Precise detection of awareness in disorders of consciousness using deep learning framework

The evaluation of the level of consciousness in patients with disorders of consciousness (DOC) is primarily based on behavioural assessments. Patients with unresponsive wakefulness syndrome (UWS) do not show any sign of awareness of their environment, while minimally conscious state (MCS) patients show reproducible but fluctuating signs of awareness. Some patients, although with remaining cognitive abilities, are not able to exhibit overt voluntary responses at the bedside and may be misdiagnosed as UWS. Several studies investigated functional neuroimaging and neurophysiology as an additional tool to evaluate the level of consciousness and to detect covert command following in DOC. Most of these studies are based on auditory stimulation, neglecting patients suffering from decreased or absent hearing abilities. In the present study, we aim to assess the response to a P3-based paradigm in 40 patients with DOC and 12 healthy participants using auditory (AEP) and vibrotactile (VTP) stimulation. To this end, an EEG-based brain-computer interface was used at DOC patient’s bedside. We compared the significance of the P3 performance (i.e., the interpretation of significance of the evoked P3 response) as obtained by ‘direct processing’ (i.e., theoretical-based significance threshold) and ‘offline processing’ (i.e., permutation-based single subject level threshold). We evaluated whether the P3 performances were dependent on clinical variables such as diagnosis (UWS and MCS), aetiology and time since injury. Last we tested the dependency of AEP and VTP performances at the single subject level. Direct processing tends to overestimate P3 performance. We did not find any difference in the presence of a P3 performance according to the level of consciousness (UWS vs. MCS) or the aetiology (traumatic vs. non-traumatic brain injury). The performance achieved at the AEP paradigm was independent from what was achieved at the VTP paradigm, indicating that some patients performed better on the AEP task while others performed better on the VTP task. Our results support the importance of using multimodal approaches in the assessment of DOC patients in order to optimise the evaluation of patient’s abilities.

Disorders of Consciousness (DOC) are a spectrum of pathologies affecting one’s ability to interact with the external world. Two possible conditions of patients with DOC are Unresponsive Wakefulness Syndrome/Vegetative State (UWS/VS) and Minimally Conscious State (MCS). Analysis of spontaneous EEG activity and the Heart Rate Variability (HRV) are effective techniques in exploring and evaluating patients with DOC. This study aims to observe fluctuations in EEG and HRV parameters in the morning/afternoon resting-state recording. The study enrolled 13 voluntary Healthy Control (HC) subjects and 12 DOC patients (7 MCS, 5 UWS/VS). EEG and EKG were recorded. PSDalpha, PSDtheta powerband, alpha-blocking, alpha/theta of the EEG, Complexity Index (CI) and SDNN of EKG were analyzed. Higher values of PSDalpha, alpha-blocking, alpha/theta and CI values and lower values of PSD theta characterized HC individuals in the morning with respect to DOC patients. In the afternoon, we detected a significant difference between groups in the CI, PSDalpha, PSDtheta, alpha/theta and SDNN, with lower PSDtheta value for HC. CRS-R scores showed a strong correlation with recorded parameters mainly during evaluations in the morning. Our finding put in evidence the importance of the assessment, as the stimulation of DOC patients in research for behavioural response, in the morning.

Background: Disorders of consciousness are challenging to diagnose, with inconsistent behavioral responses, motor and cognitive disabilities, leading to approximately 40% misdiagnoses. Heart rate variability (HRV) reflects the complexity of the heart-brain two-way dynamic interactions. HRV entropy analysis quantifies the unpredictability and complexity of the heart rate beats intervals. We here investigate the complexity index (CI), a score of HRV complexity by aggregating the non-linear multi-scale entropies over a range of time scales, and its discriminative power in chronic patients with unresponsive wakefulness syndrome (UWS) and minimally conscious state (MCS), and its relation to brain functional connectivity. Methods: We investigated the CI in short (CIs) and long (CIl) time scales in 14 UWS and 16 MCS sedated. CI for MCS and UWS groups were compared using a Mann-Whitney exact test. Spearman's correlation tests were conducted between the Coma Recovery Scale-revised (CRS-R) and both CI. Discriminative power of both CI was assessed with One-R machine learning model. Correlation between CI and brain connectivity (detected with functional magnetic resonance imagery using seed-based and hypothesis-free intrinsic connectivity) was investigated using a linear regression in a subgroup of 10 UWS and 11 MCS patients with sufficient image quality. Results: Higher CIs and CIl values were observed in MCS compared to UWS. Positive correlations were found between CRS-R and both CI. The One-R classifier selected CIl as the best discriminator between UWS and MCS with 90% accuracy, 7% false positive and 13% false negative rates after a 10-fold cross-validation test. Positive correlations were observed between both CI and the recovery of functional connectivity of brain areas belonging to the central autonomic networks (CAN). Conclusion: CI of MCS compared to UWS patients has high discriminative power and low false negative rate at one third of the estimated human assessors' misdiagnosis, providing an easy, inexpensive and non-invasive diagnostic tool. CI reflects functional connectivity changes in the CAN, suggesting that CI can provide an indirect way to screen and monitor connectivity changes in this neural system. Future studies should assess the extent of CI's predictive power in a larger cohort of patients and prognostic power in acute patients.

