Abstract
Large-for-gestational-age (LGA), defined as foetal weight above the 90th percentile, is an adverse pregnancy outcome associated with increased delivery complications such as shoulder dystocia and caesarean deliveries. Standard prediction methods have been reported to be generally poor predictors of LGA. This study uses ethnically diverse data from the Born In Bradford dataset to predict LGA using machine learning algorithms. Data from 13,194 pregnant women with singleton infants was used, 43% of which were South Asian women and 35% White women. Within this dataset, 5% of the infants born to South Asian women were LGA compared to 11% of infants born to White women. Models built with resampled White and South Asian data had improved sensitivity (19–92%), and low precision (7–28%). Therefore, additional class balancing techniques are required to achieve more precise prediction models.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Júnior, E.A., et al.: Macrosomia. Best Pract. Res. Clin. Obstet. Gynaecol. 38, 83–96 (2017). https://doi.org/10.1016/j.bpobgyn.2016.08.003
Aye, S.S., Miller, V., Saxena, S, Farhan, D.M.: Review management of large-for-gestational-age pregnancy in non-diabetic women key content: learning objectives: ethical issues. Obstet. Gynaecol. 12, 250–256 (2010). https://doi.org/10.1576/toag.12.4.250.27617
Boulet, S.L., et al.: Macrosomic births in the United States: determinants, outcomes, and proposed grades of risk. Am. J. Obstet. Gynecol. 188(5), 1372–1378 (2003). https://doi.org/10.1067/mob.2003.302
Asplund, C.A., et al.: Percentage change in antenatal body mass index as a predictor of neonatal macrosomia. Ann. Family Med. 6(6), 550–554 (2008). https://doi.org/10.1370/afm.903
Boulvain, M., et al.: Induction of labour versus expectant management for large-for-date fetuses: a randomised controlled trial. Lancet 385(9987), 2600–2605 (2015). https://doi.org/10.1016/S0140-6736(14)61904-8
Coomarasamy, A., et al.: Accuracy of ultrasound biometry in the prediction of macrosomia: a systematic quantitative review. BJOG Int. J. Obstet. Gynaecol. 112(11), 1461–1466 (2005). https://doi.org/10.1111/j.1471-0528.2005.00702.x
Hanif, W., Susarla, R.: Diabetes and cardiovascular risk in UK South Asians - an overview. Br. J. Cardiol. (2018). https://doi.org/10.5837/bjc.2018.s08
West, J., et al.: UK-born Pakistani-origin infants are relatively more adipose than white British infants: Findings from 8704 mother-offspring pairs in the Born-In-Bradford prospective birth cohort. J. Epidemiol. Community Health 67(7), 544–551 (2013). https://doi.org/10.1136/jech-2012-201891
Kuhle, S., et al.: Comparison of logistic regression with machine learning methods for the prediction of fetal growth abnormalities: a retrospective cohort study. BMC Pregnancy Childbirth 18(1), 1–9 (2018). https://doi.org/10.1186/s12884-018-1971-2
Shigemi, D., et al.: Predictive model for macrosomia using maternal parameters without sonography information. J. Maternal-Fetal Neonatal Med. 32(22) 3859–3863. Taylor & Francis (2019). https://doi.org/10.1080/14767058.2018.1484090
Ye, S., et al.: Ensemble learning to improve the prediction of fetal macrosomia and large-for-gestational age. J. Clin. Med. 9(2), 380 (2020). https://doi.org/10.3390/jcm9020380
Akhtar, F., Li, J., Pei, Y., et al.: Diagnosis and prediction of large-for-gestational-age fetus using the stacked generalization method. Appl. Sci. (Switz.) 9(20), 1–18 (2019). https://doi.org/10.3390/app9204317
Akhtar, F., Li, J., Guan, Y., et al.: Monitoring bio-chemical indicators using machine learning techniques for an effective large for gestational age prediction model with reduced computational overhead. In: Hung, J., Yen, N., Hui, L. (eds.) Frontier Computing. FC 2018. Lecture Notes in Electrical Engineering, vol. 542. Springer, Singapore (2019). https://doi.org/10.1007/978-981-13-3648-5_15
Akhtar, F., et al.: Effective large for gestational age prediction using machine learning techniques with monitoring biochemical indicators. J. Supercomput. 76(8), 6219–6237 (2019). https://doi.org/10.1007/s11227-018-02738-w
Wright, J., et al.: Cohort profile: the Born In Bradford multi-ethnic family cohort study. Int. J. Epidemiol. 42(4), 978–991 (2013). https://doi.org/10.1093/ije/dys112
Raynor, P., et al.: Born In Bradford, a cohort study of babies Born In Bradford, and their parents: protocol for the recruitment phase. BMC Public Health 8, 1–13 (2008). https://doi.org/10.1186/1471-2458-8-327
Beretta, L., Santaniello, A.: Nearest neighbor imputation algorithms: a critical evaluation. BMC Med. Inform. Decis. Mak. 16(Suppl 3) (2016). https://doi.org/10.1186/s12911-016-0318-z
Nnamoko, N., Korkontzelos, I.: Efficient treatment of outliers and class imbalance for diabetes prediction. Artif. Intell. Med. 104(February), 101815 (2020). https://doi.org/10.1016/j.artmed.2020.101815
Blagus, R., Lusa, L.: Joint use of over-and under-sampling techniques and cross-validation for the development and assessment of prediction models. BMC Bioinform. 16(1), 1–10(2015). https://doi.org/10.1186/s12859-015-0784-9
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sabouni, S., Qahwaji, R., Poterlowicz, K., Graham, A.M. (2022). Developing Prediction Models for Large for Gestational Age Infants Using Ethnically Diverse Data. In: Jansen, T., Jensen, R., Mac Parthaláin, N., Lin, CM. (eds) Advances in Computational Intelligence Systems. UKCI 2021. Advances in Intelligent Systems and Computing, vol 1409. Springer, Cham. https://doi.org/10.1007/978-3-030-87094-2_39
Download citation
DOI: https://doi.org/10.1007/978-3-030-87094-2_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87093-5
Online ISBN: 978-3-030-87094-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)