Similarity network fusion to identify phenotypes of small for gestational age fetuses
- 1. BCNatal – Barcelona Center for Maternal-Fetal and Neonatal Medicine (Hospital Clínic and Hospital Sant Joan de Deu), IDIBAPS, University of Barcelona, and Centre for Biomedical Research on Rare Diseases (CIBER-ER), Barcelona, Spain.
- 2. University of Barcelona, Biomedicine department, IDIBAPS, Centre for Biomedical Research on Respiratory Diseases (CIBERES), Barcelona, Spain.
- 3. Department of Epidemiology, School of Public Health and Tropical Medicine, Tulane University, New Orleans, Louisiana, United States.
- 4. BCNatal – Barcelona Center for Maternal-Fetal and Neonatal Medicine (Hospital Clínic and Hospital Sant Joan de Deu), IDIBAPS, University of Barcelona, and Centre for Biomedical Research on Rare Diseases (CIBER-ER), Barcelona, Spain
- 5. Metabolomics Platform, IISPV, DEEiA, Universidad Rovira i Virgili, Biomedical Research Centre in Diabetes and Associated Metabolic Disorders (CIBERDEM), Tarragona, Spain.
- 6. BIONAND, Andalusian Centre for Nanomedicine and Biotechnology, Junta de Andalucía, Universidad de Málaga, Málaga, Spain.
- 7. Biosfer Teslab, Reus, Spain.
- 8. Institute for Research & Innovation in Health (i3S), University of Porto, Porto, Portugal.
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.
Files
Files
(862.7 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:b5e983c026da566a6a29dbf3b03faf2e
|
862.7 kB | Download |
Additional details
Related works
- Is part of
- Journal article: 10.1038/s41598-018-31832-5 (DOI)