Related Experiment Video
Updated: Jul 11, 2025
Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale
Published on: August 25, 2014
Developing a length of stay prediction model for newborns, achieving better accuracy with greater usability
Tzviel Frostig1, Yoav Benjamini2, Orli Kehat3
1Department of Statistics and Operation Research, Tel Aviv University, Ramat Aviv, 69978, Tel Aviv, Israel.
Insights
A new model accurately predicts Neonatal Intensive Care Unit (NICU) length of stay (LOS) for preterm newborns using only four factors available at birth. This simple, robust tool aids NICU management and parental anxiety.
Area of Science:
- Neonatalogy
- Biostatistics
- Health Informatics
Background:
- Preterm birth affects 1 in 10 newborns, leading to prolonged Neonatal Intensive Care Unit (NICU) stays.
- Extended NICU length of stay (LOS) impacts hospital resources, costs, and parental well-being.
- Accurate prediction of NICU LOS is crucial for effective resource allocation and management.
Purpose of the Study:
- To develop a generalizable and robust model for predicting the NICU LOS of preterm newborns.
- To identify key predictors of NICU LOS available at birth.
- To compare the performance of various predictive modeling techniques.
Main Methods:
- Utilized data from 5,362 newborns in a tertiary NICU (2011-2018) for model development.
- Externally validated the model on 8,768 newborns from another tertiary NICU.
- Compared Random Forest, quantile RF, LASSO, AIC step-forward, and a novel False Discovery Rate (FDR)-based quantile regression selection method.
Main Results:
- A high-order quantile regression model with four features at birth outperformed complex models.
- Achieved Mean Absolute Error (MAE) of 6.26 days (internal) and 6.04 days (external validation).
- The FDR-based selection demonstrated superior performance compared to AIC-based selection.
Conclusions:
- A simple, robust model for NICU LOS prediction in preterm infants was developed.
- The model significantly improves upon existing methods used for NICU financing.
- An accessible online web application was created to support parents and NICU management.
Background:
One in ten newborn children is born prematurely. The elongated length of stay (LOS) of these children in the Neonatal Intensive Care Unit (NICU) has important implications on hospital occupancy figures, healthcare and management costs, as well as the psychology of parents. In order to allow accurate planning and resource allocation, this study aims to create a generalizable and robust model to predict the NICU LOS of preterm newborns.
Methods:
Data were collected from a large tertiary center NICU between 2011 and 2018 and relates to 5,362 newborns. The selected model was externally validated using a data set of 8,768 newborns from another tertiary center NICU. This report compares several models, such as Random Forest (RF), quantile RF, and other feature selection methods, including LASSO and AIC step-forward selection. In addition, a novel step-forward selection based on False Discovery Rate (FDR) for quantile regression is presented and evaluated.
Results:
A high-orderquantile regression model for predicting preterm newborns' LOS that uses only four features available at birth had more attractive properties than other richer ones. The model achieved a Mean Absolute Error (MAE) of 6.26 days on the internal validation set (average LOS 27.04) and an MAE of 6.04 days on the external validation set (average LOS 29.32). The suggested model surpassed the accuracy obtained by models in the literature. It is shown empirically that the FDR-based selection has better properties than the AIC-based step-forward selection approach.
Conclusion:
This paper demonstrates a process to create a predictive model for NICU LOS in preterm newborns, where each step is reasoned. We obtain a simple and robust model for NICU LOS prediction, which achieves far better results than the current model used for financing NICUs. Utilizing this model, we have created an easy-to-use online web application to ease parents' worries and to assist NICU management: https://tzviel.shinyapps.io/calcuLOS.
