Related Experiment Video
Updated: Jul 14, 2026
A Ferret Model of Inflammation-sensitized Late Preterm Hypoxic-ischemic Brain Injury
Published on: November 19, 2019
Development and validation of an explainable model of brain injury in premature infants: A prospective cohort study
Zhijie He1, Ruiqi Zhang2, Pengfei Qu3
1Northwest Women's and Children's Hospital, No. 1616 Yanxiang Road, Xi'an, 710061, China; College of Life Sciences, Northwest A&F University, Yangling, 712100, China.
Insights
This study developed PBIPred, a machine learning model for early preterm brain injury detection. It identifies key risk factors like mechanical ventilation and anemia, aiding in timely diagnosis and management of this critical condition.
Area of Science:
- Neonatal Medicine
- Computational Biology
- Medical Informatics
Background:
- Preterm brain injury (PBI) is a significant complication in preterm infants, causing severe neurological deficits.
- Early detection of PBI is crucial but challenging due to non-specific early symptoms, leading to potential misdiagnosis.
- Currently, no specific treatments exist for PBI, emphasizing the need for early identification and intervention.
Purpose of the Study:
- To develop and validate an interpretable machine learning (ML) model for the early detection of PBI in preterm infants.
- To identify patient-wide and individual risk factors associated with PBI.
- To create accessible tools for clinical diagnosis and prediction of PBI.
Main Methods:
- Utilized a cohort of 650 preterm infants' medical records (2019-2021) with PBI identified via cranial MRI.
- Employed 14 ML models with 10-fold cross-validation and SHAP for interpretation, followed by feature selection.
- Validated the final model on an independent test set to assess predictive performance.
Main Results:
- The CatBoost model, refined into PBIPred (Preterm Brain Injury Predictor), achieved an AUC of 0.8229 on the independent test set.
- PBIPred was constructed using seven key features, demonstrating strong predictive accuracy for PBI.
- Identified positive risk factors for PBI: mechanical ventilation, weight, anemia of prematurity, respiratory distress syndrome, albumin, and white blood cell count.
Conclusions:
- PBIPred offers a reliable and interpretable ML-based approach for early PBI detection.
- The identified risk factors provide valuable insights for clinical risk assessment and management strategies.
- Developed freely accessible webserver and tools (PBIPred) for clinical application and research.
Background:
Preterm brain injury (PBI) is a prevalent complication in preterm infants, leading to the destruction of critical structural and functional brain connections and placing a significant burden on families. The timely detection of PBI is of paramount importance for the prevention and treatment of the condition. However, the absence of specific clinical manifestations in the early stages of PBI renders it susceptible to misdiagnosis and missed diagnoses. Moreover, once it occurs, there is no specific treatment available. The aim of this study was to develop and validate a machine learning (ML) based interpretable model for the early detection of PBI, as well as the assessment of patient-wide and individual risk factors for this disease.
Methods:
This study utilized a cohort of premature infants provided by Northwest Women's and Children's Hospital in China, comprising medical records of 650 premature infants, spanning from 2019 to 2021. PBI were identified based on cranial magnetic resonance imaging (MRI). Fourteen machine learning models were employed with stratified 10-fold cross-validation method used to evaluate model performance. The Shapley Additive Explanations (SHAP) method was applied for model interpretation. Feature selection methods were used to determine the final model which was validated on the independent test set. Subsequently, risk factors for the entire cohort and individual patients were assessed.
Results:
Among the fourteen machine learning models, the CatBoost model demonstrated the best discriminative ability. Following feature selection, the final model was constructed using seven features, designated as PBIPred (Preterm Brain Injury Predictor). PBIPred exhibited strong performance in both 10-fold cross-validation and independent test set (AUC = 0.8229) for accurately predicting PBI. The screening for risk factors in the cohort and individuals identified the following variables as positive risk factors for PBI: Mechanical ventilation (MV), Weight, Anemia of prematurity (AOP), Respiratory distress syndrome (RDS), Albumin (ALB), and White blood cell (WBC).
Availability And Implementation:
The PBIPred webserver and PBIPred tool were developed for clinical diagnosis and large-scale local medical record data prediction. They can be accessed freely at http://pbipred.liaolab.net and https://github.com/chikit2077/PBIPred, respectively.
