc. Romero-Ternero, “A review of AI application in pregnancy” IEEE Access, vol. 8, pp. 181450–181484, Jan. 2020, doi: 10.1109/access.2020.3028333.
13. M. N. Islam, S. N. Mustafina, T. Mahmud, A. K. M. N. Islam and N. I. Khan, “To Predict key features for childbirth modes to using machine learning approches,” IEEE Access, vol. 9, pp. 1680–1692, Dec. 2020, doi: 10.1109/access.2020.3045469.
14. S. N. Tumpa, A. B. Islam and Md. T. M. Ankon, A approaches of an intelligent smart care system and assistant for pregnant mothers. 2017, pp. 754–759. doi: 10.1109/icaee.2017.8255455.
15. T. M. Kadarina and R. Priambodo,A study of supporting mother and child health program. Using preliminary design of IoT. 2017, pp. 1–6. doi: 10.1109/bcwsp.2017.8272576.

View PDF