Frontal EEG for intensive care unit sedation: treating numbers or patients?

Adaptive Sedation Monitoring From EEG in ICU Patients With Online Learning

Sedative medications are routinely administered to provide comfort and facilitate clinical care in critically ill ICU patients. Prior work shows that brain monitoring using electroencephalography (EEG) to track sedation levels may help medical personnel to optimize drug dosing and avoid the adverse effects of oversedation and undersedation. However, the performance of sedation monitoring methods proposed to date deal poorly with individual variability across patients, leading to inconsistent performance. To address this challenge we develop an online learning approach based on Adaptive Regularization of Weight Vectors (AROW). Our approach adaptively updates a sedation level prediction algorithm under a continuously evolving data distribution. The prediction model is gradually calibrated for individual patients in response to EEG observations and routine clinical assessments over time. The evaluations are performed on a population of 172 sedated ICU patients whose sedation levels were assessed using the Richmond Agitation-Sedation Scale (scores between -5 = comatose and 0 = awake). The proposed adaptive model achieves better performance than the same model without adaptation (average accuracies with tolerance of one level difference: 68.76% vs. 61.10%). Moreover, our approach is shown to be robust to sudden changes caused by label noise. Medication administrations have different effects on model performance. We find that the model performs best in patients receiving only propofol, compared to patients receiving no sedation or multiple simultaneous sedative medications.

Automated tracking of level of consciousness and delirium in critical illness using deep learning

Over- and under-sedation are common in the ICU, and contribute to poor ICU outcomes including delirium. Behavioral assessments, such as Richmond Agitation-Sedation Scale (RASS) for monitoring levels of sedation and Confusion Assessment Method for the ICU (CAM-ICU) for detecting signs of delirium, are often used. As an alternative, brain monitoring with electroencephalography (EEG) has been proposed in the operating room, but is challenging to implement in ICU due to the differences between critical illness and elective surgery, as well as the duration of sedation. Here we present a deep learning model based on a combination of convolutional and recurrent neural networks that automatically tracks both the level of consciousness and delirium using frontal EEG signals in the ICU. For level of consciousness, the system achieves a median accuracy of 70% when allowing prediction to be within one RASS level difference across all patients, which is comparable or higher than the median technician–nurse agreement at 59%. For delirium, the system achieves an AUC of 0.80 with 69% sensitivity and 83% specificity at the optimal operating point. The results show it is feasible to continuously track level of consciousness and delirium in the ICU.

Potential EEG biomarkers of sedation doses in intensive care patients unveiled by using a machine learning approach

OBJECTIVE

Sedation of neurocritically ill patients is one of the most challenging situation in ICUs. Quantitative knowledge on the sedation effect on brain activity in that complex scenario could help to uncover new markers for sedation assessment. Hence, we aim to evaluate the existence of changes of diverse EEG-derived measures in deeply-sedated (RASS-Richmond agitation-sedation scale  -4 and  -5) neurocritically ill patients, and also whether sedation doses are related with those eventual changes.

APPROACH

We performed an observational prospective cohort study in the intensive care unit of the Hospital de la Princesa. Twenty-six adult patients suffered from traumatic brain injury and subarachnoid hemorrhage were included in the present study. Long-term continuous electroencephalographic (EEG) recordings (2141 h) and hourly annotated information were used to determine the relationship between intravenous sedation infusion doses and network and spectral EEG measures. To do that, two different strategies were followed: assessment of the statistical dependence between both variables using the Spearman correlation rank and by performing an automatic classification method based on a machine learning algorithm.

MAIN RESULTS

More than 60% of patients presented a correlation greater than 0.5 in at least one of the calculated EEG measures with the sedation dose. The automatic classification method presented an accuracy of 84.3% in discriminating between different sedation doses. In both cases the nodes' degree was the most relevant measurement.

SIGNIFICANCE

The results presented here provide evidences of brain activity changes during deep sedation linked to sedation doses. Particularly, the capability of network EEG-derived measures in discriminating between different sedation doses could be the framework for the development of accurate methods for sedation levels assessment.

