Early prediction and longitudinal modeling of preeclampsia from multiomics

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; Nima Aghaeepour

doi:10.1016/j.patter.2022.100655

Early prediction and longitudinal modeling of preeclampsia from multiomics

Patterns (N Y). 2022 Dec 9;3(12):100655. doi: 10.1016/j.patter.2022.100655.

Authors

Ivana Marić¹, Kévin Contrepois², Mira N Moufarrej³, Ina A Stelzer⁴, Dorien Feyaerts⁴, Xiaoyuan Han⁵, Andy Tang⁴, Natalie Stanley⁴, Ronald J Wong¹, Gavin M Traber², Mathew Ellenberger², Alan L Chang⁴, Ramin Fallahzadeh⁴, Huda Nassar⁴, Martin Becker⁴, Maria Xenochristou⁴, Camilo Espinosa⁴, Davide De Francesco⁴, Mohammad S Ghaemi^{4

6}, Elizabeth K Costello⁷, Anthony Culos⁴, Xuefeng B Ling⁸, Karl G Sylvester⁸, Gary L Darmstadt¹, Virginia D Winn⁹, Gary M Shaw¹, David A Relman^{7

10}, Stephen R Quake³, Martin S Angst⁴, Michael P Snyder², David K Stevenson¹, Brice Gaudilliere^{1

4}, Nima Aghaeepour^{1

4

11}

Affiliations

¹ Department of Pediatrics, Division of Neonatal and Developmental Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA.
² Department of Genetics, Stanford University School of Medicine, Stanford, CA 94305, USA.
³ Departments of Bioengineering and Applied Physics, Stanford University and Chan Zuckerberg Biohub, Stanford, CA 94305, USA.
⁴ Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA.
⁵ University of the Pacific, Arthur A. Dugoni School of Dentistry, San Francisco, CA 94103, USA.
⁶ Digital Technologies Research Centre, National Research Council Canada, Toronto, Canada.
⁷ Departments of Medicine, and of Microbiology & Immunology, Stanford University School of Medicine, Stanford, CA 94305, USA.
⁸ Department of Surgery, Stanford University School of Medicine, Stanford, CA 94305, USA.
⁹ Department of Obstetrics and Gynecology, Stanford University School of Medicine, Stanford, CA 94305, USA.
¹⁰ Infectious Diseases Section, Veterans Affairs Palo Alto Health Care System, Palo Alto, CA 94304, USA.
¹¹ Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, USA.

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.

Keywords: biomarkers; machine learning; multiomics; predictive modeling; preeclampsia.

Grants and funding

R35 GM138353/GM/NIGMS NIH HHS/United States