Related Experiment Video
Updated: Jul 13, 2026
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Early prediction of preeclampsia from clinical, multi-omics and laboratory data using random forest model
Qiang Zhao1,2, Jia Li3,4, Zhuo Diao4
1Department of Obstetrics and Gynecology, Jiangmen Central Hospital, Guangdong Province, Jiangmen, 529030, China.
Insights
Predicting preeclampsia (PE) early in pregnancy is challenging. This study developed accurate prediction models for early-onset PE and late-onset PE using clinical, metabolomic, proteomic, and laboratory data, improving early risk assessment.
Area of Science:
- Obstetrics and Gynecology
- Biomarker Discovery
- Translational Medicine
Background:
- Predicting preeclampsia (PE) before 16 weeks gestation is difficult due to complex risk factors and varied causes.
- Early identification of PE subtypes, early-onset PE (EPE) and late-onset PE (LPE), remains a clinical challenge.
Purpose of the Study:
- To develop predictive models for EPE and LPE using clinical, metabolomic, proteomic, and laboratory data.
- To identify key biomarkers for differentiating PE subtypes from normotensive pregnancies.
Main Methods:
- Retrospective analysis of 56 EPE, 50 LPE patients, and 92 controls using early pregnancy clinical and laboratory data.
- Multi-omics (metabolome, proteome) and laboratory variable analysis to identify differentially expressed biomarkers.
- Random forest algorithm applied to develop prediction models for EPE and LPE.
Main Results:
- Identified 49 metabolites and 28 proteins for EPE, and 33 metabolites and 36 proteins for LPE.
- Developed an EPE prediction model with 87.5% sensitivity and 94.1% specificity using seven clinical factors, seven metabolites, and five lab variables.
- Created an LPE prediction model with 66.7% sensitivity and 94.1% specificity using seven clinical factors, five metabolites, and eight proteins.
Conclusions:
- Significant omics and laboratory features were identified for PE prediction.
- The developed models demonstrate high predictive performance for preeclampsia risk.
- Integration of clinical, multi-omics, and laboratory data enhances early PE risk assessment.
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.
