Machine learning models for neurocognitive outcome prediction in preterm born infants
Related Experiment Video
Updated: Jun 1, 2025
Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale
Published on: August 25, 2014
Menne R van Boven1,2,3, Frank C Bennis4,5,6, Wes Onland7,5
1Emma Children's Hospital Amsterdam UMC, location University of Amsterdam, Department of Neonatology, Meibergdreef 9, Amsterdam, The Netherlands. m.r.vanboven@amsterdamumc.nl.
Insights
Machine learning models modestly improved neurocognitive outcome prediction in preterm infants, showing promise for early identification of children without adverse outcomes. These models utilized readily available neonatal data, outperforming conventional methods.
Area of Science:
- Neonatal Medicine
- Artificial Intelligence in Healthcare
- Developmental Pediatrics
Background:
- Neurocognitive outcome prediction in preterm infants is challenging.
- Existing methods often rely on complex predictors not suitable for routine clinical use.
- This study explored machine learning for improved prediction using accessible neonatal data.
Purpose of the Study:
- To investigate machine learning's potential to enhance neurocognitive outcome prediction in preterm infants.
- To compare machine learning models against conventional logistic regression.
- To utilize predictors readily available in neonatal settings.
Main Methods:
- Machine learning models (Random Forest, Support Vector Machine) were developed.
- Predictors from antenatal and neonatal periods were used for infants born <30 weeks gestation.
- Models were validated using internal cross-validation and compared to logistic regression.
Main Results:
- Random Forest and Support Vector Machine models achieved AUCs of 0.682 (2-year) and 0.695 (5-year).
- High negative predictive values (95% and 91%) were observed for identifying infants without adverse outcomes.
- Machine learning models significantly outperformed conventional logistic regression.
Conclusions:
- Machine learning offers a promising approach for early identification of preterm infants at low risk for adverse neurocognitive outcomes.
- While overall predictive performance was moderate, the high NPV is clinically valuable.
- Future research should explore integrating diverse routine clinical data, like vital sign time series, into predictive models.
Background:
Outcome prediction after preterm birth is important for long-term neonatal care, but has proven notoriously challenging for neurocognitive outcome. This study investigated the potential of machine learning to improve neurocognitive outcome prediction at two and five years of corrected age in preterm infants, using readily available predictors from the neonatal setting.
Methods:
Predictors originating from the antenatal and neonatal period of preterm infants born <30 weeks gestation were used to predict adverse neurocognitive outcome on the Bayley Scale and Wechsler Preschool and Primary Scale of Intelligence. Machine learning models were compared to conventional logistic regression and validated using internal cross-validation.
Results:
Best performing models were a random forest (two-year outcome) and a support vector machine (five-year outcome) with an area under the receiver operating characteristic curve (AUC) of 0.682 and 0.695 respectively, reaching high negative predictive values (95% and 91%, respectively). These models performed significantly better than the conventional models.
Conclusions:
The models reached moderate overall predictive performance, yet with promising potential for early identification of children without adverse neurocognitive outcome. Machine learning modestly improved neurocognitive outcome prediction. Future research may harvest the predictive potential of a wider variety of routine (clinical) data, such as vital sign time series.
Impact:
Early prediction of neurocognitive outcome in preterm infants will enable targeted follow-up and deployment of early (preventative) interventions to improve outcome. Neurocognitive outcome remains notoriously challenging using conventional models, while existing machine learning models depend on advanced MRI-derived predictors with limited potential for implementation into daily clinical practice. This study developed machine learning models for neurocognitive outcome prediction using predictors that are readily available in neonatal settings. Neurocognitive outcome prediction remains challenging due to low AUC and PPV, however, the models demonstrate high NPV, indicating potential for identifying children at low risk for adverse outcome.
More Related Videos
11:14A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
Published on: October 4, 2015
05:58Application of an Amplitude-integrated EEG Monitor Cerebral Function Monitor to Neonates
Published on: September 6, 2017