Related Experiment Video
Updated: Sep 8, 2025
19:15
Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale
Published on: August 25, 2014
86.3K
External Validation of a Model for Predicting Outcomes in Preterm Newborns
Laura Routier1,2, Sarah Touati1,3, Ghida Ghostine-Ramadan1,3
1INSERM UMR 1105, Research Group on Multimodal Analysis of Brain Function, University of Picardie Jules Verne, Amiens, France.
JAMA Network Open
|July 31, 2025
Summary
This study validated the PRETERM-POM model for predicting neurodevelopmental impairment in extremely preterm newborns. The model demonstrated high accuracy, confirming its clinical utility for guiding management and rehabilitation.
Area of Science:
- Neonatal Medicine
- Developmental Pediatrics
- Medical Informatics
Background:
- Predicting outcomes in preterm newborns is essential for tailored therapeutic strategies and rehabilitation.
- Prognostic models offer a promising avenue, but require robust validation for reliability and generalizability.
Purpose of the Study:
- To externally validate the PRETERM-POM, a multimodal prognostic model designed to predict outcomes in extremely preterm infants at two years of age.
Main Methods:
- A temporal validation group of preterm infants (23-28 weeks gestational age) born between 2018-2021 was used.
- The PRETERM-POM model's parameters were applied to predict neurodevelopmental outcomes (favorable vs. adverse) assessed via the Denver Developmental Screening Test-II.
- Statistical analyses included AUC, DeLong test, calibration-in-the-large, calibration curves, Hosmer-Lemeshow test, and Brier score.
Main Results:
- The validation group included 104 infants (median gestational age 26.3 weeks).
- The PRETERM-POM model achieved an AUC of 85.9% for outcome prediction, comparable to the development cohort.
- The model demonstrated good fit but tended to underestimate the risk of adverse outcomes.
Conclusions:
- External validation confirmed the PRETERM-POM model's high performance in predicting neurodevelopmental impairment in preterm infants.
- This multimodal approach, with transparent risk factor contributions, supports its clinical application for timely management decisions.
Related Concept Videos
01:03Data Validation
5.3K
Data validation is an essential part of a comprehensive assessment. Validation is confirming or verifying and opening the door to gathering more assessment data as it clarifies vague or unclear data. The process of checking and verifying the collected information is called data validation. The primary purpose of data validation is to ensure data is as free from error, bias, and misinterpretation as possible.
Nursing assessment guides are generally based on holistic models rather than medical...
Nursing assessment guides are generally based on holistic models rather than medical...
5.3K
01:52Regression Toward the Mean
6.5K
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...
6.5K