Early prediction of preeclampsia from clinical, multi-omics and laboratory data using random forest model

Abstract Background Predicting preeclampsia (PE) within the first 16 weeks of gestation is difficult due to various risk factors, poorly understood causes and likely multiple pathogenic phenotypes of preeclampsia.  Objectives In this study, we aimed to develop prediction models for early-onset preec...

Full description

Saved in:
Bibliographic Details
Main Authors: Qiang Zhao, Jia Li, Zhuo Diao, Xiao Zhang, Suihua Feng, Guixue Hou, Wenqiu Xu, Zhiguang Zhao, Zhixu Qiu, Wenzhi Yang, Si Zhou, Peirun Tian, Qun Zhang, Weiping Chen, Huahua Li, Gefei Xiao, Jie Qin, Liqing Hu, Zhongzhe Li, Liang Lin, Shunyao Wang, Ruyun Gao, Wuyan Huang, Xiaohong Ruan, Sufen Zhang, Jianguo Zhang, Lijian Zhao, Rui Zhang
Format: Article
Language:English
Published: BMC 2025-05-01
Series:BMC Pregnancy and Childbirth
Subjects:
Online Access:https://doi.org/10.1186/s12884-025-07582-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849311913556574208
author Qiang Zhao
Jia Li
Zhuo Diao
Xiao Zhang
Suihua Feng
Guixue Hou
Wenqiu Xu
Zhiguang Zhao
Zhixu Qiu
Wenzhi Yang
Si Zhou
Peirun Tian
Qun Zhang
Weiping Chen
Huahua Li
Gefei Xiao
Jie Qin
Liqing Hu
Zhongzhe Li
Liang Lin
Shunyao Wang
Ruyun Gao
Wuyan Huang
Xiaohong Ruan
Sufen Zhang
Jianguo Zhang
Lijian Zhao
Rui Zhang
author_facet Qiang Zhao
Jia Li
Zhuo Diao
Xiao Zhang
Suihua Feng
Guixue Hou
Wenqiu Xu
Zhiguang Zhao
Zhixu Qiu
Wenzhi Yang
Si Zhou
Peirun Tian
Qun Zhang
Weiping Chen
Huahua Li
Gefei Xiao
Jie Qin
Liqing Hu
Zhongzhe Li
Liang Lin
Shunyao Wang
Ruyun Gao
Wuyan Huang
Xiaohong Ruan
Sufen Zhang
Jianguo Zhang
Lijian Zhao
Rui Zhang
author_sort Qiang Zhao
collection DOAJ
description Abstract Background Predicting preeclampsia (PE) within the first 16 weeks of gestation is difficult due to various risk factors, poorly understood causes and likely multiple pathogenic phenotypes of preeclampsia.  Objectives In this study, we aimed to develop prediction models for early-onset preeclampsia (EPE) and late-onset preeclampsia (LPE) respectively using clinical data, metabolome and proteome analyses on plasma samples and laboratory data. Methods We retrospectively recruited 56 EPE, 50 LPE patients and 92 normotensive controls from three tertiary hospitals and used clinical and laboratory data in early pregnancy. Models for EPE and LPE were fitted with the use of patient’ clinical, multi-omics and laboratory data. Results By comparing multi-omics and laboratory test variables between EPE, LPE and healthy controls, we identified sets of differentially expressed biomarkers, including 49 and 33 metabolites, 28 and 36 proteins as well as 5 and 7 laboratory variables associated with EPE and LPE respectively. Using the random forest algorithm, we developed a prediction model using seven clinical factors, seven metabolites, five laboratory test variables. The model yielded the highest accuracy for EPE prediction with good sensitivity (87.5%, 95% confidence interval [CI]: 67.64%-97.34%) and specificity (94.1%, 95% CI: 80.32%-99.28%). We also developed a prediction model that exhibited high accuracy in separating LPE from controls (sensitivity: 66.67%, 95% CI: 43.03%-85.41%; specificity: 94.12%, 95% CI: 80.32%-99.28%) using seven clinical factors, five metabolites and eight proteins. Conclusion Our study has identified a set of significant omics and laboratory features for PE prediction. The established models yielded high prediction performance for preeclampsia risk from clinical, multi-omics and laboratory information.
