Reliability of visual review of intracranial electroencephalogram in identifying the seizure onset zone: A systematic review and implications for the accuracy of automated methods

Abstract

Visual review of intracranial electroencephalography (iEEG) is often an essential component for defining the zone of resection for epilepsy surgery. Unsupervised approaches using machine and deep learning are being employed to identify seizure onset zones (SOZs). This prompts a more comprehensive understanding of the reliability of visual review as a reference standard. We sought to summarize existing evidence on the reliability of visual review of iEEG in defining the SOZ for patients undergoing surgical workup and understand its implications for algorithm accuracy for SOZ prediction. We performed a systematic literature review on the reliability of determining the SOZ by visual inspection of iEEG in accordance with best practices. Searches included MEDLINE, Embase, Cochrane Library, and Web of Science on May 8, 2022. We included studies with a quantitative reliability assessment within or between observers. Risk of bias assessment was performed with QUADAS‐2. A model was developed to estimate the effect of Cohen kappa on the maximum possible accuracy for any algorithm detecting the SOZ. Two thousand three hundred thirty‐eight articles were identified and evaluated, of which one met inclusion criteria. This study assessed reliability between two reviewers for 10 patients with temporal lobe epilepsy and found a kappa of .80. These limited data were used to model the maximum accuracy of automated methods. For a hypothetical algorithm that is 100% accurate to the ground truth, the maximum accuracy modeled with a Cohen kappa of .8 ranged from .60 to .85 (F‐2). The reliability of reviewing iEEG to localize the SOZ has been evaluated only in a small sample of patients with methodologic limitations. The ability of any algorithm to estimate the SOZ is notably limited by the reliability of iEEG interpretation. We acknowledge practical limitations of rigorous reliability analysis, and we propose design characteristics and study questions to further investigate reliability.

Lesion detection in epilepsy surgery: Lessons from a prospective evaluation of a machine learning algorithm

“…The blinded assessor (RT) was a clinical neurophysiologist with significant SEEG experience who was not involved in SEEG planning or interpretation for any of the included patients. Given the lack of data to support high interrater reliability in the visual assessment of SEEG data, 16 the assessment specifically asked two questions: (1) was a focal SOZ identified? and (2) if so, were the additional electrodes involved in this SOZ?…”

Physiological and pathological neuronal connectivity in the living human brain based on intracranial EEG signals: the current state of research

“…iEEG-based connectivity assessment has a promising application in mapping epileptogenic networks. Nowadays, the identification of the SOZ during presurgical evaluation is a manual, time-consuming process which operates with large amounts of disparate neural data and has a basically unexplored reliability (Flanary et al, 2023). Although a number of automated approaches using machine and deep learning have been applied to Frontiers in Network Physiology frontiersin.org identify SOZ, the visual iEEG reading by epileptologists remains the gold diagnostic standard worldwide.…”

Development of a Seizure Matching System for Clinical Decision Making in Epilepsy Surgery

“…However, similar studies on pre-surgical planning in epilepsy surgery remain limited. [15][16][17] We assessed the expert IRA in determining if SEEG seizures gathered from different patients are indeed similar and which features contributed to this similarity. Based on evidence from scalp EEG, 11,12 we hypothesized that there exists a moderate agreement for seizure similarity across epileptologists and that a generalizable automated seizure matching system can therefore be developed.…”