Machine learning driven modeling of synergistic perinatal risk profiles in early onset pediatric cerebral palsy
- 1College of Health & Life Sciences (CHLS), Hamad Bin Khalifa University (HBKU), Doha, 34110 Qatar
- 2Sidra Medical and Research Center, Pediatric Rehabilitation Medicine, Doha, 26999 Qatar
- 3College of Science and Engineering (CSE), Hamad Bin Khalifa University (HBKU), Doha, 34110 Qatar
Abstract
AIM: To develop and evaluate machine learning (ML) models for early cerebral palsy (CP) prediction and identify synergistic perinatal risk factors in a pediatric population.
Method: We conducted a retrospective case–control study using demographic, perinatal, and postnatal clinical data collected at Sidra Medicine, Qatar. Four ML models- Random Forest (RF), XGBoost, Support Vector Machine (SVM), and a feedforward neural network (FFN) were trained using clinically relevant features. Model performance was assessed using precision, recall, area under the curve (AUC), F1-score, and SHAP-based interpretability. A multidimensional interaction framework was used to evaluate cumulative risk across 16 subgroups.
Results: All ML models exhibited high predictive accuracy (ROC-AUC: 0.98–0.99, and PR-AUC: 0.97–0.98), with four key factors: low birth weight (LBW), premature birth, neonatal intensive care unit (NICU) admission, and multiple pregnancies. Infants exposed to all four factors demonstrated a 93.15% incidence of CP (OR = 1382.67; p < 0.0001). A clear dose-response gradient was observed across exposure subgroups. SHAP analysis confirmed consistent cross-model importance of LBW, very preterm birth, NICU admission, and multigravidity. Cross-validation confirmed model robustness, and severity analysis identified NICU admission and birth weight as independent predictors of higher GMFCS classification.
Conclusion: Four ML models achieved high predictive accuracy (ROC-AUC 0.98–0.99) for CP risk stratification in a Middle Eastern pediatric cohort, with LBW, very preterm birth, NICU admission, and multigravidity as the most consistent cross-model predictors. The synergistic interaction of these exposures – evidenced by a 93.15% CP incidence in the highest-risk subgroup – supports a paradigm shift from single-factor screening to exposure-weighted, ML-driven neonatal surveillance. These findings provide a data-driven foundation for early risk stratification and targeted intervention planning in high-risk neonatal population.
Supplementary Information: The online version contains supplementary material available at https://doi.org/10.1186/s12911-026-03710-y.
Related
- Comparative and synergistic effects of digital devices and Child Life services in pediatric clinical practice: a systematic review
- Compartment-specific soluble immune profiles associated with preterm birth, perinatal death, and low birthweight in pregnant individuals living with HIV
- Bidirectional Synergistic Interaction Between Influenza Virus and SARS‐CoV‐2 in the Postpandemic Era: A Modeling Study
- Modeling perinatal brain injury with human brain organoids: from pathophysiology to treatment development.
- Paramedic attitudinal profiles regarding pediatric pain management: A latent class analysis in a standardized emergency medical services system
BibTeX
@article{ahammad2026machine,
title = {{Machine learning driven modeling of synergistic perinatal risk profiles in early onset pediatric cerebral palsy}},
author = {Foysal Ahammad and Munira Aden and Ayesha Banu and Muhammad Marwan and Sadam Hussain and Safa Salim and Adnan Mohammed and Tanvir Alam and Lisa Thornton and Farhan Mohammad},
journal = {BMC Medical Informatics and Decision Making},
year = {2026},
month = jul,
doi = {10.1186/s12911-026-03710-y},
url = {https://doi.org/10.1186/s12911-026-03710-y},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Machine learning driven modeling of synergistic perinatal risk profiles in early onset pediatric cerebral palsy
AU - Foysal Ahammad
AU - Munira Aden
AU - Ayesha Banu
AU - Muhammad Marwan
AU - Sadam Hussain
AU - Safa Salim
AU - Adnan Mohammed
AU - Tanvir Alam
AU - Lisa Thornton
AU - Farhan Mohammad
PY - 2026
DA - 2026/07/01
JO - BMC Medical Informatics and Decision Making
DO - 10.1186/s12911-026-03710-y
UR - https://doi.org/10.1186/s12911-026-03710-y
AB - AIM: To develop and evaluate machine learning (ML) models for early cerebral palsy (CP) prediction and identify synergistic perinatal risk factors in a pediatric population. Method: We conducted a retrospective case–control study using demographic, perinatal, and postnatal clinical data collected at Sidra Medicine, Qatar. Four ML models- Random Forest (RF), XGBoost, Support Vector Machine (SVM), and a feedforward neural network (FFN) were trained using clinically relevant features. Model performance was assessed using precision, recall, area under the curve (AUC), F1-score, and SHAP-based interpretability. A multidimensional interaction framework was used to evaluate cumulative risk across 16 subgroups. Results: All ML models exhibited high predictive accuracy (ROC-AUC: 0.98–0.99, and PR-AUC: 0.97–0.98), with four key factors: low birth weight (LBW), premature birth, neonatal intensive care unit (NICU) admission, and multiple pregnancies. Infants exposed to all four factors demonstrated a 93.15% incidence of CP (OR = 1382.67; p < 0.0001). A clear dose-response gradient was observed across exposure subgroups. SHAP analysis confirmed consistent cross-model importance of LBW, very preterm birth, NICU admission, and multigravidity. Cross-validation confirmed model robustness, and severity analysis identified NICU admission and birth weight as independent predictors of higher GMFCS classification. Conclusion: Four ML models achieved high predictive accuracy (ROC-AUC 0.98–0.99) for CP risk stratification in a Middle Eastern pediatric cohort, with LBW, very preterm birth, NICU admission, and multigravidity as the most consistent cross-model predictors. The synergistic interaction of these exposures – evidenced by a 93.15% CP incidence in the highest-risk subgroup – supports a paradigm shift from single-factor screening to exposure-weighted, ML-driven neonatal surveillance. These findings provide a data-driven foundation for early risk stratification and targeted intervention planning in high-risk neonatal population. Supplementary Information: The online version contains supplementary material available at https://doi.org/10.1186/s12911-026-03710-y.
SN - 1472-6947
ER -