Development of a Urine Metabolomics Biomarker-Based Prediction Model for Preeclampsia during Early Pregnancy

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 interventions, such as low-dose aspirin administration. In this study, conducted at Stanford Health Care, we exa...

Full description

Bibliographic Details
Main Authors: Yaqi Zhang, Karl G. Sylvester, Bo Jin, Ronald J. Wong, James Schilling, C. James Chou, Zhi Han, Ruben Y. Luo, Lu Tian, Subhashini Ladella, Lihong Mo, Ivana Marić, Yair J. Blumenfeld, Gary L. Darmstadt, Gary M. Shaw, David K. Stevenson, John C. Whitin, Harvey J. Cohen, Doff B. McElhinney, Xuefeng B. Ling
Format: Article
Language:English
Published: MDPI AG 2023-05-01
Series:Metabolites
Subjects:
Online Access:https://www.mdpi.com/2218-1989/13/6/715
_version_ 1797593493777940480
author Yaqi Zhang
Karl G. Sylvester
Bo Jin
Ronald J. Wong
James Schilling
C. James Chou
Zhi Han
Ruben Y. Luo
Lu Tian
Subhashini Ladella
Lihong Mo
Ivana Marić
Yair J. Blumenfeld
Gary L. Darmstadt
Gary M. Shaw
David K. Stevenson
John C. Whitin
Harvey J. Cohen
Doff B. McElhinney
Xuefeng B. Ling
author_facet Yaqi Zhang
Karl G. Sylvester
Bo Jin
Ronald J. Wong
James Schilling
C. James Chou
Zhi Han
Ruben Y. Luo
Lu Tian
Subhashini Ladella
Lihong Mo
Ivana Marić
Yair J. Blumenfeld
Gary L. Darmstadt
Gary M. Shaw
David K. Stevenson
John C. Whitin
Harvey J. Cohen
Doff B. McElhinney
Xuefeng B. Ling
author_sort Yaqi Zhang
collection DOAJ
description 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 interventions, 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.
first_indexed 2024-03-11T02:09:57Z
format Article
id doaj.art-12f704f046f849cbb2610c1b43b80fd1
institution Directory Open Access Journal
issn 2218-1989
language English
last_indexed 2024-03-11T02:09:57Z
publishDate 2023-05-01
publisher MDPI AG
record_format Article
series Metabolites
spelling doaj.art-12f704f046f849cbb2610c1b43b80fd12023-11-18T11:34:42ZengMDPI AGMetabolites2218-19892023-05-0113671510.3390/metabo13060715Development of a Urine Metabolomics Biomarker-Based Prediction Model for Preeclampsia during Early PregnancyYaqi Zhang0Karl G. Sylvester1Bo Jin2Ronald J. Wong3James Schilling4C. James Chou5Zhi Han6Ruben Y. Luo7Lu Tian8Subhashini Ladella9Lihong Mo10Ivana Marić11Yair J. Blumenfeld12Gary L. Darmstadt13Gary M. Shaw14David K. Stevenson15John C. Whitin16Harvey J. Cohen17Doff B. McElhinney18Xuefeng B. Ling19College of Automation, Guangdong Polytechnic Normal University, Guangzhou 510665, ChinaDepartment of Surgery, Stanford University School of Medicine, Stanford, CA 94305, USAmProbe Inc., Palo Alto, CA 94303, USADepartment of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USAmProbe Inc., Palo Alto, CA 94303, USADepartment of Surgery, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Surgery, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Pathology, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Biomedical Data Science, Stanford University School of Medicine, Stanford, CA 94305, USACommunity Medical Centers, UCSF Fresno, Fresno, CA 93722, USAUC Davis Health, Sacramento, CA 95817, USADepartment of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Obstetrics and Gynecology, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USADepartments of Cardiothoracic Surgery and Pediatrics (Cardiology), Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Surgery, Stanford University School of Medicine, Stanford, CA 94305, USAPreeclampsia (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 interventions, 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.https://www.mdpi.com/2218-1989/13/6/715early pregnancypreeclampsia risk predictionbiomarkerurinary metaboliteLC-MS/MS
