Citation: Zhang, Y.; Sylvester, K.G.;
Jin, B.; Wong, R.J.; Schilling, J.; Chou,
C.J.; Han, Z.; Luo, R.Y.; Tian, L.;
Ladella, S.; et al. Development of a
Urine Metabolomics
Biomarker-Based Prediction Model
for Preeclampsia during Early
Pregnancy. Metabolites 2023, 13, 715.
https://doi.org/10.3390/
metabo13060715
Academic Editors: Susanne Aufreiter
and Bo Li
Received: 21 April 2023
Revised: 21 May 2023
Accepted: 25 May 2023
Published: 31 May 2023
Copyright: © 2023 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
metabolites
H
OH
OH
Article
Development of a Urine Metabolomics Biomarker-Based
Prediction Model for Preeclampsia during Early Pregnancy
Yaqi Zhang
1,2
, Karl G. Sylvester
2
, Bo Jin
3
, Ronald J. Wong
4
, James Schilling
3
, C. James Chou
2
, Zhi Han
2
,
Ruben Y. Luo
5
, Lu Tian
6
, Subhashini Ladella
7
, Lihong Mo
8
, Ivana Mari´ c
4
, Yair J. Blumenfeld
9
,
Gary L. Darmstadt
4
, Gary M. Shaw
4
, David K. Stevenson
4
, John C. Whitin
4
, Harvey J. Cohen
4
,
Doff B. McElhinney
10
and Xuefeng B. Ling
2,
*
1
College of Automation, Guangdong Polytechnic Normal University, Guangzhou 510665, China;
yaqizhang@gpnu.edu.cn
2
Department of Surgery, Stanford University School of Medicine, Stanford, CA 94305, USA;
karls@stanford.edu (K.G.S.); cjchou@stanford.edu (C.J.C.); zhihan01@stanford.edu (Z.H.)
3
mProbe Inc., Palo Alto, CA 94303, USA; bo.jin@mprobe.com (B.J.); james.s@mprobe.com (J.S.)
4
Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USA;
rjwong@stanford.edu (R.J.W.); ivanam@stanford.edu (I.M.); gdarmsta@stanford.edu (G.L.D.);
gmshaw@stanford.edu (G.M.S.); dks750@stanford.edu (D.K.S.); cuke@stanford.edu (J.C.W.);
punko@stanford.edu (H.J.C.)
5
Department of Pathology, Stanford University School of Medicine, Stanford, CA 94305, USA;
rubenluo@stanford.edu
6
Department of Biomedical Data Science, Stanford University School of Medicine, Stanford, CA 94305, USA;
lutian@stanford.edu
7
Community Medical Centers, UCSF Fresno, Fresno, CA 93722, USA; sladella@communitymedical.org
8
UC Davis Health, Sacramento, CA 95817, USA
9
Department of Obstetrics and Gynecology, Stanford University School of Medicine, Stanford, CA 94305, USA;
yairb@stanford.edu
10
Departments of Cardiothoracic Surgery and Pediatrics (Cardiology), Stanford University School of Medicine,
Stanford, CA 94305, USA; doff@stanford.edu
* Correspondence: bxling@stanford.edu; Tel.: +1-650-427-9198
Abstract: Preeclampsia (PE) is a condition that poses a significant risk of maternal mortality and
multiple organ failure during pregnancy. Early prediction of PE can enable timely surveillance and in-
terventions, such as low-dose aspirin administration. In this study, conducted at Stanford Health Care,
we examined a cohort of 60 pregnant women and collected 478 urine samples between gestational
weeks 8 and 20 for comprehensive metabolomic profiling. By employing liquid chromatography mass
spectrometry (LCMS/MS), we identified the structures of seven out of 26 metabolomics biomarkers
detected. Utilizing the XGBoost algorithm, we developed a predictive model based on these seven
metabolomics biomarkers to identify individuals at risk of developing PE. The performance of the
model was evaluated using 10-fold cross-validation, yielding an area under the receiver operating
characteristic curve of 0.856. Our findings suggest that measuring urinary metabolomics biomarkers
offers a noninvasive approach to assess the risk of PE prior to its onset.
Keywords: early pregnancy; preeclampsia risk prediction; biomarker; urinary metabolite; LC-MS/MS
1. Introduction
Preeclampsia (PE) is a severe hypertensive disorder that can contribute to the mortality
and morbidity of pregnant women [1]. PE can cause problems in the liver, kidneys, brain,
and blood coagulation system of pregnant women and can also lead to adverse pregnancy
outcomes such as poor fetal growth and premature birth [2]. Early treatment with low-dose
aspirin can effectively reduce the risk of developing PE [3]. Usually, PE develops after the
20th week of gestation. Therefore, accurate PE prediction before the 20th week could help
Metabolites 2023, 13, 715. https://doi.org/10.3390/metabo13060715 https://www.mdpi.com/journal/metabolites