Machine learning-based assessment of seizure risk predictors in myelomeningocele patients: A single-center retrospective cohort study

• DOI: 10.5339/qmj.2025.15
• Publication Date: 2025-04-21T07:30:26Z
• Authors: Maher Al Rifai; Sultan Jarrar; Mohammad Barbarawi; Mohammad Jamous; Suleiman Daoud; Amer Jaradat; Owais Ghammaz; Bashar Hatem Abul...; Qutaiba Alsumadi; Tala Ali Shibli; Ahmad Osamah Alqudah
• Keywords: Single Center; Center (category theory)

Background: Myelomeningocele (MMC) is a severe congenital malformation of the CNS (central nervous system) that often leads to seizures due factors such as shunt complications and hydrocephalus. This study aims develop machine learning model predict likelihood in MMC patients by analyzing various predictors. Methods: retrospective involved 103 patients. Factors demographics, location, history, imaging were analyzed using random forest classifier, support vector logistic regression. Model performance was assessed through bootstrap estimates, cross-validation, classification reports, area under curve (AUC). Results: Of evaluated patients, 11 experienced seizures. The key influencing included gestational age, sacral hydrocephalus, corpus callosum dysgenesis. Machine (ML) models predicted seizure risk with an accuracy 86–92% AUC ranging from 0.764 0.865. Significant predictors findings, infection age. Conclusion: ML effectively certain variables showing strong associations significant impact.