Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 16, 2026

Disruption of the Mouse Blood-Brain Barrier by Small Extracellular Vesicles from Hypoxic Human Placentas

Disruption of the Mouse Blood-Brain Barrier by Small Extracellular Vesicles from Hypoxic Human Placentas

Published on: January 26, 2024

Phenotyping Preeclampsia Using Unsupervised Machine Learning: A Prospective Cohort Study.

Ohad Houri¹, Lina Youssef¹, Francesca Crovetto^1,2

¹BCNatal-Barcelona Center for Maternal-Fetal and Neonatal Medicine (Hospital Clínic and Hospital Sant Joan de Deu), IDIBAPS, University of Barcelona, Barcelona, Spain.

BJOG : an International Journal of Obstetrics and Gynaecology

|May 15, 2026

Summary

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

Blood biomarkers and atrial remodeling in patients at risk of atrial fibrillation.

Frontiers in molecular medicine·2026

Same author

Markers in umbilical cord blood in early-onset fetal growth restricted fetuses.

Placenta·2026

Same author

Myocardial relaxation, left ventricular filling, and exercise capacity in older subjects with dyspnea.

American journal of physiology. Heart and circulatory physiology·2026

Same author

Representation learning for the prediction of length of stay in infants with congenital heart diseases undergoing cardiac surgery.

European heart journal. Digital health·2026

Same author

Histopathological placental findings in antiphospholipid antibody carriers with a fetal loss beyond 12 weeks of pregnancy.

Placenta·2026

Same author

Automated 4D flow MRI pipeline for the quantification of advanced hemodynamic parameters in the left atrium.

Scientific reports·2026

Same journal

Impact of a Structured Caesarean Reduction Strategy on Perinatal Outcomes: A Retrospective Ecological Time-Trend Study.

BJOG : an international journal of obstetrics and gynaecology·2026

Same journal

Long-Term Outcomes After Retropubic and Transobturator Sling Procedures: Reoperation for Recurrent Stress Urinary Incontinence.

BJOG : an international journal of obstetrics and gynaecology·2026

Same journal

First Trimester Screening for Preterm Preeclampsia in the United Kingdom: A Cost-Effectiveness Analysis.

BJOG : an international journal of obstetrics and gynaecology·2026

Same journal

Correction to "The Management of Nausea and Vomiting in Pregnancy and Hyperemesis Gravidarum (Green-Top Guideline No. 69)".

BJOG : an international journal of obstetrics and gynaecology·2026

Same journal

Large Language Models on European Guidelines for Cervical Cancer: Implications of Design and Clinical Applicability.

BJOG : an international journal of obstetrics and gynaecology·2026

Same journal

Internal Consistency of the Hadlock Estimated Fetal Weight Reference: Methodological Analysis.

BJOG : an international journal of obstetrics and gynaecology·2026

See all related articles

This summary is machine-generated.

Unsupervised machine learning identified three distinct preeclampsia phenotypes in pregnant women. These data-driven phenotypes may improve risk stratification and personalized management strategies for preeclampsia.

Area of Science:

Obstetrics and Gynecology
Perinatal Medicine
Computational Biology

Background:

Preeclampsia is a complex hypertensive disorder of pregnancy with variable clinical presentations.
Identifying distinct phenotypes is crucial for targeted management and improved outcomes.

Purpose of the Study:

To explore clinically meaningful phenotypes of preeclampsia using unsupervised machine learning.
To stratify patients and potentially personalize management strategies.

Main Methods:

Prospective cohort study of 482 pregnant women with preeclampsia.
Utilized maternal demographic, clinical, ultrasound, and laboratory data.
Applied Uniform Manifold Approximation and Projection for dimensionality reduction, followed by k-means clustering.

Keywords:

cluster analysis preeclampsia pregnancy complications unsupervised machine learning

Related Experiment Videos

Last Updated: May 16, 2026

Disruption of the Mouse Blood-Brain Barrier by Small Extracellular Vesicles from Hypoxic Human Placentas

Disruption of the Mouse Blood-Brain Barrier by Small Extracellular Vesicles from Hypoxic Human Placentas

Published on: January 26, 2024

Main Results:

Three distinct preeclampsia phenotypes were identified.
Cluster A: Early delivery, high angiogenic imbalance, fetal growth restriction, highest complication rates.
Cluster C: Term delivery, lowest angiogenic imbalance, highest birthweight, lowest complication rates, higher obesity/diabetes prevalence.

Conclusions:

Unsupervised learning successfully delineated three clinically relevant preeclampsia phenotypes.
These phenotypes offer potential for future risk stratification and personalized management.
Prospective external validation is recommended to confirm findings.