Electroencephalography quadratic phase self-coupling correlates with consciousness states and restoration in patients with disorders of consciousness

The assessment of awareness in patients with chronic Disorders of Consciousness (DoC), including Unresponsive Wakefulness Syndrome (UWS) and Minimally Conscious State (MCS), is challenging. The level of awareness impairment may depend on the degree of deterioration of the large-scale cortical-thalamo-cortical networks induced by brain injury. Electrophysiological approaches may shed light on awareness presence in patients with DoC by estimating cortical functions related to the cortical-thalamo-cortical networks including, for example, the cortico-subcortical processes generating motor responses to the perturbation of the peri-personal space (PPS). We measured the amplitude, latency, and duration of the hand-blink reflex (HBR) responses by recording electromyography (EMG) signals from both the orbicularis oculi muscles while electrically stimulating the median nerve at the wrist. Such a BR is thought to be mediated by a neural circuit at the brainstem level. Despite its defensive-response nature, HBR can be modulated by the distance between the stimulated hand and the face. This suggests a functional top-down control of HBR as reflected by HBR features changes (latency, amplitude, and magnitude). We therefore estimated HBR responses in a sample of patients with DoC (8 MCS and 12 UWS, compared to 15 healthy controls −HC) while performing a motor task targeting the PPS. This consisted of passive movements in which the hand of the subject was positioned at different distances from the participant’s face. We aimed at demonstrating a residual top-down modulation of HBR properties, which could be useful to differentiate patients with DoC and, potentially, demonstrate awareness preservation. We found a decrease in latency, and an increase in duration and magnitude of HBR responses, which were all inversely related to the hand-to-face distance in HC and patients with MCS, but not in individuals with UWS. Our data suggest that only patients with MCS have preserved, residual, top-down modulation of the processes related to the PPS from higher-order cortical areas to sensory-motor integration network. Although the sample size was relatively small, being thus our data preliminary, HBR assessment seems a rapid, easy, and first-level tool to differentiate patients with MCS from those with UWS. We may also hypothesize that such a HBR modulation suggests awareness preservation.

ABSTRACTObjective: 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.

Disorders of Consciousness (DoC) are clinical conditions characterized by different levels of arousal and awareness, including coma, Unresponsive Wakefulness Syndrome and Minimally Conscious State (MCS). A Brain-Computer Interface (BCI) employs brain signals to establish a non-muscular outward channel, representing a key frontier in the clinical care of individuals in MCS, with high potential to enhance communication and quality of life. The P300-based BCIs, which use the P300 ERP as a control signal, are the most investigated to emulate communication in MCS. However, a reliable control by MCS patients of these BCIs still remains matter of question. One major challenge could be the across trials variability of P300 characteristics, possibly related to attentional fluctuations in this population. The trial-by-trial instability of the P300 peak latency, known as latency jitter, negatively impacts classification performance, and an approach to mitigating this issue involves template matching algorithms (e.g. the Adaptive Wavelet Filtering, AWF) which detect and realign the P300 latency at the single-trial level. This study investigated the offline classification performance using Stepwise Linear Discriminant Analysis (SWLDA) models trained with progressively larger training sets, to discriminate target from non-target stimuli during an active auditory oddball paradigm. Performance from raw and jitter-corrected data, collected from a control group and a group of patients diagnosed as MCS, were compared. Results highlighted the key role of latency jitter correction in the enhancement of performance and classification speed.Clinical Relevance- The findings suggest that jitter correction could improve real-world applicability of P300-BCI systems for individuals with DoC.

