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

Q3 Medicine

Qatar Medical Journal Pub Date : 2025-03-13 eCollection Date: 2025-01-01 DOI:10.5339/qmj.2025.15

Maher Al Rifai, Sultan Jarrar, Mohammad Barbarawi, Mohammad Jamous, Suleiman Daoud, Amer Jaradat, Owais Ghammaz, Bashar Hatem Abulsebaa, Qutaiba Alsumadi, Tala Ali Shibli, Ahmad Osamah Alqudah

{"title":"Machine learning-based assessment of seizure risk predictors in myelomeningocele patients: A single-center retrospective cohort study.","authors":"Maher Al Rifai, Sultan Jarrar, Mohammad Barbarawi, Mohammad Jamous, Suleiman Daoud, Amer Jaradat, Owais Ghammaz, Bashar Hatem Abulsebaa, Qutaiba Alsumadi, Tala Ali Shibli, Ahmad Osamah Alqudah","doi":"10.5339/qmj.2025.15","DOIUrl":null,"url":null,"abstract":"Background: Myelomeningocele (MMC) is a severe congenital malformation of the CNS (central nervous system) that often leads to seizures due to factors such as shunt complications and hydrocephalus. This study aims to develop a machine learning model to predict the likelihood of seizures in MMC patients by analyzing various predictors.Methods: This retrospective study involved 103 MMC patients. Factors such as demographics, MMC location, shunt history, and imaging were analyzed using the random forest classifier, the support vector classifier, and logistic regression. Model performance was assessed through bootstrap estimates, cross-validation, classification reports, and area under the curve (AUC).Results: Of the evaluated patients, 11 experienced seizures. The key influencing factors included gestational age, sacral location, hydrocephalus, shunt history, and corpus callosum dysgenesis. Machine learning (ML) models predicted seizure risk with an accuracy of 86-92% and an AUC ranging from 0.764 to 0.865. Significant predictors were imaging findings, shunt infection history, and gestational age.Conclusion: ML models effectively predict seizure risk in MMC patients, with certain variables showing strong associations and significant impact.","PeriodicalId":53667,"journal":{"name":"Qatar Medical Journal","volume":"2025 1","pages":"15"},"PeriodicalIF":0.0000,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12093402/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Qatar Medical Journal","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5339/qmj.2025.15","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q3","JCRName":"Medicine","Score":null,"Total":0}

引用次数: 0

Abstract

Background: Myelomeningocele (MMC) is a severe congenital malformation of the CNS (central nervous system) that often leads to seizures due to factors such as shunt complications and hydrocephalus. This study aims to develop a machine learning model to predict the likelihood of seizures in MMC patients by analyzing various predictors.

Methods: This retrospective study involved 103 MMC patients. Factors such as demographics, MMC location, shunt history, and imaging were analyzed using the random forest classifier, the support vector classifier, and logistic regression. Model performance was assessed through bootstrap estimates, cross-validation, classification reports, and area under the curve (AUC).

Results: Of the evaluated patients, 11 experienced seizures. The key influencing factors included gestational age, sacral location, hydrocephalus, shunt history, and corpus callosum dysgenesis. Machine learning (ML) models predicted seizure risk with an accuracy of 86-92% and an AUC ranging from 0.764 to 0.865. Significant predictors were imaging findings, shunt infection history, and gestational age.

Conclusion: ML models effectively predict seizure risk in MMC patients, with certain variables showing strong associations and significant impact.

查看原文本刊更多论文

基于机器学习的脊髓脊膜膨出患者癫痫发作风险预测因素评估：单中心回顾性队列研究。

背景：髓脊膜膨出（MMC）是一种严重的中枢神经系统先天性畸形，常因分流并发症和脑积水等因素导致癫痫发作。本研究旨在开发一种机器学习模型，通过分析各种预测因素来预测MMC患者癫痫发作的可能性。方法：对103例MMC患者进行回顾性研究。使用随机森林分类器、支持向量分类器和逻辑回归分析人口统计学、MMC位置、分流历史和影像学等因素。通过自举估计、交叉验证、分类报告和曲线下面积（AUC）来评估模型的性能。结果：11例患者发生癫痫发作。主要影响因素包括胎龄、骶骨位置、脑积水、分流史和胼胝体发育不良。机器学习（ML）模型预测癫痫发作风险的准确率为86-92%，AUC范围为0.764至0.865。重要的预测因素是影像学表现、分流感染史和胎龄。结论：ML模型能有效预测MMC患者癫痫发作风险，部分变量相关性强，影响显著。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