Feasibility of continuous sedation monitoring in critically ill intensive care unit patients using the NeuroSENSE WAVCNS index

Sedation in the intensive care unit (ICU) is challenging, as both over- and under-sedation are detrimental. Current methods of assessment, such as the Richmond Agitation Sedation Scale (RASS), are measured intermittently and rely on patients' behavioral response to stimulation, which may interrupt sleep/rest. A non-stimulating method for continuous sedation monitoring may be beneficial and allow more frequent assessment. Processed electroencephalography (EEG) monitors have not been routinely adopted in the ICU. The aim of this observational study was to assess the feasibility of using the NeuroSENSE™ monitor for EEG-based continuous sedation assessment. With ethical approval, ICU patients on continuous propofol sedation were recruited. Depth-of-hypnosis index (WAV_CNS) values were obtained from the NeuroSENSE. Bedside nurses, blinded to the NeuroSENSE, performed regular RASS assessments and maintained the sedation regimen as per standard of care. Participants were monitored throughout the duration of their propofol infusion, up to 24 h. Fifteen patients, with median [interquartile range] age of 57 [52-62.5] years were each monitored for a duration of 9.0 [5.7-20.1] h. Valid WAV_CNS values were obtained for 89% [66-99] of monitoring time and were widely distributed within and between individuals, with 6% [1-31] spent < 40 (very deep), and 3% [1-15] spent > 90 (awake). Significant EEG suppression was detected in 3/15 (20%) participants. Observed RASS matched RASS goals in 36/89 (40%) assessments. The WAV_CNS variability, and incidence of EEG suppression, highlight the limitations of using RASS as a standalone sedation measure, and suggests potential benefit of adjunct continuous brain monitoring.

Linking numbers to perceptions and experiences: Why we need transdisciplinary mixed-methods combining neurophysiological and qualitative data

Today, more and more problems that scientists need to tackle are complex problems. Many examples of these can be found in the health sciences, medicine and ecology. Typical features of complex problems are that they cannot be studied by one discipline and that they need to take into account subjective data as well as objective data. Two promising responses to deal with complex problems are Transdisciplinary and Mixed Method approaches. However, there is still a lacuna to fill, with transdisciplinary studies bridging the social sciences and biomedical sciences. More specifically, we need more and better studies that combine qualitative data about subjective experiences, perception and so on with objective, quantitative, neurophysiological data. We believe that the combination of qualitative and neurophysiological data is a good example of what we would like to call transdisciplinary mixed methods. In this article, we aim to explore the opportunities of transdisciplinary mixed-methods studies in which qualitative and neurophysiological data are used. We give a brief overview of what is characteristic for this kind of studies and illustrate this with examples; we point out strengths and limitations and propose an agenda for the future. We conclude that transdisciplinary mixed-methods studies in which qualitative and neurophysiological data are used have the potential to improve our knowledge about complex problems. A main obstacle seems to be that most scientists from the biomedical sciences are not familiar with the (qualitative) methods from the social sciences and vice versa. To end this ‘clash of paradigms’™, we urgently need to cultivate transdisciplinary thinking.

Automated sedation outperforms manual administration of propofol and remifentanil in critically ill patients with deep sedation: a randomized phase II trial

PURPOSE

To compare automated administration of propofol and remifentanil guided by the Bispectral index (BIS) versus manual administration of short-acting drugs in critical care patients requiring deep sedation. The primary outcome was the percentage of BIS values between 40 and 60 (BIS(40-60)).

METHODS

This randomized controlled phase II trial in the intensive care unit (ICU) was conducted in adults with multiorgan failure. Thirty-one patients were assigned to receive sedation with propofol or remifentanil either by an automated or a manual system, both targeting BIS(40-60). Performance and feasibility of an automated administration were assessed.

RESULTS

The study groups were well balanced in terms of demographic characteristics. Study duration averaged 18 [8-24] h in the automated group and 14 [9-21] h in the manual group (p = 0.81). Adequate sedation (BIS(40-60)) was significantly more frequent in the automated group 77 [59-82] % than in the manual group 36 [22-56] %, with p = 0.001. Propofol consumption was reduced by a factor of 2 in the automated group with a median change of infusion rates of 39 ± 9 times per hour. In contrast, there were only 2 ± 1 propofol and 1 ± 1 remifentanil dose changes per hour in the manual group compared to 40 ± 9 for remifentanil in the automated group (p < 0.001). Vasopressors were more often discontinued or reduced in the automated group than in the manual control group (36 [6-40] vs. 12 [4-20] modifications, p = 0.03).

