EEG functional connectivity contributes to outcome prediction of postanoxic coma

To investigate the additional value of EEG functional connectivity features, in addition to non-coupling for outcome prediction comatose patients after cardiac arrest. Prospective, multicenter cohort study. Coherence, phase locking value, and mutual information were calculated 19-channel EEGs at 12 h, 24 h 48 Three sets machine learning classification models trained validated with connectivity, a combination these. Neurological was assessed six months categorized as “good” (Cerebral Performance Category [CPC] 1–2) or “poor” (CPC 3–5). We included 594 (46% good outcome). A sensitivity 51% (95% CI: 34–56%) 100% specificity predicting poor achieved by best connectivity-based classifier arrest, while non-coupling-based model reached 32% (0–54%) using data h. Combination both features 73% (50–77%) specificity. Functional measures improve based postanoxic coma. derived from early hold potential coma