Brain-computer interface (BCI) has been emerging as an assessment tool for patients with disorder of consciousness (DOC). With the advantages of high time resolution, low cost and portable design, EEG based BCI systems are especially suitable for bedside measurement. Recent studies showed the successful application of an EEG based BCI on DOC assessment and communication. However, the effect of repeated BCI measurement on this patient group is not clear. In this study, a tactile BCI paradigm was repeated 12 runs for 10 consecutive days on 5 DOC patients. Although the BCI performance varied among runs and days, every patient reached at least once the accuracy above 60%. Moreover, the Coma Recovery Scale Revised improved on two out of the five patients. This study addressed the significance of repeating a tactile BCI on DOC patients, and indicates a promising recovery effect of a tactile BCI on DOC patients.

Disorders of consciousness (DOC), including unresponsive wakefulness syndrome (UWS) and minimally conscious state (MCS), are complex brain dysfunctions with various causes. Misdiagnosis is common when relying solely on neurological exams, highlighting the need for accurate differentiation to guide clinical rehabilitation. This study explores metabolomic differences between UWS and MCS across cerebrospinal fluid (CSF), serum, and urine samples to identify biomarkers and metabolic pathways. Fifty-one subjects were categorized into UWS (n = 35) and MCS (n = 16) based on coma recovery scale-revised (CRS-R) scores. Ultraperformance liquid chromatography tandem mass spectrometry (UPLC-MS/MS) was used to analyze samples, and statistical methods identified 14, 24, and 22 differential metabolites in CSF, serum, and urine, respectively. CSF metabolites were linked to necrosis, apoptosis, and neuroprotection; serum metabolites to lipid metabolism and immune response; and urine metabolites to cell signaling and neural function. Metabolomic panels showed AUC values of 0.85 (95% CI: 0.73-0.96) for CSF (95% CI: 0.86-1.00), 0.94 for serum, and 0.93 (95% CI: 0.79-1.00) for urine in distinguishing UWS from MCS. This profiling offers valuable insights into DOC pathophysiology and aids in accurate differentiation of these states.

To measure regional cerebral metabolic rate of glucose (CMRGlu) in patients with chronic disorders of consciousness (DOCs) using 18F-fluorodeoxyglucose positron emission tomography (FDG-PET). This retrospective cohort study examined 50 patients (mean age: 40.9 ± 20.1 years) with traumatic brain injury (TBI)-induced chronic DOCs [minimally conscious state (MCS)+, n = 20; MCS-, n = 15 and vegetative state (VS), n = 15]. We measured FDG-PET-based CMRGlu values in 12 regions of both brain hemispheres and compared those among MCS+, MCS - and VS patients. In both hemispheres, the regional CMRGlu reduced with consciousness deterioration in 11 of 12 regions (91.7%). In seven right hemisphere regions, CMRGlu values were markedly higher in MCS+ patients than in MCS- patients. Furthermore, CMRGlu was suggestively higher in the left occipital region in MCS- patients than in VS patients. Functional preservation in the left occipital region in patients with chronic DOCs might reflect an awareness of external environments, whereas extensive functional preservation in the right cerebral hemisphere might reflect communication motivation.

Background: Disorders of consciousness (DoCs) include unresponsive wakefulness syndrome (UWS) and minimally conscious state (MCS). Critical illness polyneuropathy and myopathy (CIPNM) is frequent in severe acquired brain injuries and impacts functional outcomes at discharge from the intensive rehabilitation unit (IRU). We investigated the prevalence of CIPNM in DoCs and its relationship with the consciousness assessment. Methods: Patients with DoCs were retrospectively selected from the database including patients admitted to the IRU of the IRCCS Don Gnocchi Foundation, Florence, from August 2012 to May 2020. Electroneurography/electromyography was performed at admission. Consciousness was assessed using the Coma Recovery Scale-Revised (CRS-R) at admission and discharge. Patients transitioning from a lower consciousness state to a higher one were classified as improved responsiveness (IR). Results: A total of 177 patients were included (UWS: 81 (45.8%); MCS: 96 (54.2%); 78 (44.1%) women; 67 years (IQR: 20). At admission, 108 (61.0%) patients had CIPNM. At discharge, 117 (66.1%) patients presented an IR. In the multivariate analysis, CRS-R at admission (p = 0.006; OR: 1.462) and CIPNM (p = 0.039; OR: −1.252) remained significantly associated with IR only for the UWS patients. Conclusions: CIPNM is frequent in DoCs and needs to be considered during the clinical consciousness assessment, especially in patients with UWS.

