1. Early prediction and longitudinal modeling of preeclampsia from multiomics
- Author
-
Ivana Marić, Kévin Contrepois, Mira N. Moufarrej, Ina A. Stelzer, Dorien Feyaerts, Xiaoyuan Han, Andy Tang, Natalie Stanley, Ronald J. Wong, Gavin M. Traber, Mathew Ellenberger, Alan L. Chang, Ramin Fallahzadeh, Huda Nassar, Martin Becker, Maria Xenochristou, Camilo Espinosa, Davide De Francesco, Mohammad S. Ghaemi, Elizabeth K. Costello, Anthony Culos, Xuefeng B. Ling, Karl G. Sylvester, Gary L. Darmstadt, Virginia D. Winn, Gary M. Shaw, David A. Relman, Stephen R. Quake, Martin S. Angst, Michael P. Snyder, David K. Stevenson, Brice Gaudilliere, and Nima Aghaeepour
- Subjects
preeclampsia ,History ,machine learning ,Polymers and Plastics ,biomarkers ,General Decision Sciences ,Business and International Management ,predictive modeling ,multiomics ,Industrial and Manufacturing Engineering - 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.
- Published
- 2022
- Full Text
- View/download PDF