Fetal growth restriction (FGR) affects 5-10% of pregnancies, is the largest contributor to fetal death, and can have long-term consequences for the child. Implementation of a standard clinical classification system is hampered by the multiphenotypic spectrum of small fetuses with substantial differences in perinatal risks. Machine learning and multiomics data can potentially revolutionize clinical decision-making in FGR by identifying new phenotypes. Herein, we describe a cluster analysis of FGR based on an unbiased machine-learning method. Our results confirm the existence of two subtypes of human FGR with distinct molecular and clinical features based on multi-omic analysis. In addition, we demonstrated that clusters generated by machine learning significantly outperform single data subtype analysis and biologically support the current clinical classification in predicting adverse maternal and neonatal outcomes. Our approach can aid in the refinement of clinical classification systems for FGR supported by molecular and clinical signatures.
Miranda, J., Simões, R. V., Paules, C., Cañueto, D., Pardo-Cea, M. A., García-Martín, M. L., Crovetto, F., Fuertes-Martin, R., Domenech, M., Gómez-Roig, M. D., Eixarch, E., Estruch, R., Hansson, S. R., Amigó, N., Cañellas, N., Crispi, F., & Gratacós, E. (2018). Metabolic profiling and targeted lipidomics reveals a disturbed lipid profile in mothers and fetuses with intrauterine growth restriction. Scientific Reports, 8(1), 13614. https://doi.org/10.1038/s41598-018-31832-5
Keywords:
Fetal Growth Restriction, Disturbed Lipid Profile, Very Low Density Lipoproteins (VLDL), Cord Blood Plasma, Small Fetuses
Departament:
Enginyeria Electrònica, Elèctrica i Automàtica
Related publication's DOI:
Similarity network fusion to identify phenotypes of small for gestational age fetuses
Subject matter:
Medicina
Access rights:
info:eu-repo/semantics/openAccess
DOI:
10.5281/zenodo.8176373
Dataset title:
Similarity network fusion to identify phenotypes of small for gestational age fetuses
Description:
Fetal growth restriction (FGR) affects 5-10% of pregnancies, is the largest contributor to fetal death, and can have long-term consequences for the child. Implementation of a standard clinical classification system is hampered by the multiphenotypic spectrum of small fetuses with substantial differences in perinatal risks. Machine learning and multiomics data can potentially revolutionize clinical decision-making in FGR by identifying new phenotypes. Herein, we describe a cluster analysis of FGR based on an unbiased machine-learning method. Our results confirm the existence of two subtypes of human FGR with distinct molecular and clinical features based on multi-omic analysis. In addition, we demonstrated that clusters generated by machine learning significantly outperform single data subtype analysis and biologically support the current clinical classification in predicting adverse maternal and neonatal outcomes. Our approach can aid in the refinement of clinical classification systems for FGR supported by molecular and clinical signatures.