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

Regression Toward the Mean01:52

Regression Toward the Mean

6.6K
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...
6.6K
Steps in Outbreak Investigation01:18

Steps in Outbreak Investigation

326
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
326

You might also read

Related Articles

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

Sort by
Same author

Respiratory evolution after antenatal betamethasone dose reduction in very preterm neonates: a post hoc analysis of the BETADOSE trial.

European journal of pediatrics·2026
Same author

Commentary: Optimising neonatal transport team quality metrics.

Pediatric research·2026
Same author

Development and validity evidence for the probabilistic reasoning test in undergraduate medical students.

BMC medical education·2026
Same author

School-age neurodevelopmental outcomes after non-emergency red blood cell transfusions in preterm infants: a propensity score-matched study from the Epipage 2 cohort.

European journal of pediatrics·2026
Same author

Social Inequalities in Infant Mortality Related to Congenital Anomalies: A Population-Based Register Study.

Paediatric and perinatal epidemiology·2026
Same author

Early neonatal transfers after moderate and late preterm birth: a nationwide cohort study based on the French National Health Data System.

Pediatric research·2026

Related Experiment Video

Updated: Nov 16, 2025

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

7.4K

Machine-Learning vs. Expert-Opinion Driven Logistic Regression Modelling for Predicting 30-Day Unplanned

Robert A Reed1, Andrei S Morgan1,2,3, Jennifer Zeitlin1

  • 1Université de Paris, Epidemiology and Statistics Research Center/CRESS, INSERM, INRA, Paris, France.

Frontiers in Pediatrics
|February 22, 2021
PubMed
Summary

Machine learning models, specifically random forest, show improved prediction for unplanned rehospitalisations in preterm babies compared to traditional logistic regression. However, overall predictive accuracy remains limited for all methods.

Keywords:
epidemiologymachine-learningneonatologypredictionrehospitalisation

More Related Videos

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.7K
Establishing a Competing Risk Regression Nomogram Model for Survival Data
04:57

Establishing a Competing Risk Regression Nomogram Model for Survival Data

Published on: October 23, 2020

10.5K

Related Experiment Videos

Last Updated: Nov 16, 2025

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

7.4K
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.7K
Establishing a Competing Risk Regression Nomogram Model for Survival Data
04:57

Establishing a Competing Risk Regression Nomogram Model for Survival Data

Published on: October 23, 2020

10.5K

Area of Science:

  • Neonatal Medicine
  • Data Science
  • Biostatistics

Background:

  • Preterm infants face significant morbidity, with rehospitalisations being a key adverse event.
  • Accurate prediction of rehospitalisation risk is crucial for improving outcomes and reducing healthcare costs.
  • Machine learning offers potential advantages over traditional statistical methods for predictive modeling.

Purpose of the Study:

  • To compare the predictive performance of two machine learning algorithms (LASSO and random forest) against expert-driven logistic regression.
  • To identify the optimal method for predicting unplanned 30-day rehospitalisation in a large cohort of French preterm infants.
  • To assess the utility of machine learning in identifying high-risk preterm neonates for targeted interventions.

Main Methods:

  • Utilized data from the prospective EPIPAGE 2 cohort study of French preterm babies.
  • Developed and compared predictive models using logistic regression (10 predictors), LASSO (75 predictors), and random forest (75 predictors).
  • Evaluated model performance using 10-fold cross-validation, focusing on AUROC, sensitivity, specificity, Tjur's coefficient, and calibration.

Main Results:

  • The rate of 30-day unplanned rehospitalisation was 9.1% in the study population.
  • Random forest demonstrated superior predictive ability with a higher AUROC (0.65) and specificity compared to logistic regression (AUROC 0.57).
  • LASSO regression showed similar performance to logistic regression, with no significant improvement in predictive accuracy.

Conclusions:

  • Random forest models provide enhanced prediction of 30-day unplanned rehospitalisations in preterm infants compared to expert-selected logistic regression.
  • Despite improvements, the predictive power of all evaluated models was relatively modest.
  • Further research is needed to enhance predictive accuracy for preterm infant rehospitalisation.