Search

Assessing the integrity of neural functions in coma after cardiac arrest remains an open challenge. Prognostication of coma outcome relies mainly on visual expert scoring of physiological signals, which is prone to subjectivity and leaves a considerable number of patients in a ‘grey zone’, with uncertain prognosis. Quantitative analysis of EEG responses to auditory stimuli can provide a window into neural functions in coma and information about patients’ chances of awakening. However, responses to standardized auditory stimulation are far from being used in a clinical routine due to heterogeneous and cumbersome protocols. Here, we hypothesize that convolutional neural networks can assist in extracting interpretable patterns of EEG responses to auditory stimuli during the first day of coma that are predictive of patients’ chances of awakening and survival at 3 months. We used convolutional neural networks (CNNs) to model single-trial EEG responses to auditory stimuli in the first day of coma, under standardized sedation and targeted temperature management, in a multicentre and multiprotocol patient cohort and predict outcome at 3 months. The use of CNNs resulted in a positive predictive power for predicting awakening of 0.83 ± 0.04 and 0.81 ± 0.06 and an area under the curve in predicting outcome of 0.69 ± 0.05 and 0.70 ± 0.05, for patients undergoing therapeutic hypothermia and normothermia, respectively. These results also persisted in a subset of patients that were in a clinical ‘grey zone’. The network’s confidence in predicting outcome was based on interpretable features: it strongly correlated to the neural synchrony and complexity of EEG responses and was modulated by independent clinical evaluations, such as the EEG reactivity, background burst-suppression or motor responses. Our results highlight the strong potential of interpretable deep learning algorithms in combination with auditory stimulation to improve prognostication of coma outcome.

Both the brain and the bodily activity shape how we react to the external world (Azzalini et al., 2019). As an example, cardio-audio synchrony is the phenomenon by which heart and brain responses depend on the synchronization of auditory stimuli with the cardiac rhythm (Pfeiffer & De Lucia, 2017 ; Banellis & Cruse, 2020). However, the mechanisms supporting this kind of synchronization remain debated (Palmer & Demos, 2022): surprise response proposes that bodily signals are reacting to deviations from sensory predictions, active inference proposes that bodily rhythms are regulated to reduce the mismatch between sensory and bodily signals and dynamical coupling argues that bodily rhythms depend on the coupling between oscillators at the brain and cardiac level (Palmer & Demos, 2022). Because these different mechanistic interpretations of the phenomenon make different predictions that could not be resolved in the literature so far, we designed a protocol to test which mechanism underlies cardio-audio synchrony. To do so, we aim first to replicate the fact that physiological responses depend on the synchronization between external sound and cardiac activity and will then directly compare predictions of theories by manipulating: - The type of deviations - The expectancy of deviations Surprise response proposes that bodily signals are reacting to deviations from sensory predictions, active inference proposes that bodily rhythms are regulated to reduce the mismatch between sensory and bodily signals and dynamical coupling argues that bodily rhythms depend on the coupling between oscillators at the brain and cardiac level (Palmer & Demos, 2022).

Early prognostication of long-term outcome of comatose patients after cardiac arrest remains challenging. Electroencephalography-based power spectra after cardiac arrest have been shown to help with the identification of patients with favourable outcome during the first day of coma. Here, we aim at comparing the power spectra prognostic value during the first and second day after coma onset following cardiac arrest and to investigate the impact of sedation on prognostication. In this cohort observational study, we included comatose patients (N = 91) after cardiac arrest for whom resting-state electroencephalography was collected on the first and second day after cardiac arrest in four Swiss hospitals. We evaluated whether the average power spectra values at 4.6-15.2 Hz were predictive of patients' outcome based on the best cerebral performance category score at 3 months, with scores ranging from 1 to 5 and dichotomized as favourable (1-2) and unfavourable (3-5). We assessed the effect of sedation and its interaction with the electroencephalography-based power spectra on patient outcome prediction through a generalized linear mixed model. Power spectra values provided 100% positive predictive value (95% confidence intervals: 0.81-1.00) on the first day of coma, with correctly predicted 18 out of 45 favourable outcome patients. On the second day, power spectra values were not predictive of patients' outcome (positive predictive value: 0.46, 95% confidence intervals: 0.19-0.75). On the first day, we did not find evidence of any significant contribution of sedative infusion rates to the patient outcome prediction (P > 0.05). Comatose patients' outcome prediction based on electroencephalographic power spectra is higher on the first compared with the second day after cardiac arrest. Sedation does not appear to impact patient outcome prediction.

OBJECTIVE: Most of the available clinical tests for prognosis of post-anoxic coma are informative of poor outcome. Previous work has shown that an improvement in auditory discrimination over the first days of coma is predictive of awakening. Here, we aimed at evaluating this test on a large cohort of patients undergoing therapeutic hypothermia and at investigating its added value on existing clinical measures. METHODS: We recorded electroencephalography responses to auditory stimuli in 94 comatose patients, under hypothermia and after re-warming to normal temperature. Auditory discrimination was semi-automatically quantified by decoding electroencephalography responses to frequently repeated vs. rare sounds. Outcome prediction was based on the change of decoding performance from hypothermia to normothermia. RESULTS: An increase in auditory discrimination from hypothermia to normothermia was observed for 33 out of 94 patients. Among them, 27 awoke from coma, resulting in a positive predictive value of awakening of 82% (95% confidence interval: 0.65-0.93). Most non-survivors showing an improvement in auditory discrimination had incident status epilepticus. By excluding them, 27 out of 29 patients with improvement in auditory discrimination survived, resulting in a considerable improvement of the predictive value for awakening (93%, with 95% confidence interval: 0.77-0.99). Importantly, this test predicted the awakening of 13 out of 51 patients for which the outcome was uncertain based on current tests. INTERPRETATION: The progression of auditory discrimination from hypothermia to normothermia has a high predictive value for awakening. This quantitative measure provides an added value to existing clinical tests and encourages the maintenance of life support. This article is protected by copyright. All rights reserved.

Decision-making in an uncertain environment is driven by two major needs: exploring the environment to gather information or exploiting acquired knowledge to maximize reward. The neural processes underlying exploratory decision-making have been mainly studied by means of functional magnetic resonance imaging, overlooking any information about the time when decisions are made. Here, we carried out an electroencephalography (EEG) experiment, in order to detect the time when the brain generators responsible for these decisions have been sufficiently activated to lead to the next decision. Our analyses, based on a classification scheme, extract time-unlocked voltage topographies during reward presentation and use them to predict the type of decisions made on the subsequent trial. Classification accuracy, measured as the area under the Receiver Operator's Characteristic curve was on average 0.65 across 7 subjects. Classification accuracy was above chance levels already after 516 ms on average, across subjects. We speculate that decisions were already made before this critical period, as confirmed by a positive correlation with reaction times across subjects. On an individual subject basis, distributed source estimations were performed on the extracted topographies to statistically evaluate the neural correlates of decision-making. For trials leading to exploration, there was significantly higher activity in dorsolateral prefrontal cortex and the right supramarginal gyrus; areas responsible for modulating behavior under risk and deduction. No area was more active during exploitation. We show for the first time the temporal evolution of differential patterns of brain activation in an exploratory decision-making task on a single-trial basis.