Auditory discrimination improvement predicts awakening of postanoxic comatose patients treated with targeted temperature management at 36 °C

Deep learning for EEG-based prognostication after cardiac arrest: from current research to future clinical applications

Outcome prognostication in comatose patients after cardiac arrest (CA) remains to date a challenge. The major determinant of clinical outcome is the post-hypoxic/ischemic encephalopathy. Electroencephalography (EEG) is routinely used to assess neural functions in comatose patients. Currently, EEG-based outcome prognosis relies on visual evaluation by medical experts, which is time consuming, prone to subjectivity, and oblivious to complex patterns. The field of deep learning has given rise to powerful algorithms for detecting patterns in large amounts of data. Analyzing EEG signals of coma patients with deep neural networks with the goal of assisting in outcome prognosis is therefore a natural application of these algorithms. Here, we provide the first narrative literature review on the use of deep learning for prognostication after CA. Existing studies show overall high performance in predicting outcome, relying either on spontaneous or on auditory evoked EEG signals. Moreover, the literature is concerned with algorithmic interpretability, and has shown that largely, deep neural networks base their decisions on clinically or neurophysiologically meaningful features. We conclude this review by discussing considerations that the fields of artificial intelligence and neurology will need to jointly address in the future, in order for deep learning algorithms to break the publication barrier, and to be integrated in clinical practice.

Auditory stimulation and deep learning predict awakening from coma after cardiac arrest

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.

Predicting neurological outcome after cardiac arrest by combining computational parameters extracted from standard and deviant responses from auditory evoked potentials

Background

Despite multimodal assessment (clinical examination, biology, brain MRI, electroencephalography, somatosensory evoked potentials, mismatch negativity at auditory evoked potentials), coma prognostic evaluation remains challenging.

Methods

We present here a method to predict the return to consciousness and good neurological outcome based on classification of auditory evoked potentials obtained during an oddball paradigm. Data from event-related potentials (ERPs) were recorded noninvasively using four surface electroencephalography (EEG) electrodes in a cohort of 29 post-cardiac arrest comatose patients (between day 3 and day 6 following admission). We extracted retrospectively several EEG features (standard deviation and similarity for standard auditory stimulations and number of extrema and oscillations for deviant auditory stimulations) from the time responses in a window of few hundreds of milliseconds. The responses to the standard and the deviant auditory stimulations were thus considered independently. By combining these features, based on machine learning, we built a two-dimensional map to evaluate possible group clustering.

Results

Analysis in two-dimensions of the present data revealed two separated clusters of patients with good versus bad neurological outcome. When favoring the highest specificity of our mathematical algorithms (0.91), we found a sensitivity of 0.83 and an accuracy of 0.90, maintained when calculation was performed using data from only one central electrode. Using Gaussian, K-neighborhood and SVM classifiers, we could predict the neurological outcome of post-anoxic comatose patients, the validity of the method being tested by a cross-validation procedure. Moreover, the same results were obtained with one single electrode (Cz).

Conclusion

statistics of standard and deviant responses considered separately provide complementary and confirmatory predictions of the outcome of anoxic comatose patients, better assessed when combining these features on a two-dimensional statistical map. The benefit of this method compared to classical EEG and ERP predictors should be tested in a large prospective cohort. If validated, this method could provide an alternative tool to intensivists, to better evaluate neurological outcome and improve patient management, without neurophysiologist assistance.

Prognostication after cardiac arrest: how EEG and evoked potentials may improve the challenge

About 80% of patients resuscitated from CA are comatose at ICU admission and nearly 50% of survivors are still unawake at 72 h. Predicting neurological outcome of these patients is important to provide correct information to patient's relatives, avoid disproportionate care in patients with irreversible hypoxic-ischemic brain injury (HIBI) and inappropriate withdrawal of care in patients with a possible favorable neurological recovery. ERC/ESICM 2021 algorithm allows a classification as "poor outcome likely" in 32%, the outcome remaining "indeterminate" in 68%. The crucial question is to know how we could improve the assessment of both unfavorable but also favorable outcome prediction. Neurophysiological tests, i.e., electroencephalography (EEG) and evoked-potentials (EPs) are a non-invasive bedside investigations. The EEG is the record of brain electrical fields, characterized by a high temporal resolution but a low spatial resolution. EEG is largely available, and represented the most widely tool use in recent survey examining current neuro-prognostication practices. The severity of HIBI is correlated with the predominant frequency and background continuity of EEG leading to "highly malignant" patterns as suppression or burst suppression in the most severe HIBI. EPs differ from EEG signals as they are stimulus induced and represent the summated activities of large populations of neurons firing in synchrony, requiring the average of numerous stimulations. Different EPs (i.e., somato sensory EPs (SSEPs), brainstem auditory EPs (BAEPs), middle latency auditory EPs (MLAEPs) and long latency event-related potentials (ERPs) with mismatch negativity (MMN) and P300 responses) can be assessed in ICU, with different brain generators and prognostic values. In the present review, we summarize EEG and EPs signal generators, recording modalities, interpretation and prognostic values of these different neurophysiological tools. Finally, we assess the perspective for futures neurophysiological investigations, aiming to reduce prognostic uncertainty in comatose and disorders of consciousness (DoC) patients after CA.

