Abstract
This work presents an application of machine learning methods in the area of environmental epidemiology. We have used lifestyle and exposure data from 769 mother-child pairs from Slovenia and Croatia to predict the neurodevelopment of the children, expressed through five Bayley-III test scores. We have applied single- and multi-target (semi-)supervised predictive methods to build models capable of predicting the Bayley-III scores. Additionally, we have used feature ranking methods to estimate the importance of individual lifestyle and mercury exposure attributes on the Bayley-III test scores. The learned models offer useful insights into the effect of prenatal mercury exposure on the neural development of children.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
CLUS software is available for download at http://source.ijs.si/ktclus/clus-public.
References
Barbone, F., et al.: Prenatal mercury exposure and child neurodevelopment outcomes at 18 months: results from the Mediterranean Phime cohort. Int. J. Hyg. Environ. Health 222(1), 9–21 (2019). https://doi.org/10.1016/j.ijheh.2018.07.011
Logsdon, A.: Bayley Scales of Infant and Toddler Development. 3rd edn (2008). http://images.pearsonclinical.com/images/pdf/bayley-iii_webinar.pdf, last accessed 07.09.2020
Blockeel, H., De Raedt, L., Ramon, J.: Top-down induction of clustering trees. In: Proceedings of the Fifteenth International Conference on Machine Learning, pp. 55–63 (1998)
Breskvar, M., Zenko, B., Džeroski, S.: Relating biological and clinical features of Alzheimer’s patients with predictive clustering trees. In: International Multi-Conference Information Society (2015)
Kim, K.H., Kabir, E., Jahan, S.A.: A review on the distribution of hg in the environment and its human health impacts. J. Hazard. Mater. 306, 376–385 (2016). https://doi.org/10.1016/j.jhazmat.2015.11.031
Kocev, D., Vens, C., Struyf, J., Džeroski, S.: Tree ensembles for predicting structured outputs. Pattern Recogn. 46(3), 817–833 (2013)
Levatić, J., Kocev, D., Ceci, M., Džeroski, S.: Semi-supervised trees for multi-target regression. Inf. Sci. 450, 109–127 (2018). https://doi.org/10.1016/j.ins.2018.03.033
Petković, M., Kocev, D., Džeroski, S.: Feature ranking for multi-target regression. Mach. Learn. 109(6), 1179–1204 (2019). https://doi.org/10.1007/s10994-019-05829-8
Prpic, I., et al.: Prenatal exposure to low-level methyl mercury alters the child’s fine motor skills at the age of 18 months. Environ. Res. 152 (2016). https://doi.org/10.1016/j.envres.2016.10.011
Quinlan, J.R.: Learning with continuous classes. In: 5th Australian Joint Conference on Artificial Intelligence, pp. 343–348. World Scientific (1992)
Snoj Tratnik, J., et al.: Prenatal mercury exposure, neurodevelopment and apolipoprotein e genetic polymorphism. Environ. Res. 152, 375–385 (2017). https://doi.org/10.1016/j.envres.2016.08.035
Struyf, J., Džeroski, S.: Constraint based induction of multi-objective regression trees. In: International Workshop on Knowledge Discovery in Inductive Databases, pp. 222–233. Springer, Berlin (2005). https://doi.org/10.1007/978-3-540-75549-4
Trdin, A., et al.: Mercury speciation in prenatal exposure in Slovenian and Croatian population - Phime study. Environ. Res. 177, 108627 (2019). https://doi.org/10.1016/j.envres.2019.108627, https://www.sciencedirect.com/science/article/pii/S0013935119304244
Valmarska, A., Miljkovic, D., Konitsiotis, S., Gatsios, D., Lavrac, N., Robnik-Sikonja, M.: Combining multitask learning and short time series analysis in Parkinson’s disease patients stratification. In: Conference on Artificial Medicine in Europe, pp. 116–125, May 2017. https://doi.org/10.1007/978-3-319-59758-4_13
Zajc, J., et al.: Chaophilic or chaotolerant fungi: a new category of extremophiles? Front. Microbiol. 5 (2014)
Ženko, B.: Learning predictive clustering rules. Ph.D. thesis, University of Ljubljana (2007), http://eprints.fri.uni-lj.si/709/1/zenko%2Dphd%2Dthesis.pdf
Acknowledgements
SP would like to acknowledge the financial support in the form of a scholarship of the Public Scholarship, Development, Disability and Maintenance Fund of the Republic of Slovenia. SD, MB and SP would like to acknowledge the grant number P2-0103 (the research programme Knowledge Technologies). All authors acknowledge the NEURODYS project (J7-9400, Neuropsychological dysfunctions caused by low level exposure to selected environmental pollutants in susceptible population) for financial support of the overall work. JST, DM and MH also acknowledge the EU funded 6th FP project PHIME for providing the data used in this work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Popov, S., Tratnik, J.S., Breskvar, M., Mazej, D., Horvat, M., Džeroski, S. (2022). Modeling the Association Between Prenatal Exposure to Mercury and Neurodevelopment of Children. In: Antovski, L., Armenski, G. (eds) ICT Innovations 2021. Digital Transformation. ICT Innovations 2021. Communications in Computer and Information Science, vol 1521. Springer, Cham. https://doi.org/10.1007/978-3-031-04206-5_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-04206-5_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-04205-8
Online ISBN: 978-3-031-04206-5
eBook Packages: Computer ScienceComputer Science (R0)