Article Sidebar

PDF
Date Published: 29/04/2025
Abstract Views: 234
Views PDF: 52
DOI: https://doi.org/10.51298/vmj.v550i1.13889
Issue
Vol. 550 No. 1 (2025): Vietnam Medical Journal
Section
Các bài báo
How to Cite
Ba Nha, P. ., Phuong Tu, N. ., Le Duc Anh, T. ., Ba Quang Huy, D. ., Hai Phuong, N. ., Anh Thu, N. ., Phuong Hong Minh, N. ., Thien Thai, L. ., Thi Huong Linh, N. ., & Tien Hoang, N. . (2025). PRELIMINARY RESULTS OF AI APPLICATION IN PREDICTING PRENATAL WEIGHT IN VIET NAM. Vietnam Medical Journal, 550(1). https://doi.org/10.51298/vmj.v550i1.13889

PRELIMINARY RESULTS OF AI APPLICATION IN PREDICTING PRENATAL WEIGHT IN VIET NAM

Pham Ba Nha1, Nguyen Phuong Tu2,3, Tran Le Duc Anh4, Do Ba Quang Huy5, Nguyen Hai Phuong6, Nguyen Anh Thu7, Nguyen Phuong Hong Minh7, Le Thien Thai1, Nguyen Thi Huong Linh1, Nguyen Tien Hoang1,
1 Women’s Health Center, Vinmec Times City Hospital
2 Ha Noi Medical University
3 Bach Mai Hospital
4 School of Electrical and Electronic Engineering, Hanoi University of Science and Technology
5 FPT automative, FPT Software
6 National hospital of obstetrics and gynecology
7 College of Health Sciences, Vin University

Main Article Content

Abstract

Objective: Our research aims to propose the application of AI in improving the accuracy for estimating fetal weight.


Method: This is a cross-sectional analytical study combining the development and comparison of predictive models supported by AI that include 1162 pregnancy women that came for scheduled visit and give birth at Obstetric Department at Vinmec Times City International Hospital. The pregnancy women were chosen based on: age (18 to 35 years old), live singleton pregnancy, Vietnamese, height > 153 cm, and gestational age ≥ 36 weeks. Maternal and fetal parameters are then collected and divided into data and test set. Symbolic regression learning method is applied to our ensemble model which include Operon, XGBoost, LightGBM, FEAT, Hadlock, GP-GOMEA, DSR, and SBP-GP. The performance of each algorithms are then evaluated using test data set and compared the results to the traditional method.


Results: 1162 pregnancy women were selected, and each were collected 9 maternal and fetal variables. MAE, MSE, RMSE, and R2 value of each model were calculated from their performance. Operon model’s MAE was 158.542 grams, RMSE was 205.485 and R2 of 0.538, while Hadlock model’s MAE was 186.98 grams, RMSE was 331.373 and R2 of -0.19.


Conclusion: AI-driven methods, particularly symbolic regression, demonstrates greater accuracy and efficacy compared to the traditional method, hence suggests a promising potential in prenatal weight estimation.

Article Details

Keywords

symbolic regression, fetal weight estimation, ensemble learning, machine learning

References

1. Hadlock FP, Harrist RB, Sharman RS, Deter RL, Park SK. Estimation of fetal weight with the use of head, body, and femur measurements—A prospective study. Am J Obstet Gynecol. 1985 Feb 1;151(3):333–7.
2. Nguyen XC, Doan QH, Bui TT, Le NQH, Nguyen QM, Dam LC, et al. Khảo sát giá trị các phương pháp ước lượng cân nặng thai nhi đủ tháng | Tạp chí Phụ sản. 2023 Sep 23 [cited 2024 Dec 7];21(3). Available from: https://vjog.vn/journal/article/view/1615
3. Kumari A, Goswami S, Mukherjee P. Comparative Study of Various Methods of Fetal Weight Estimation in Term Pregnancy. J South Asian Fed Obstet Gynaecol. 2013 Apr;5(1):22–5.
4. Marien M, Perron S, Bergeron AM, Singbo N, Demers S. Comparison of the Accuracy of INTERGROWTH-21 and Hadlock Ultrasound Formulae for Fetal Weight Prediction. J Obstet Gynaecol Can JOGC J Obstet Gynecol Can JOGC. 2021 Nov;43(11):1254–9.
5. Ma J, Cheng D, Zhang Z, Cai B, Xu X. Evaluating the accuracy of sonographic fetal weight estimations using the Hadlock IV formula in a Chinese population. Quant Imaging Med Surg. 2023 Jun 1;13(6):3726–34.
6. Saw SN, Lim MC, Liew CN, Ahmad Kamar A, Sulaiman S, Saaid R, et al. The accuracy of international and national fetal growth charts in detecting small-for-gestational-age infants using the Lambda-Mu-Sigma method. Front Surg [Internet]. 2023 Apr 11 [cited 2024 Nov 26];10. Available from: https://www.frontiersin.org/journals/surgery/articles/10.3389/fsurg.2023.1123948/full
7. Schmidt M, Lipson H. Distilling Free-Form Natural Laws from Experimental Data. Science. 2009 Apr 3;324(5923):81–5.
8. Lu Y, Fu X, Chen F, Wong KKL. Prediction of fetal weight at varying gestational age in the absence of ultrasound examination using ensemble learning. Artif Intell Med. 2020 Jan 1;102:101748.