format Article
id doaj-art-22de0bb5b4f84c9d8402338abeeefc64
institution Kabale University
issn 1471-2393
language English
publishDate 2025-05-01
publisher BMC
record_format Article
series BMC Pregnancy and Childbirth
spelling doaj-art-22de0bb5b4f84c9d8402338abeeefc642025-08-20T03:53:16ZengBMCBMC Pregnancy and Childbirth1471-23932025-05-0125111510.1186/s12884-025-07582-4Early prediction of preeclampsia from clinical, multi-omics and laboratory data using random forest modelQiang Zhao0Jia Li1Zhuo Diao2Xiao Zhang3Suihua Feng4Guixue Hou5Wenqiu Xu6Zhiguang Zhao7Zhixu Qiu8Wenzhi Yang9Si Zhou10Peirun Tian11Qun Zhang12Weiping Chen13Huahua Li14Gefei Xiao15Jie Qin16Liqing Hu17Zhongzhe Li18Liang Lin19Shunyao Wang20Ruyun Gao21Wuyan Huang22Xiaohong Ruan23Sufen Zhang24Jianguo Zhang25Lijian Zhao26Rui Zhang27Department of Obstetrics and Gynecology, Jiangmen Central HospitalClin Lab, Hebei Industrial Technology Research Institute of Genomics in Maternal & Child Health, BGI GenomicsBGI GenomicsClin Lab, Hebei Industrial Technology Research Institute of Genomics in Maternal & Child Health, BGI GenomicsDepartment of Obstetrics and Gynecology, Jiangmen Central HospitalBGI GenomicsClin Lab, Hebei Industrial Technology Research Institute of Genomics in Maternal & Child Health, BGI GenomicsClin Lab, Hebei Industrial Technology Research Institute of Genomics in Maternal & Child Health, BGI GenomicsClin Lab, Hebei Industrial Technology Research Institute of Genomics in Maternal & Child Health, BGI GenomicsClin Lab, Hebei Industrial Technology Research Institute of Genomics in Maternal & Child Health, BGI GenomicsClin Lab, Hebei Industrial Technology Research Institute of Genomics in Maternal & Child Health, BGI GenomicsBGI GenomicsDepartment of Obstetrics and Gynecology, Jiangmen Central HospitalDepartment of Obstetrics and Gynecology, Jiangmen Central HospitalDepartment of Obstetrics and Gynecology, Jiangmen Central HospitalInstitute of Medical Genetics, Zhuhai Center for Maternal and Child Health CareInstitute of Medical Genetics, Zhuhai Center for Maternal and Child Health CareInstitute of Medical Genetics, Zhuhai Center for Maternal and Child Health CareDepartment of Prevention and Health Care, Zhuhai Center for Maternal and Child Health CareBGI GenomicsBGI GenomicsSchool of Public Health, Hebei Province Key Laboratory of Environment and Human Health, Hebei Medical UniversityInstitute of Medical Genetics, Zhuhai Center for Maternal and Child Health CareDepartment of Obstetrics and Gynecology, Jiangmen Central HospitalInstitute of Medical Genetics, Zhuhai Center for Maternal and Child Health CareClin Lab, Hebei Industrial Technology Research Institute of Genomics in Maternal & Child Health, BGI GenomicsClin Lab, Hebei Industrial Technology Research Institute of Genomics in Maternal & Child Health, BGI GenomicsDivision of Maternal-Fetal Medicine, Shenzhen Baoan Women’s and Children’s HospitalAbstract Background Predicting preeclampsia (PE) within the first 16 weeks of gestation is difficult due to various risk factors, poorly understood causes and likely multiple pathogenic phenotypes of preeclampsia.  Objectives In this study, we aimed to develop prediction models for early-onset preeclampsia (EPE) and late-onset preeclampsia (LPE) respectively using clinical data, metabolome and proteome analyses on plasma samples and laboratory data. Methods We retrospectively recruited 56 EPE, 50 LPE patients and 92 normotensive controls from three tertiary hospitals and used clinical and laboratory data in early pregnancy. Models for EPE and LPE were fitted with the use of patient’ clinical, multi-omics and laboratory data. Results By comparing multi-omics and laboratory test variables between EPE, LPE and healthy controls, we identified sets of differentially expressed biomarkers, including 49 and 33 metabolites, 28 and 36 proteins as well as 5 and 7 laboratory variables associated with EPE and LPE respectively. Using the random forest algorithm, we developed a prediction model using seven clinical factors, seven metabolites, five laboratory test