Related Experiment Video
Updated: Jul 15, 2026
Scanning Skeletal Remains for Bone Mineral Density in Forensic Contexts
Published on: January 29, 2018
Prediction of Postnatal Growth Failure in Very Low Birth Weight Infants Using a Machine Learning Model
So Jin Yoon1, Donghyun Kim2,3, Sook Hyun Park1
1Department of Pediatrics, Yonsei University College of Medicine, Seoul 03722, Republic of Korea.
Insights
This study developed a machine learning model to predict postnatal growth failure in very low birth weight infants. The model achieved good early detection accuracy, aiding in timely interventions and improved infant health outcomes.
Area of Science:
- Neonatal Medicine
- Machine Learning in Healthcare
- Pediatric Growth Research
Background:
- Postnatal growth failure (PGF) impacts very low birth weight (VLBW) infants, necessitating early detection for intervention.
- Accurate prediction models are crucial for proactive management and improved VLBW infant outcomes.
Purpose of the Study:
- To develop and evaluate a machine learning model for predicting PGF in VLBW infants at discharge.
- To identify key predictive features for PGF using extreme gradient boosting.
Main Methods:
- Utilized extreme gradient boosting on data from 729 VLBW infants across four hospitals (2013-2017).
- Defined PGF as a z-score decrease >1.28 between birth and discharge.
- Performed feature selection and addition at multiple time points (0, 7, 14, 28 days) to optimize prediction accuracy.
Main Results:
- An initial model with 12 features achieved an AUROC of 0.78 at 7 days.
- Adding weight change improved the AUROC to 0.84 at 7 days.
- Identified key predictors including sex, gestational age, birth weight, SGA, maternal hypertension, RDS, ventilation duration, PDA, sepsis, PN, and FEN.
Conclusions:
- The developed machine learning model demonstrates strong early detection capabilities for PGF in VLBW infants.
- This predictive tool holds potential as a supplemental clinical aid to reduce PGF and enhance infant health.
- Early identification facilitates timely interventions, potentially mitigating long-term growth complications.
Abstract:
Accurate prediction of postnatal growth failure (PGF) can be beneficial for early intervention and prevention. We aimed to develop a machine learning model to predict PGF at discharge among very low birth weight (VLBW) infants using extreme gradient boosting. A total of 729 VLBW infants, born between 2013 and 2017 in four hospitals, were included. PGF was defined as a decrease in z-score between birth and discharge that was greater than 1.28. Feature selection and addition were performed to improve the accuracy of prediction at four different time points, including 0, 7, 14, and 28 days after birth. A total of 12 features with high contribution at all time points by feature importance were decided upon, and good performance was shown as an area under the receiver operating characteristic curve (AUROC) of 0.78 at 7 days. After adding weight change to the 12 features-which included sex, gestational age, birth weight, small for gestational age, maternal hypertension, respiratory distress syndrome, duration of invasive ventilation, duration of non-invasive ventilation, patent ductus arteriosus, sepsis, use of parenteral nutrition, and reach at full enteral nutrition-the AUROC at 7 days after birth was shown as 0.84. Our prediction model for PGF performed well at early detection. Its potential clinical application as a supplemental tool could be helpful for reducing PGF and improving child health.
Related Concept Videos
01:52Regression Toward the Mean
01:19Survival Tree
Building a Survival Tree
Constructing a survival tree begins...