Machine learning models for predicting seizure outcome after MR-guided laser interstitial thermal therapy in children

Area of Science:

• Neurology
• Medical Technology
• Machine Learning in Medicine

Background:

• MR-guided laser interstitial thermal therapy (MRgLITT) offers a safer alternative to open surgery for drug-resistant epilepsy but has variable seizure-free outcomes.
• Predictors of seizure freedom after MRgLITT are not well-established, hindering prognostication.

Purpose of the Study:

• To develop and validate machine learning models for predicting seizure freedom following MRgLITT in pediatric patients.
• To identify key clinical and procedural predictors of seizure freedom after MRgLITT.

Main Methods:

• A multicenter study involving 268 children with drug-resistant epilepsy treated with MRgLITT.
• Development of five machine learning algorithms using clinical data, diagnostic investigations, and ablation features.
• Feature selection methods were employed to identify significant predictors and develop parsimonious models.

Main Results:

• A gradient-boosting machine model achieved the highest predictive performance (AUC 0.67) on the testing cohort.
• Video-EEG concordance, lesion size, preoperative seizure frequency, and number of antiseizure medications were identified as significant predictors of seizure freedom.
• Parsimonious models based on selected features showed a slight improvement in performance.

Conclusions:

• Machine learning models can effectively predict seizure freedom after MRgLITT in children.
• Identifying key predictors like video-EEG concordance and lesion size aids in patient selection and prognostication for MRgLITT.