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

Related Concept Videos

Regression Toward the Mean

Regression Toward the Mean

Regression toward the mean (“RTM”) is a phenomenon in which extremely high or low values—for example, and individual’s blood pressure at a particular moment—appear closer to a group’s average upon remeasuring. Although this statistical peculiarity is the result of random error and chance, it has been problematic across various medical, scientific, financial and psychological applications. In particular, RTM, if not taken into account, can interfere when...

You might also read

Related Articles

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

Sort by

Same author

Increased risk of postpartum hemorrhage in women with endometriosis and adenomyosis: a prospective cohort study.

Frontiers in endocrinology·2026

Same author

Addressing the translation gap in SCT donor selection.

Frontiers in immunology·2026

Same author

Maternal overweight and obesity during pregnancy and sex-dependent dysregulation of the materno-fetal stress axis.

International journal of gynaecology and obstetrics: the official organ of the International Federation of Gynaecology and Obstetrics·2026

Same author

Maternal health behavior during pregnancy mediates the relationship between maternal stress and newborn telomere length.

Brain, behavior, & immunity - health·2026

Same author

Repeat cesarean delivery with hysterectomy: a sheep model to examine uterine scars.

Reproduction & fertility·2026

Same author

Maternal obesity and the metabolic syndrome in reproductive health: assessing incretin-based interventions.

Reviews in endocrine & metabolic disorders·2026

Search research articles

Related Experiment Video

Updated: Oct 4, 2025

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

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

Published on: May 15, 2020

A machine-learning-based algorithm improves prediction of preeclampsia-associated adverse outcomes.

Leon J Schmidt¹, Oliver Rieger¹, Mark Neznansky¹

¹Department of Obstetrics, Charité - Universitätsmedizin Berlin, Berlin, Germany.

American Journal of Obstetrics and Gynecology

|February 3, 2022

Summary

Machine learning accurately predicts preeclampsia adverse outcomes using biomarkers and clinical data. This automated system offers improved prediction over standard clinical methods for high-risk pregnancies.

Keywords:

adverse outcomes clinical decision support machine learning placental growth factor predictive models preeclampsia random forest soluble fms-like tyrosine kinase-1

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Related Experiment Videos

Last Updated: Oct 4, 2025

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

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

Published on: May 15, 2020

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Area of Science:

Obstetrics and Gynecology
Medical Informatics
Machine Learning in Healthcare

Background:

Preeclampsia is a prevalent pregnancy complication (2-5% incidence), significantly increasing maternal mortality risk and perinatal morbidity.
It is a leading cause of perinatal mortality and morbidity, posing a substantial global health challenge.
Early detection of preeclampsia is crucial for improving maternal and fetal outcomes.

Purpose of the Study:

To develop and validate an automated machine learning model for predicting adverse outcomes in suspected preeclampsia cases.
To leverage novel biomarkers (soluble fms-like tyrosine kinase-1, placental growth factor) and clinical data for enhanced predictive accuracy.
To provide an automated, reliable tool for early risk assessment in preeclampsia.

Main Methods:

Retrospective analysis of a real-world dataset of 2472 samples from 1647 women with suspected preeclampsia.
Feature engineering included conventional clinical data, biomarkers, and sonographic indices (e.g., umbilical artery pulsatility index).
Two machine learning models (gradient-boosted tree, random forest) were trained and evaluated using 10x10-fold cross-validation.

Main Results:

The gradient-boosted tree model achieved 89%±3% overall accuracy, 88%±6% positive predictive value, and 97%±2% specificity.
The random forest classifier demonstrated comparable performance, with both models showing high predictive values.
Optimizing prediction cutoffs further enhanced model performance, demonstrating the model's adaptability.

Conclusions:

Machine learning models provide a valid and superior approach to predicting adverse outcomes in preeclampsia compared to current clinical standards.
The developed automated system requires no manual tuning, offering a practical tool for clinical implementation.
This approach holds significant potential for improving the management and outcomes of high-risk pregnancies.