variables. The model yielded the highest accuracy for EPE prediction with good sensitivity (87.5%, 95% confidence interval [CI]: 67.64%-97.34%) and specificity (94.1%, 95% CI: 80.32%-99.28%). We also developed a prediction model that exhibited high accuracy in separating LPE from controls (sensitivity: 66.67%, 95% CI: 43.03%-85.41%; specificity: 94.12%, 95% CI: 80.32%-99.28%) using seven clinical factors, five metabolites and eight proteins. Conclusion Our study has identified a set of significant omics and laboratory features for PE prediction. The established models yielded high prediction performance for preeclampsia risk from clinical, multi-omics and laboratory information.https://doi.org/10.1186/s12884-025-07582-4PreeclampsiaProteomeMetabolomeLaboratory dataRandom forest
spellingShingle Qiang Zhao
Jia Li
Zhuo Diao
Xiao Zhang
Suihua Feng
Guixue Hou
Wenqiu Xu
Zhiguang Zhao
Zhixu Qiu
Wenzhi Yang
Si Zhou
Peirun Tian
Qun Zhang
Weiping Chen
Huahua Li
Gefei Xiao
Jie Qin
Liqing Hu
Zhongzhe Li
Liang Lin
Shunyao Wang
Ruyun Gao
Wuyan Huang
Xiaohong Ruan
Sufen Zhang
Jianguo Zhang
Lijian Zhao
Rui Zhang
Early prediction of preeclampsia from clinical, multi-omics and laboratory data using random forest model
BMC Pregnancy and Childbirth
Preeclampsia
Proteome
Metabolome
Laboratory data
Random forest
title Early prediction of preeclampsia from clinical, multi-omics and laboratory data using random forest model
title_full Early prediction of preeclampsia from clinical, multi-omics and laboratory data using random forest model
title_fullStr Early prediction of preeclampsia from clinical, multi-omics and laboratory data using random forest model
title_full_unstemmed Early prediction of preeclampsia from clinical, multi-omics and laboratory data using random forest model
title_short Early prediction of preeclampsia from clinical, multi-omics and laboratory data using random forest model
title_sort early prediction of preeclampsia from clinical multi omics and laboratory data using random forest model
topic Preeclampsia
Proteome
Metabolome
Laboratory data
Random forest
url https://doi.org/10.1186/s12884-025-07582-4
work_keys_str_mv AT qiangzhao earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT jiali earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT zhuodiao earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT xiaozhang earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT suihuafeng earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT guixuehou earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT wenqiuxu earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT zhiguangzhao earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT zhixuqiu earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT wenzhiyang earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT sizhou earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT peiruntian earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT qunzhang earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT weipingchen earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT huahuali earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT gefeixiao earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT jieqin earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT liqinghu earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT zhongzheli earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT lianglin earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT shunyaowang earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT ruyungao earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT wuyanhuang earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT xiaohongruan earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT sufenzhang earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT jianguozhang earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT lijianzhao earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel
AT ruizhang earlypredictionofpreeclampsiafromclinicalmultiomicsandlaboratorydatausingrandomforestmodel