Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Decoding preeclampsia: A fusion of multi-view machine learning and multi-omics to identify putative inflammation-related mechanisms.

Molecular therapy. Nucleic acids·2026
Same author

A fluorescence spectrometry method for vitamin B6 determination based on its coordination reaction with Fe<sup>3</sup>.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2026
Same author

Targeted metabolomics reveals tricarboxylic acid cycle-related metabolites serve as predictive biomarkers for trastuzumab resistance in human epidermal growth factor receptor 2-positive breast cancer.

Journal of molecular medicine (Berlin, Germany)·2025
Same author

Smug1 alleviates the reproductive toxicity of 5-FU through functioning in rRNA quality control.

Scientific reports·2025
Same author

OTAMatch: Optimal Transport Assignment with PseudoNCE for Semi-supervised Learning.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2024
Same author

Analysis of the potential regulatory mechanisms of female and latent genital tuberculosis affecting ovarian reserve function using untargeted metabolomics.

Scientific reports·2024

Related Experiment Video

Updated: Jan 15, 2026

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

7.5K

Clinical Deployment of Interpretable AI: Bridging Routine Clinical Tests and Proteomic Signatures for Preeclampsia

Yuting Guo1,2, Yuchao Liang1,2, Ming Liu1,2

  • 1State Key Laboratory of Reproductive Regulation and Breeding of Grassland Livestock, School of Life Sciences, Inner Mongolia University, Hohhot, 010021, China.

Current Drug Targets
|October 14, 2025
PubMed
Summary

Preeclampsia diagnosis is improved using machine learning models that analyze routine lab tests and proteomic data. A new prediction system enhances early detection and accuracy for this leading cause of maternal mortality.

Keywords:
Preeclampsiamachine learningprediction.routine clinical laboratory tests

More Related Videos

A High Throughput, Multiplexed and Targeted Proteomic CSF Assay to Quantify Neurodegenerative Biomarkers and Apolipoprotein E Isoforms Status
07:08

A High Throughput, Multiplexed and Targeted Proteomic CSF Assay to Quantify Neurodegenerative Biomarkers and Apolipoprotein E Isoforms Status

Published on: October 20, 2016

8.2K
Hydra, a Computer-Based Platform for Aiding Clinicians in Cardiovascular Analysis and Diagnosis
07:51

Hydra, a Computer-Based Platform for Aiding Clinicians in Cardiovascular Analysis and Diagnosis

Published on: September 26, 2018

8.0K

Related Experiment Videos

Last Updated: Jan 15, 2026

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

7.5K
A High Throughput, Multiplexed and Targeted Proteomic CSF Assay to Quantify Neurodegenerative Biomarkers and Apolipoprotein E Isoforms Status
07:08

A High Throughput, Multiplexed and Targeted Proteomic CSF Assay to Quantify Neurodegenerative Biomarkers and Apolipoprotein E Isoforms Status

Published on: October 20, 2016

8.2K
Hydra, a Computer-Based Platform for Aiding Clinicians in Cardiovascular Analysis and Diagnosis
07:51

Hydra, a Computer-Based Platform for Aiding Clinicians in Cardiovascular Analysis and Diagnosis

Published on: September 26, 2018

8.0K

Area of Science:

  • Obstetrics and Gynecology
  • Biomarker Discovery
  • Machine Learning in Healthcare

Background:

  • Preeclampsia (PE) is a significant global cause of maternal mortality, affecting 5% of first-time pregnancies.
  • Clinical heterogeneity in PE necessitates improved diagnostic accuracy and novel biomarkers.
  • Current diagnostic methods, like proteinuria (PRO) testing, require quantitative evaluation and enhancement.

Purpose of the Study:

  • To quantitatively assess the diagnostic efficiency of positive proteinuria (PRO) for preeclampsia (PE).
  • To develop and compare machine learning models for PE prediction using routine clinical laboratory tests (RCLTs) and proteomic data.
  • To identify novel protein biomarkers for enhanced PE diagnosis.

Main Methods:

  • Utilized data from 1,215 pregnant women and 362 peripheral blood proteomic samples.
  • Applied and evaluated 5 machine learning models for PE prediction.
  • Performed feature selection to identify key RCLTs for a practical prediction model.

Main Results:

  • Machine learning assessment of PRO yielded an AUROC of 0.771.
  • Integrating 66 RCLTs improved PE prediction accuracy with an AUROC of 0.920.
  • A superior model using 5 RCLTs (PRO, ALP, AMY, UA, LDH) was developed; EphA1 identified as a potential protein biomarker.

Conclusions:

  • Developed a cost-effective PE prediction system using routine clinical data and machine learning.
  • The study quantitatively assessed proteinuria's diagnostic efficiency and identified key predictive features.
  • An interpretable webserver was established to aid in early PE detection and improve diagnostic accuracy.