Early prediction and longitudinal modeling of preeclampsia from multiomics

Authors

• Ivana Marić, Stanford University School of Medicine
• Kévin Contrepois, Stanford University School of Medicine
• Mira N. Moufarrej, Stanford University
• Ina A. Stelzer, Stanford University School of Medicine
• Dorien Feyaerts, Stanford University School of Medicine
• Xiaoyuan Han, University of the PacificFollow
• Andy Tang, Stanford University School of Medicine
• Natalie Stanley, Stanford University School of Medicine
• Ronald J. Wong, Stanford University School of Medicine
• Gavin M. Traber, Stanford University School of Medicine
• Mathew Ellenberger, Stanford University School of Medicine
• Alan L. Chang, Stanford University School of Medicine
• Ramin Fallahzadeh, Stanford University School of Medicine
• Huda Nassar, Stanford University School of Medicine
• Martin Becker, Stanford University School of Medicine
• Maria Xenochristou, Stanford University School of Medicine
• Camilo Espinosa, Stanford University School of Medicine
• Davide De Francesco, Stanford University School of Medicine
• Mohammad S. Ghaemi, Stanford University School of Medicine
• Elizabeth K. Costello, Stanford University School of Medicine
• Anthony Culos, Stanford University School of Medicine
• Xuefeng B. Ling, Stanford University School of Medicine

Document Type

Article

Publication Title

Patterns

Department

Biomedical Sciences

ISSN

26663899

Volume

3

Issue

12

DOI

10.1016/j.patter.2022.100655

First Page

1

Last Page

16

Publication Date

12-9-2022

Abstract

Preeclampsia is a complex disease of pregnancy whose physiopathology remains unclear. We developed machine-learning models for early prediction of preeclampsia (first 16 weeks of pregnancy) and over gestation by analyzing six omics datasets from a longitudinal cohort of pregnant women. For early pregnancy, a prediction model using nine urine metabolites had the highest accuracy and was validated on an independent cohort (area under the receiver-operating characteristic curve [AUC] = 0.88, 95% confidence interval [CI] [0.76, 0.99] cross-validated; AUC = 0.83, 95% CI [0.62,1] validated). Univariate analysis demonstrated statistical significance of identified metabolites. An integrated multiomics model further improved accuracy (AUC = 0.94). Several biological pathways were identified including tryptophan, caffeine, and arachidonic acid metabolisms. Integration with immune cytometry data suggested novel associations between immune and proteomic dynamics. While further validation in a larger population is necessary, these encouraging results can serve as a basis for a simple, early diagnostic test for preeclampsia.

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Recommended Citation

Marić, Ivana; Contrepois, Kévin; Moufarrej, Mira N.; Stelzer, Ina A.; Feyaerts, Dorien; Han, Xiaoyuan; Tang, Andy; Stanley, Natalie; Wong, Ronald J.; Traber, Gavin M.; Ellenberger, Mathew; Chang, Alan L.; Fallahzadeh, Ramin; Nassar, Huda; Becker, Martin; Xenochristou, Maria; Espinosa, Camilo; De Francesco, Davide; Ghaemi, Mohammad S.; Costello, Elizabeth K.; Culos, Anthony; and Ling, Xuefeng B., "Early prediction and longitudinal modeling of preeclampsia from multiomics" (2022). Pacific Faculty Work. 221.
https://scholarlycommons.pacific.edu/all-faculty/221