Translate 
Abstract
Accurate identification of seizure onset zones (SOZ) is essential for the surgical treatment of epilepsy. This narrative review examines recent advances in machine learning approaches for SOZ localization using intracranial electroencephalography (iEEG) data. Existing studies are analyzed while addressing key questions: What machine learning techniques are used for SOZ localization? How effective are these methods? What are the limitations, and what solutions can drive further progress in the field? This narrative review examined peer-reviewed studies that employed machine learning techniques for SOZ localization using iEEG data. The selected studies were analyzed to identify trends in machine learning applications, performance metrics, benefits, and challenges associated with SOZ identification. The review highlights the increasing adoption of machine learning for SOZ localization, mostly with supervised approaches. Particularly support vector machine (SVM) using high frequency oscillation (HFO) biomarker feature being the most prevalent. High accuracy and sensitivity, especially in studies with smaller sample sizes are reported. However, patient-wise validation reveals limited generalizability. Additionally, ambiguity in SOZ definition and the scarcity of open-access iEEG datasets continue to hinder progress and reproducibility in the field. Machine learning offers significant potential for advancing SOZ localization. Development of more robust algorithms, integration of multimodal data, and greater model interpretability, can improve model reliability, ensure consistency, and enhance real-world applicability, thereby transforming the future of SOZ localization.
Highlights
Epilepsy is a neurological disorder characterized by recur‐ rent, unprovoked seizures resulting from abnormal electri‐ cal activity in the brain [1]
Neurologists identify seizure onset zone (SOZ) by visually assessing electroencephalography (EEG) [9], supplemented by the findings from seizure symptoms recorded during long-term video EEG monitoring [12] and from neuroimag‐ ing modalities such as magnetic resonance imaging (MRI) [14], positron emission tomography (PET) [15], single‐pho‐ ton emission computed tomography (SPECT) [15] and magnetoencephalography (MEG) [13]
High-resolution, noise-free data significantly enhances the precision of SOZ boundary localization. intracranial EEG (iEEG) is a form of electroencephalography in which electrodes are positioned directly on or within the cortex to capture electrical activ‐ ity [28]
Summary
Epilepsy is a neurological disorder characterized by recur‐ rent, unprovoked seizures resulting from abnormal electri‐ cal activity in the brain [1]. Neurologists identify SOZ by visually assessing electroencephalography (EEG) [9], supplemented by the findings from seizure symptoms recorded during long-term video EEG monitoring [12] and from neuroimag‐ ing modalities such as magnetic resonance imaging (MRI) [14], positron emission tomography (PET) [15], single‐pho‐ ton emission computed tomography (SPECT) [15] and magnetoencephalography (MEG) [13] Among these clini‐ cal methods, intracranial EEG (iEEG) is considered the gold standard for guiding surgical planning in patients [5, 16]. Unlike traditional EEG, which collects signals via the skull, iEEG gives higher spatial and temporal resolution data with minimal interfer‐ ence, making it effective, especially in pinpointing specific brain regions linked to neurological problems (Fig. 1). For this reason, when it comes to locating SOZ, iEEG has been considered as an indispensable source of data in certain situ‐ ations [5, 16]
Sign-in/Register to view highlights & summary 
Paper version not known (
Free)
Published Version
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
