RESUMEN
Consciousness can be defined by two components: arousal (wakefulness) and awareness (subjective experience). However, neurophysiological consciousness metrics able to disentangle between these components have not been reported. Here, we propose an explainable consciousness indicator (ECI) using deep learning to disentangle the components of consciousness. We employ electroencephalographic (EEG) responses to transcranial magnetic stimulation under various conditions, including sleep (n = 6), general anesthesia (n = 16), and severe brain injury (n = 34). We also test our framework using resting-state EEG under general anesthesia (n = 15) and severe brain injury (n = 34). ECI simultaneously quantifies arousal and awareness under physiological, pharmacological, and pathological conditions. Particularly, ketamine-induced anesthesia and rapid eye movement sleep with low arousal and high awareness are clearly distinguished from other states. In addition, parietal regions appear most relevant for quantifying arousal and awareness. This indicator provides insights into the neural correlates of altered states of consciousness.
Asunto(s)
Lesiones Encefálicas , Aprendizaje Profundo , Anestesia General , Nivel de Alerta/fisiología , Estado de Conciencia/fisiología , Electroencefalografía , Humanos , Vigilia/fisiologíaRESUMEN
Neuroscience has generated a number of recent advances in the search for the neural correlates of consciousness, but these have yet to find valuable real-world applications. Electroencephalography under anesthesia provides a powerful experimental setup to identify electrophysiological signatures of altered states of consciousness, as well as a testbed for developing systems for automatic diagnosis and prognosis of awareness in clinical settings. In this work, we use deep convolutional neural networks to automatically differentiate sub-anesthetic states and depths of anesthesia, solely from one second of raw EEG signal. Our results with leave-one-participant-out-cross-validation show that behavioral measures, such as the Ramsay score, can be used to learn generalizable neural networks that reliably predict levels of unconsciousness in unseen transitional anesthetic states, as well as in unseen experimental setups and behaviors. Our findings highlight the potential of deep learning to detect progressive changes in anesthetic-induced unconsciousness with higher granularity than behavioral or pharmacological markers. This work has broader significance for identifying generalized patterns of brain activity that index states of consciousness.Clinical Relevance- In the United States alone, over 100,000 people receive general anesthesia every day, from which up to 1% is affected by unintended intraoperative awareness [1]. Despite this, brain-based monitoring of consciousness is not common in the clinic, and has had mixed success [2]. Given this context, our aim is to develop and explore an automated deep learning model that accurately predicts and interprets the depth and quality of anesthesia from the raw EEG signal.
Asunto(s)
Anestésicos , Propofol , Estado de Conciencia , Humanos , Redes Neurales de la Computación , Inconsciencia/inducido químicamenteRESUMEN
Objective: To obtain a CRS-R index suitable for diagnosis of patients with disorders of consciousness (DOC) and compare it to other CRS-R based scores to evaluate its potential for clinics and research. Design: We evaluated the diagnostic accuracy of several CRS-R-based scores in 124 patients with DOC. ROC analysis of the CRS-R total score, the Rasch-based CRS-R score, CRS-R-MS and the CRS-R index evaluated the diagnostic accuracy for patients with the Unresponsive Wakefulness Syndrome (UWS) and Minimally Conscious State (MCS). Correlations were computed between the CRS-R-MS, CRS-R index, the Rasch-based score and the CRS-R total score. Results: Both the CRS-R-MS and CRS-R index ranged from 0 to 100, with a cut-off of 8.315 that perfectly distinguishes between patients with UWS and MCS. The CRS-R total score and Rasch-based score did not provide a cut-off score for patients with UWS and MCS. The proposed CRS-R index correlated with the CRS-R total score, Rasch-based score and the CRS-R-MS. Conclusion: The CRS-R index is reliable to diagnose patients with UWS and MCS and can be used in compliance with the CRS-R scoring guidelines. The obtained index offers the opportunity to improve the interpretation of clinical assessment and can be used in (longitudinal) research protocols. Abbreviations: CRS-R: Coma Recovery Scale-Revised; CRS-R-MS: Coma Recovery Scale-Revised Modified Score; DOC: Disorders of Consciousness; MCS: Minimally Conscious State; UWS: Unresponsive Wakefulness Syndrome; ROC: Receiver Operating Characteristic; AUC: Area Under the Curve; IRT: Item Response Theory.