概要
目的
建立一个预测妊娠期糖尿病新生儿出生体重的人工神经网络模型, 并评估其预测的准确性。
创新点
妊娠期糖尿病新生儿出生体重的预测十分重要, 但目前预测精度欠佳。本研究利用大样本量的临床数据, 突破传统统计学方法, 应用机器学习建立了一个基于人工神经网络的预测模型, 其预测精度较传统方法有明显提升。
方法
收集2462名妊娠期糖尿病孕妇的临床数据, 其中80%的数据用于构建一个前馈神经网络模型, 并用反向传播算法和10折交叉验证法训练和优化;剩余20%的数据用于验证最终模型的性能, 并将其与传统方法进行比较。
结论
本研究构建的人工神经网络模型对妊娠期糖尿病新生儿出生体重具有较高的预测精度, 其预测能力优于传统方法, 不足之处则在于其仍有可能会低估高出生体重。
References
Alsulyman OM, Ouzounian JG, Kjos SL, 1997. The accuracy of intrapartum ultrasonographic fetal weight estimation in diabetic pregnancies. Am J Obstet Gynecol, 177(3): 503–506. https://doi.org/10.1016/s0002-9378(97)70136-4
Benson CB, Doubilet PM, Saltzman DH, 1987. Sonographic determination of fetal weights in diabetic pregnancies. Am J Obstet Gynecol, 156(2):441–444. https://doi.org/10.1016/0002-9378(87)90303-6
Best G, Pressman EK, 2002. Ultrasonographic prediction of birth weight in diabetic pregnancies. Obstet Gynecol, 99(5): 740–744. https://doi.org/10.1016/s0029-7844(02)01662-9
Cesnaite G, Domza G, Ramasauskaite D, et al., 2020. The accuracy of 22 fetal weight estimation formulas in diabetic pregnancies. Fetal Diagn Ther, 47(1):54–59. https://doi.org/10.1159/000500452
Hadlock FP, Harrist RB, Sharman RS, et al., 1985. Estimation of fetal weight with the use of head, body, and femur measurements—a prospective study. Am J Obstet Gynecol, 151(3):333–337. https://doi.org/10.1016/0002-9378(85)90298-4
Hammami A, Mazer Zumaeta A, Syngelaki A, et al., 2018. Ultrasonographic estimation of fetal weight: development of new model and assessment of performance of previous models. Ultrasound Obstet Gynecol, 52(1):35–43. https://doi.org/10.1002/uog.19066
Husslein H, Worda C, Leipold H, et al., 2012. Accuracy of fetal weight estimation in women with diet controlled gestational diabetes. Geburtshilfe Frauenheilkd, 72(2):144–148. https://doi.org/10.1055/s-0031-1298278
Kriegeskorte N, Golan T, 2019. Neural network models and deep learning. Curr Biol, 29(7):R231–R236. https://doi.org/10.1016/j.cub.2019.02.034
Li CH, Peng Y, Zhang B, et al., 2019. Birth weight prediction models for the different gestational age stages in a Chinese population. Sci Rep, 9:10834. https://doi.org/10.1038/s41598-019-47056-0
McIntyre HD, Catalano P, Zhang CL, et al., 2019. Gestational diabetes mellitus. Nat Rev Dis Primers, 5:47. https://doi.org/10.1038/s41572-019-0098-8
Mitanchez D, Yzydorczyk C, Siddeek B, et al., 2015. The offspring of the diabetic mother—short- and long-term implications. Best Pract Res Clin Obstet Gynaecol, 29(2): 256–269. https://doi.org/10.1016/j.bpobgyn.2014.08.004
Pretscher J, Kehl S, Stumpfe FM, et al., 2020. Ultrasound fetal weight estimation in diabetic pregnancies. J Ultrasound Med, 39(2):341–350. https://doi.org/10.1002/jum.15112
Scioscia M, Vimercati A, Ceci O, et al., 2008. Estimation of birth weight by two-dimensional ultrasonography: a critical appraisal of its accuracy. Obstet Gynecol, 111(1): 57–65. https://doi.org/10.1097/01.AOG.0000296656.81143.e6
Valent AM, Newman T, Kritzer S, et al., 2017. Accuracy of sonographically estimated fetal weight near delivery in pregnancies complicated with diabetes mellitus. J Ultrasound Med, 36(3):593–599. https://doi.org/10.7863/ultra.15.12021
Wong SF, Chan FY, Cincotta RB, et al., 2001. Sonographic estimation of fetal weight in macrosomic fetuses: diabetic versus non-diabetic pregnancies. Aust N Z J Obstet Gynaecol, 41(4):429–432. https://doi.org/10.1111/j.1479-828x.2001.tb01323.x
Acknowledgments
This work was supported by the Key Research and Development Project of Zhejiang Province (No. 2018C03010) and the Natural Science Foundation of Zhejiang Province (No. LQ20H040005), China.
Author information
Authors and Affiliations
Corresponding author
Additional information
Materials and methods
Detailed methods are provided in the electronic supplementary materials of this paper.
Supplementary information
Materials and methods; Table S1
Author contributions
Menglin ZHOU performed the data analysis, wrote and edited the manuscript. Jiansheng JI and Nie XIE performed the data collection. Danqing CHEN performed the study design, funding support, and process supervision. All authors have read and approved the final manuscript, and therefore, have full access to all the data in the study and take responsibility for the integrity and security of the data.
Compliance with ethics guidelines
Menglin ZHOU, Jiansheng JI, Nie XIE, and Danqing CHEN declare that they have no conflict of interest.
All procedures followed were in accordance with the ethical standards of the responsible committee on human experimentation (institutional and national) and with the Helsinki Declaration of 1975, as revised in 2008 (5). Informed consent was not obtained since de-identified retrospective data were collected and it was approved by the Institutional Ethics Committee of Women’s Hospital, Zhejiang University School of Medicine, Hangzhou, China (No. IRB-20210136-R).
Rights and permissions
About this article
Cite this article
Zhou, M., Ji, J., Xie, N. et al. Prediction of birth weight in pregnancy with gestational diabetes mellitus using an artificial neural network. J. Zhejiang Univ. Sci. B 23, 432–436 (2022). https://doi.org/10.1631/jzus.B2100753
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1631/jzus.B2100753