Complementary roles of neural synchrony and complexity for indexing consciousness and chances of surviving in acute coma

An open challenge in consciousness research is understanding how neural functions are altered by pathological loss of consciousness. To maintain consciousness, the brain needs synchronized communication of information across brain regions, and sufficient complexity in neural activity. Coordination of brain activity, typically indexed through measures of neural synchrony, has been shown to decrease when consciousness is lost and to reflect the clinical state of patients with disorders of consciousness. Moreover, when consciousness is lost, neural activity loses complexity, while the levels of neural noise, indexed by the slope of the electroencephalography (EEG) spectral exponent decrease. Although these properties have been well investigated in resting state activity, it remains unknown whether the sensory processing network, which has been shown to be preserved in coma, suffers from a loss of synchronization or information content. Here, we focused on acute coma and hypothesized that neural synchrony in response to auditory stimuli would reflect coma severity, while complexity, or neural noise, would reflect the presence or loss of consciousness. Results showed that neural synchrony of EEG signals was stronger for survivors than non-survivors and predictive of patients' outcome, but indistinguishable between survivors and healthy controls. Measures of neural complexity and neural noise were not informative of patients' outcome and had high or low values for patients compared to controls. Our results suggest different roles for neural synchrony and complexity in acute coma. Synchrony represents a precondition for consciousness, while complexity needs an equilibrium between high or low values to support conscious cognition.

Clinical and advanced neurophysiology in the prognostic and diagnostic evaluation of disorders of consciousness: review of an IFCN-endorsed expert group

The analysis of spontaneous EEG activity and evoked potentialsis a cornerstone of the instrumental evaluation of patients with disorders of consciousness (DoC). Thepast few years have witnessed an unprecedented surge in EEG-related research applied to the prediction and detection of recovery of consciousness after severe brain injury,opening up the prospect that new concepts and tools may be available at the bedside. This paper provides a comprehensive, critical overview of bothconsolidated and investigational electrophysiological techniquesfor the prognostic and diagnostic assessment of DoC.We describe conventional clinical EEG approaches, then focus on evoked and event-related potentials, and finally we analyze the potential of novel research findings. In doing so, we (i) draw a distinction between acute, prolonged and chronic phases of DoC, (ii) attempt to relate both clinical and research findings to the underlying neuronal processes and (iii) discuss technical and conceptual caveats.The primary aim of this narrative review is to bridge the gap between standard and emerging electrophysiological measures for the detection and prediction of recovery of consciousness. The ultimate scope is to provide a reference and common ground for academic researchers active in the field of neurophysiology and clinicians engaged in intensive care unit and rehabilitation.

Electroencephalography-based power spectra allow coma outcome prediction within 24 h of cardiac arrest

BACKGROUND

Outcome prediction in comatose patients following cardiac arrest remains challenging. Here, we assess the predictive performance of electroencephalography-based power spectra within 24 h from coma onset.

METHODS

We acquired electroencephalography (EEG) from comatose patients (n = 138) on the first day of coma in four hospital sites in Switzerland. Outcome was categorised as favourable or unfavourable based on the best state within three months. Data were split in training and test sets. We evaluated the predictive performance of EEG power spectra for long term outcome and its added value to standard clinical tests.

RESULTS

Out of 138 patients, 80 had a favourable outcome. Power spectra comparison between favourable and unfavourable outcome in the training set yielded significant differences at 5.2-13.2 Hz and above 21 Hz. Outcome prediction based on power at 5.2-13.2 Hz was accurate in training and test sets. Overall, power spectra predicted patients' outcome with maximum specificity and positive predictive value: 1.00 (95% with CI: 0.94-1.00 and 0.89-1.00, respectively). The combination of power spectra and reactivity yielded better accuracy and sensitivity (0.81, 95% CI: 0.71-0.89) than prediction based on power spectra alone.

CONCLUSIONS

On the first day of coma following cardiac arrest, low power spectra values around 10 Hz, typically linked to impaired cortico-thalamic structural connections, are highly specific of unfavourable outcome. Peaks in this frequency range can predict long-term outcome.

Somatosensory and auditory deviance detection for outcome prediction during postanoxic coma

Objective

Prominent research in patients with disorders of consciousness investigated the electrophysiological correlates of auditory deviance detection as a marker of consciousness recovery. Here, we extend previous studies by investigating whether somatosensory deviance detection provides an added value for outcome prediction in postanoxic comatose patients.

Methods

Electroencephalography responses to frequent and rare stimuli were obtained from 66 patients on the first and second day after coma onset.

Results

Multivariate decoding analysis revealed an above chance‐level auditory discrimination in 25 patients on the first day and in 31 patients on the second day. Tactile discrimination was significant in 16 patients on the first day and in 23 patients on the second day. Single‐day sensory discrimination was unrelated to patients’ outcome in both modalities. However, improvement of auditory discrimination from first to the second day was predictive of good outcome with a positive predictive power (PPV) of 0.73 (CI = 0.52–0.88). Analyses considering the improvement of tactile, auditory and tactile, or either auditory or tactile discrimination showed no significant prediction of good outcome (PPVs = 0.58–0.68).

Interpretation

Our results show that in the acute phase of coma deviance detection is largely preserved for both auditory and tactile modalities. However, we found no evidence for an added value of somatosensory to auditory deviance detection function for coma‐outcome prediction.