Sensitivity and specificity of the Salzburg EEG criteria for nonconvulsive status epilepticus.

OBJECTIVE: The Salzburg EEG criteria for nonconvulsive status epilepticus (NCSE) have been proposed as consensus criteria for NCSE. We aimed to perform an independent study of their diagnostic accuracy. METHODS: A prospective study was carried out at Oslo University Hospital, including all consecutive patients ≥15 years old who were referred for an EEG with an explicit or implicit question of NCSE from February 2020 to February 2022. Two independent EEG readers scored the included EEGs according to the Salzburg criteria and blinded to the clinical data. The reference standard was defined as the clinical diagnosis the patient received based on all available clinical and paraclinical data. Diagnostic accuracy in identifying "certain/possible NCSE" was assessed by calculating sensitivity, specificity, positive predictive value, and negative predictive value with their 95% confidence intervals. RESULTS: In total, 469 patients/EEGs were included in the study. The prevalence of NCSE according to the reference standard was 11% (n = 53). The criteria showed a sensitivity of 94% (95% CI: 92-96%), a specificity of 77% (95% CI: 73-81%), a positive predictive value of 34% (95% CI: 30-39%), and a negative predictive value of 99% (95% CI: 98-100%). False positives for "certain NCSE" (n = 16) included many serial seizures and stimulus-induced rhythmic and periodic discharges (SIRPIDs), as well as a focal cortical dysplasia. False positives for "possible NCSE" (n = 79) were mainly represented by different encephalopathies and postictality. INTERPRETATION: The low specificity of the Salzburg criteria calls for refinement before implementation into daily clinical practice.

Automated Interpretation of Clinical Electroencephalograms Using Artificial Intelligence.

Importance: Electroencephalograms (EEGs) are a fundamental evaluation in neurology but require special expertise unavailable in many regions of the world. Artificial intelligence (AI) has a potential for addressing these unmet needs. Previous AI models address only limited aspects of EEG interpretation such as distinguishing abnormal from normal or identifying epileptiform activity. A comprehensive, fully automated interpretation of routine EEG based on AI suitable for clinical practice is needed. Objective: To develop and validate an AI model (Standardized Computer-based Organized Reporting of EEG-Artificial Intelligence [SCORE-AI]) with the ability to distinguish abnormal from normal EEG recordings and to classify abnormal EEG recordings into categories relevant for clinical decision-making: epileptiform-focal, epileptiform-generalized, nonepileptiform-focal, and nonepileptiform-diffuse. Design, Setting, and Participants: In this multicenter diagnostic accuracy study, a convolutional neural network model, SCORE-AI, was developed and validated using EEGs recorded between 2014 and 2020. Data were analyzed from January 17, 2022, until November 14, 2022. A total of 30 493 recordings of patients referred for EEG were included into the development data set annotated by 17 experts. Patients aged more than 3 months and not critically ill were eligible. The SCORE-AI was validated using 3 independent test data sets: a multicenter data set of 100 representative EEGs evaluated by 11 experts, a single-center data set of 9785 EEGs evaluated by 14 experts, and for benchmarking with previously published AI models, a data set of 60 EEGs with external reference standard. No patients who met eligibility criteria were excluded. Main Outcomes and Measures: Diagnostic accuracy, sensitivity, and specificity compared with the experts and the external reference standard of patients' habitual clinical episodes obtained during video-EEG recording. Results: The characteristics of the EEG data sets include development data set (N = 30 493; 14 980 men; median age, 25.3 years [95% CI, 1.3-76.2 years]), multicenter test data set (N = 100; 61 men, median age, 25.8 years [95% CI, 4.1-85.5 years]), single-center test data set (N = 9785; 5168 men; median age, 35.4 years [95% CI, 0.6-87.4 years]), and test data set with external reference standard (N = 60; 27 men; median age, 36 years [95% CI, 3-75 years]). The SCORE-AI achieved high accuracy, with an area under the receiver operating characteristic curve between 0.89 and 0.96 for the different categories of EEG abnormalities, and performance similar to human experts. Benchmarking against 3 previously published AI models was limited to comparing detection of epileptiform abnormalities. The accuracy of SCORE-AI (88.3%; 95% CI, 79.2%-94.9%) was significantly higher than the 3 previously published models (P < .001) and similar to human experts. Conclusions and Relevance: In this study, SCORE-AI achieved human expert level performance in fully automated interpretation of routine EEGs. Application of SCORE-AI may improve diagnosis and patient care in underserved areas and improve efficiency and consistency in specialized epilepsy centers.