spellingShingle Yaqi Zhang
Karl G. Sylvester
Bo Jin
Ronald J. Wong
James Schilling
C. James Chou
Zhi Han
Ruben Y. Luo
Lu Tian
Subhashini Ladella
Lihong Mo
Ivana Marić
Yair J. Blumenfeld
Gary L. Darmstadt
Gary M. Shaw
David K. Stevenson
John C. Whitin
Harvey J. Cohen
Doff B. McElhinney
Xuefeng B. Ling
Development of a Urine Metabolomics Biomarker-Based Prediction Model for Preeclampsia during Early Pregnancy
Metabolites
early pregnancy
preeclampsia risk prediction
biomarker
urinary metabolite
LC-MS/MS
title Development of a Urine Metabolomics Biomarker-Based Prediction Model for Preeclampsia during Early Pregnancy
title_full Development of a Urine Metabolomics Biomarker-Based Prediction Model for Preeclampsia during Early Pregnancy
title_fullStr Development of a Urine Metabolomics Biomarker-Based Prediction Model for Preeclampsia during Early Pregnancy
title_full_unstemmed Development of a Urine Metabolomics Biomarker-Based Prediction Model for Preeclampsia during Early Pregnancy
title_short Development of a Urine Metabolomics Biomarker-Based Prediction Model for Preeclampsia during Early Pregnancy
title_sort development of a urine metabolomics biomarker based prediction model for preeclampsia during early pregnancy
topic early pregnancy
preeclampsia risk prediction
biomarker
urinary metabolite
LC-MS/MS
url https://www.mdpi.com/2218-1989/13/6/715
work_keys_str_mv AT yaqizhang developmentofaurinemetabolomicsbiomarkerbasedpredictionmodelforpreeclampsiaduringearlypregnancy
AT karlgsylvester developmentofaurinemetabolomicsbiomarkerbasedpredictionmodelforpreeclampsiaduringearlypregnancy
AT bojin developmentofaurinemetabolomicsbiomarkerbasedpredictionmodelforpreeclampsiaduringearlypregnancy
AT ronaldjwong developmentofaurinemetabolomicsbiomarkerbasedpredictionmodelforpreeclampsiaduringearlypregnancy
AT jamesschilling developmentofaurinemetabolomicsbiomarkerbasedpredictionmodelforpreeclampsiaduringearlypregnancy
AT cjameschou developmentofaurinemetabolomicsbiomarkerbasedpredictionmodelforpreeclampsiaduringearlypregnancy
AT zhihan developmentofaurinemetabolomicsbiomarkerbasedpredictionmodelforpreeclampsiaduringearlypregnancy
AT rubenyluo developmentofaurinemetabolomicsbiomarkerbasedpredictionmodelforpreeclampsiaduringearlypregnancy
AT lutian developmentofaurinemetabolomicsbiomarkerbasedpredictionmodelforpreeclampsiaduringearlypregnancy
AT subhashiniladella developmentofaurinemetabolomicsbiomarkerbasedpredictionmodelforpreeclampsiaduringearlypregnancy
AT lihongmo developmentofaurinemetabolomicsbiomarkerbasedpredictionmodelforpreeclampsiaduringearlypregnancy
AT ivanamaric developmentofaurinemetabolomicsbiomarkerbasedpredictionmodelforpreeclampsiaduringearlypregnancy
AT yairjblumenfeld developmentofaurinemetabolomicsbiomarkerbasedpredictionmodelforpreeclampsiaduringearlypregnancy
AT garyldarmstadt developmentofaurinemetabolomicsbiomarkerbasedpredictionmodelforpreeclampsiaduringearlypregnancy
AT garymshaw developmentofaurinemetabolomicsbiomarkerbasedpredictionmodelforpreeclampsiaduringearlypregnancy
AT davidkstevenson developmentofaurinemetabolomicsbiomarkerbasedpredictionmodelforpreeclampsiaduringearlypregnancy
AT johncwhitin developmentofaurinemetabolomicsbiomarkerbasedpredictionmodelforpreeclampsiaduringearlypregnancy
AT harveyjcohen developmentofaurinemetabolomicsbiomarkerbasedpredictionmodelforpreeclampsiaduringearlypregnancy
AT doffbmcelhinney developmentofaurinemetabolomicsbiomarkerbasedpredictionmodelforpreeclampsiaduringearlypregnancy
AT xuefengbling developmentofaurinemetabolomicsbiomarkerbasedpredictionmodelforpreeclampsiaduringearlypregnancy