Martín Carrasco-Gómez1, Hanneke M Keijzer2, Barry J Ruijter3, Ricardo Bruña4, Marleen C Tjepkema-Cloostermans5, Jeannette Hofmeijer6, Michel J A M van Putten5. 1. Laboratory of Cognitive and Computational Neuroscience (LNCyC), Centre for Biomedical Technology, Universidad Politécnica de Madrid, Spain; Biomedical Research Networking Center in Bioengineering Biomaterials and Nanomedicine (CIBER-BBN), Madrid, Spain. Electronic address: martin.carrasco@ctb.upm.es. 2. Department of Neurology, Rijnstate Hospital, Arnhem, the Netherlands; Department of Neurology, Donders Institute for Brain, Cognition, and Behaviour, Radboud University Medical Centre, Nijmegen, the Netherlands. 3. Clinical Neurophysiology (CNPH), TechMed Centre, University of Twente, the Netherlands. 4. Laboratory of Cognitive and Computational Neuroscience (LNCyC), Centre for Biomedical Technology, Universidad Politécnica de Madrid, Spain; Biomedical Research Networking Center in Bioengineering Biomaterials and Nanomedicine (CIBER-BBN), Madrid, Spain. 5. Clinical Neurophysiology (CNPH), TechMed Centre, University of Twente, the Netherlands; Neurocentrum, Medisch SpectrumTwente, Enschede, the Netherlands. 6. Clinical Neurophysiology (CNPH), TechMed Centre, University of Twente, the Netherlands; Department of Neurology, Rijnstate Hospital, Arnhem, the Netherlands.
Abstract
OBJECTIVE: To investigate the additional value of EEG functional connectivity features, in addition to non-coupling EEG features, for outcome prediction of comatose patients after cardiac arrest. METHODS: Prospective, multicenter cohort study. Coherence, phase locking value, and mutual information were calculated in 19-channel EEGs at 12 h, 24 h and 48 h after cardiac arrest. Three sets of machine learning classification models were trained and validated with functional connectivity, EEG non-coupling features, and a combination of these. Neurological outcome was assessed at six months and categorized as "good" (Cerebral Performance Category [CPC] 1-2) or "poor" (CPC 3-5). RESULTS: We included 594 patients (46% good outcome). A sensitivity of 51% (95% CI: 34-56%) at 100% specificity in predicting poor outcome was achieved by the best functional connectivity-based classifier at 12 h after cardiac arrest, while the best non-coupling-based model reached a sensitivity of 32% (0-54%) at 100% specificity using data at 12 h and 48 h. Combination of both sets of features achieved a sensitivity of 73% (50-77%) at 100% specificity. CONCLUSION: Functional connectivity measures improve EEG based prediction models for poor outcome of postanoxic coma. SIGNIFICANCE: Functional connectivity features derived from early EEG hold potential to improve outcome prediction of coma after cardiac arrest.
OBJECTIVE: To investigate the additional value of EEG functional connectivity features, in addition to non-coupling EEG features, for outcome prediction of comatosepatients after cardiac arrest. METHODS: Prospective, multicenter cohort study. Coherence, phase locking value, and mutual information were calculated in 19-channel EEGs at 12 h, 24 h and 48 h after cardiac arrest. Three sets of machine learning classification models were trained and validated with functional connectivity, EEG non-coupling features, and a combination of these. Neurological outcome was assessed at six months and categorized as "good" (Cerebral Performance Category [CPC] 1-2) or "poor" (CPC 3-5). RESULTS: We included 594 patients (46% good outcome). A sensitivity of 51% (95% CI: 34-56%) at 100% specificity in predicting poor outcome was achieved by the best functional connectivity-based classifier at 12 h after cardiac arrest, while the best non-coupling-based model reached a sensitivity of 32% (0-54%) at 100% specificity using data at 12 h and 48 h. Combination of both sets of features achieved a sensitivity of 73% (50-77%) at 100% specificity. CONCLUSION: Functional connectivity measures improve EEG based prediction models for poor outcome of postanoxic coma. SIGNIFICANCE: Functional connectivity features derived from early EEG hold potential to improve outcome prediction of coma after cardiac arrest.