CONCLUSIONS

Continuous titration of propofol and remifentanil sedation with an automatic controller maintains deep sedation better than manual control in severely ill patients. It is associated with reduced sedative and vasopressor use.

Bispectral index to monitor propofol sedation in trauma patients

BACKGROUND

This study tested the hypothesis that the bispectral index (BIS) is reliable relative to clinical judgment for estimating sedation level during daily propofol spontaneous awakening trials (SATs) in trauma patients.

METHODS

This was a prospective observational trial with waiver of consent conducted in the intensive care unit of Level I trauma center in 94 mechanically ventilated trauma patients sedated with propofol alone or in combination with midazolam. BIS, Richmond Agitation Sedation Scale (RASS), electromyography, and heart rate variability, as a test of autonomic function, were measured for 45 minutes during daily SATs. Data were evaluated with analysis of variance, linear regression, and nonparametric tests.

RESULTS

The BIS wave form coincided almost exactly with propofol on/off. Steady-state BIS correlated with RASS (p < 0.0001) and with propofol dose (p < 0.0001), but the strengths of association were relatively low (all r(2) < 0.5). BIS wave form was not altered by age, heart rate, or heart rate variability and was similar with propofol alone or propofol plus midazolam, but the presence of brain injury or the use of paralytics shifted the curve downward (both p < 0.001). The overall test characteristics for BIS versus RASS without neuromuscular blockade were sensitivity: 90% versus 77% (p = 0.034); specificity: 90% versus 75% (p = 0.021); positive predictive value: 90% versus 76% (p = 0.021), and negative predictive value: 90% versus 76% (p = 0.021).

CONCLUSIONS

In the first trial in trauma patients and largest trial in any surgical population, the (1) BIS was reliable and has advantages over RASS of being continuous and objective, at least during a propofol SAT; (2) BIS interpretation remains somewhat subjective in patients receiving paralytic agents or with traumatic brain injury.

Long-term sedation in intensive care unit: a randomized comparison between inhaled sevoflurane and intravenous propofol or midazolam

PURPOSE

To evaluate efficacy and adverse events related to inhaled sevoflurane for long-term sedation compared with standard intravenous (i.v.) sedation with propofol or midazolam.

METHODS

Randomized controlled trial. Sixty intensive care unit (ICU) patients expected to require more than 24 h sedation were randomly assigned to one of three groups: group S, inhaled sevoflurane; group P, i.v. propofol; group M, i.v. midazolam. All patients also received i.v. remifentanil for goal-directed sedation (Ramsay scale and pain score) until extubation or for a maximum of 96 h. Primary end points were wake-up times and extubation delay from termination of sedative administration. Proportion of time within Ramsay score 3-4, i.v. morphine consumption at 24 h post extubation, hallucination episodes after end of sedation, adverse events, inorganic fluoride plasma levels, and ambient sevoflurane concentrations were recorded.

RESULTS

Forty-seven patients were analyzed. Wake-up time and extubation delay were significantly (P<0.01) shorter in group S (18.6 ± 11.8 and 33.6 ± 13.1 min) than in group P (91.3 ± 35.2 and 326.11 ± 360.2 min) or M (260.2 ± 150.2 and 599.6 ± 586.6 min). Proportion of time within desired interval of sedation score was comparable between groups. Morphine consumption during the 24 h following extubation was lower in group S than in groups P and M. Four hallucination episodes were reported in group P, five in group M, and none in group S (P=0.04). No hepatic or renal adverse events were reported. Mean plasma fluoride value was 82 μmol l(-1) (range 12-220 μmol l(-1)), and mean ambient sevoflurane concentration was 0.3 ± 0.1 ppm.

CONCLUSIONS

Long-term inhaled sevoflurane sedation seems to be a safe and effective alternative to i.v. propofol or midazolam. It decreases wake-up and extubation times, and post extubation morphine consumption, and increases awakening quality.