Disorders of consciousness (DOC) diagnosis relies on the presence or absence of purposeful motor responsiveness, which characterizes the minimally conscious state (MCS) and the unresponsive wakefulness syndrome (UWS), respectively. Functional neuroimaging studies have raised the question of possible residual conscious awareness also in clinically-defined UWS patients. The aim of our study was to identify electrophysiological parameters, by means of a transcranial magnetic stimulation approach, which might potentially express the presence of residual networks sustaining fragmentary behavioral patterns, even when no conscious behavior can be observed. We enrolled 25 severe DOC patients, following post-anoxic or traumatic brain injury and 20 healthy individuals (HC) as control group. Baseline electrophysiological evaluation evidenced, in comparison to HC, a partial preservation of cortical effective connectivity and excitability in clinically defined MCS, whereas these components were absent in clinically defined UWS. Then, we applied an anodal transcranial direct current stimulation (a-tDCS) protocol over the orbitofrontal cortex. a-tDCS was able to boost cortical connectivity and excitability in all HC, MCS, and to unmask such excitability/connectivity in some UWS patients. a-tDCS could be useful in identifying residual connectivity markers in clinically-defined UWS, who may lack of purposeful behavior as a result of a motor-output failure.

ABSTRACTBackground: Eye behaviour is important to distinguish minimally conscious state (MCS) from vegetative state (VS).Objective: To search for conditions most suitable to characterize patients in MCS and in VS on quantitative assessment of visual tracking.Design: This is a cross-sectional study.Participants: In total, 20 patients in VS, 13 in MCS plus and 11 in MCS minus participated in this study.Setting: Neurorehabilitation Unit.Methods: Evaluation of eye behaviour was performed by infrared system; stimuli were represented by a red circle, a picture of a patient’s own face and a picture of an unfamiliar face, slowly moving on a personal computer (PC) monitor. Visual tracking on the horizontal and vertical axes was compared.Main outcome measures: The main outcome measures were proportion of on-target fixations and mean fixation duration.Results: The proportion of on-target fixations differed as a function of the stimulus in patients in MCS plus but not in other groups. Own face and unfamiliar face elicited a similar proportion of on-target fixations. Tracking along the horizontal axis was more accurate than that along the vertical axis in patients in both MCS plus and MCS minus. Fixation duration did not differ among the three groups.Conclusions: Horizontal visual tracking of salient stimuli seems particularly suitable for eliciting on-target fixations. Quantitative assessment of visual tracking can complement clinical evaluation for reducing diagnostic uncertainty between patients in MCS or VS.

Given the enormous consequences that the diagnosis of vegetative state (VS) vs. minimally conscious state (MCS) may have for the treatment of patients with disorders of consciousness, it is particularly important to empirically legitimate the distinction between these two discrete levels of consciousness. Therefore, the aim of this contribution is to review all the articles reporting statistical evidence concerning the performance of patients in VS vs. patients in MCS, on behavioral or neurophysiological measures. Twenty-three articles matched these inclusion criteria, and comprised behavioral, electroencephalographic (EEG), positron emission tomography (PET) and magnetic resonance imaging (MRI) measures. The analysis of these articles yielded 47 different statistical findings. More than half of these findings (n = 24) did not reveal any statistically significant difference between VS and MCS. Overall, there was no combination of variables that allowed reliably discriminating between VS and MCS. This pattern of results casts doubt on the empirical validity of the distinction between VS and MCS.

Little is known about plastic changes occurring in the brains of patients with severe disorders of consciousness (DOCs) caused by acute brain injuries at rest and during rehabilitative treatment. Brain-derived neurotrophic factor (BDNF) is a neurotrophin involved in neurogenesis and synaptic plasticity whose production is powerfully modulated by physical exercise. In this study, we compared serum BDNF levels in 18 patients with unresponsive wakefulness syndrome (UWS) and in a minimally conscious state (MCS) with those in 16 sex- and age-matched healthy controls. In 12 patients, serum BDNF levels before and after verticalization with ErigoPro robot-assisted lower-limb training were compared. Serum BDNF levels were significantly lower in patients (median, 1141 pg/ml; 25th and 75th percentiles, 1016 and 1704 pg/ml) than in controls (median, 2450 pg/ml; 25th and 75th percentiles, 2100 and 2875 pg/ml; p < 0.001). BDNF levels measured before and after verticalization with robot-assisted lower-limb training did not change (p = 0.5). Moreover, BDNF levels did not differ between patients with UWS and MCS (p = 0.2), or between patients with traumatic and nontraumatic brain injuries (p = 0.6). BDNF level correlated positively with the time since brain injury (p = 0.025). In conclusion, serum BDNF levels are reduced in patients with UWS and MCS and cannot be improved by verticalization associated with passive lower-limb training. Additional studies are needed to better understand the mechanisms underlying BDNF reduction in patients with DOCs and to determine the best rehabilitative strategies to promote restorative plastic changes in these patients.