Related Experiment Video
Updated: Apr 11, 2026
Short-Duration Hypothermia Induction in Rats using Models for Studies examining Clinical Relevance and Mechanisms
Published on: March 3, 2021
Development and internal validation of machine learning-based models for predicting admission hypothermia in preterm
Xiaokuan Cao1, Zuqin Peng1, Shihan Yao1
1Department of Neonatology, Children's Diagnosis and Treatment Center, The Affiliated Traditional Chinese Medicine Hospital, Southwest Medical University, Luzhou, Sichuan, China.
Insights
Machine learning models can predict hypothermia in preterm infants using routine data. Logistic regression offers a reliable and interpretable tool for early risk stratification and thermal management in neonates.
Area of Science:
- Neonatal Medicine
- Medical Informatics
- Machine Learning in Healthcare
Background:
- Admission hypothermia is a common, preventable complication in preterm infants, linked to higher morbidity and mortality.
- Early identification of at-risk infants is crucial for timely thermal management and prevention.
- This study focused on developing predictive models for admission hypothermia in preterm neonates.
Purpose of the Study:
- To develop and validate machine learning models for predicting admission hypothermia in preterm infants.
- To identify key predictors of admission hypothermia using routinely collected data.
- To evaluate the performance and interpretability of different machine learning algorithms for this prediction task.
Main Methods:
- A retrospective cohort study of preterm infants (<37 weeks' gestation) admitted to a tertiary neonatal center.
- Development and internal validation of six machine learning models (logistic regression, decision tree, random forest, support vector machine, artificial neural network, naïve Bayes).
- Least Absolute Shrinkage and Selection Operator (LASSO) regression for predictor selection, and Shapley Additive Explanations (SHAP) for model interpretability.
Main Results:
- Out of 346 preterm infants, 44.5% experienced admission hypothermia.
- Eleven predictors were identified, including gestational age, birth weight, ambient temperature, and transport time.
- Logistic regression and artificial neural network achieved the highest discrimination (AUC=0.86) in the validation cohort; logistic regression offered superior calibration and interpretability.
Conclusions:
- Machine learning models utilizing readily available perinatal and environmental data can effectively predict admission hypothermia in preterm infants.
- Logistic regression demonstrates robust predictive performance and interpretability, making it suitable for clinical integration.
- These models can aid in early neonatal risk stratification and guide targeted thermal management strategies to reduce hypothermia-related complications.
Background:
Admission hypothermia remains a frequent and preventable complication in preterm infants and is associated with increased morbidity and mortality. Early risk stratification may enable timely thermal management and targeted preventive strategies. This study aimed to develop and internally validate multivariable machine learning-based models for predicting admission hypothermia in preterm infants.
Methods:
We conducted a retrospective cohort study including consecutively admitted preterm infants (<37 weeks' gestation) at a tertiary neonatal referral center in Southwest China (January 2017-January 2025). Admission hypothermia was defined as an axillary temperature <36.5 °C at NICU admission. The dataset was randomly divided into a training cohort (70%) and a validation cohort (30%). Candidate predictors were selected using least absolute shrinkage and selection operator (LASSO) regression. Six models-logistic regression, decision tree, random forest, support vector machine, artificial neural network, and naïve Bayes-were developed. Model performance was evaluated using discrimination (AUC), calibration, Brier score, and classification metrics. Shapley Additive Explanations (SHAP) were applied to enhance interpretability.
Results:
Among 346 preterm infants, 154 (44.5%) experienced admission hypothermia. LASSO identified 11 predictors, including gestational age, birth weight, ambient temperature, transport time, inborn status, and preheated incubator use. In the validation cohort, AUCs ranged from 0.78 to 0.86, with logistic regression and artificial neural network demonstrating the highest discrimination (AUC = 0.86). Logistic regression showed favorable calibration and interpretability. SHAP analysis identified lower gestational age, lower birth weight, lower ambient temperature, and longer transport time as the strongest contributors to risk.
Conclusion:
Machine learning-based models using routinely available perinatal and environmental variables can effectively predict admission hypothermia in preterm infants. Logistic regression provided robust performance with strong interpretability, supporting its potential integration into early neonatal risk stratification and targeted thermal management strategies.
