Decoding sequence auditory expectations for clinical diagnostic and prognostic assessment of prolonged disorders of consciousness

Abstract Objective. Electroencephalogram (EEG) features are important objective markers for diagnostic and prognostic evaluation of prolonged disorders of consciousness (DOC). However, task-based EEG paradigms are limited by mismatches between task demands and patients' residual awareness, as well as the limited individual assessment capacity of machine-learning-based detection frameworks. Approach. In this study, we proposed a lowdemand DOC detection strategy by decoding expectations of global regularities in sequence auditory stimulation using a modified local-global paradigm. Three single-trial classification frameworks using canonical correlation analysis, principal component analysis, and xDAWN for feature extraction were developed for individualized detection of global-regularity expectations. We further established awareness evaluation criteria based on single-trial classification outcomes and evaluated their diagnostic and prognostic effectiveness in a DOC experiment. Main results. Experiments in healthy participants demonstrated that the principal components of event-related potentials associated with global regularities were preserved under the proposed detection strategy. Compared with the original local-global paradigm, this strategy significantly improved single-trial classification performance for global effects by up to 15%. Electrophysiological analyses indicated that this improvement was driven by larger EEG response differences for global effects and more stable trial-to-trial neural states. In a cohort of 20 DOC patients, the proposed evaluation criteria achieved an individual diagnostic balanced accuracy of 68.8% (sensitivity = 50%; specificity = 87.5%), and a prognostic balanced accuracy of 60.5% (sensitivity = 50%; specificity = 71%). Significance. These findings demonstrate that decoding sequential auditory expectations enables effective low-