Machine Learning-Based Prediction of Speech Arrest During Direct Cortical Stimulation Mapping

2025-09-10

AI Summary

This study addresses the invasiveness and time-consuming nature of electrocortical stimulation mapping (ESM) for preoperative language localization. We propose a machine learning–based approach to predict speech arrest during intraoperative stimulation, enabling noninvasive, precise presurgical mapping of language areas. Our method integrates intracranial EEG (iEEG)–derived local neural activity, anatomical region labels, and multiband functional connectivity features. A novel nonlinear ensemble model—comprising RBF-kernel SVM, multilayer perceptron (MLP), and histogram-based encoding scoring—is developed to jointly model region- and network-level features for the first time. Validated on independent subjects, the framework achieves an ROC-AUC of 0.87 and PR-AUC of 0.57, significantly outperforming single-feature baselines. The interpretable, subject-specific predictions support individualized language risk assessment in brain tumor and epilepsy surgery, advancing functional neurosurgery toward greater precision and intelligence.

Technology Category

• Machine Learning: Ensemble Methods
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Web Mining and Content Analysis: Machine learning and data science for the Web
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Identifying cortical regions critical for speech is essential for safe brain surgery in or near language areas. While Electrical Stimulation Mapping (ESM) remains the clinical gold standard, it is invasive and time-consuming. To address this, we analyzed intracranial electrocorticographic (ECoG) data from 16 participants performing speech tasks and developed machine learning models to directly predict if the brain region underneath each ECoG electrode is critical. Ground truth labels indicating speech arrest were derived independently from Electrical Stimulation Mapping (ESM) and used to train classification models. Our framework integrates neural activity signals, anatomical region labels, and functional connectivity features to capture both local activity and network-level dynamics. We found that models combining region and connectivity features matched the performance of the full feature set, and outperformed models using either type alone. To classify each electrode, trial-level predictions were aggregated using an MLP applied to histogram-encoded scores. Our best-performing model, a trial-level RBF-kernel Support Vector Machine together with MLP-based aggregation, achieved strong accuracy on held-out participants (ROC-AUC: 0.87, PR-AUC: 0.57). These findings highlight the value of combining spatial and network information with non-linear modeling to improve functional mapping in presurgical evaluation.

Problem

• Predicting speech arrest during brain stimulation mapping
• Identifying critical language areas non-invasively using ECoG
• Combining neural signals and connectivity for surgical planning

Innovation

• Machine learning models predict speech arrest from ECoG data
• Combines neural activity, anatomical regions, and connectivity features
• Uses SVM with MLP aggregation for high classification accuracy