A deep learning approach for generating intracranial pressure waveforms from extracranial signals routinely measured in the intensive care unit.

Intracranial pressure (ICP) is commonly monitored to guide treatment in patients with serious brain disorders such as traumatic brain injury and stroke. Established methods to assess ICP are resource intensive and highly invasive. We hypothesized that ICP waveforms can be computed noninvasively from three extracranial physiological waveforms routinely acquired in the Intensive Care Unit (ICU): arterial blood pressure (ABP), photoplethysmography (PPG), and electrocardiography (ECG). We evaluated over 600 h of high-frequency (125 Hz) simultaneously acquired ICP, ABP, ECG, and PPG waveform data in 10 patients admitted to the ICU with critical brain disorders. The data were segmented in non-overlapping 10-s windows, and ABP, ECG, and PPG waveforms were used to train deep learning (DL) models to re-create concurrent ICP. The predictive performance of six different DL models was evaluated in single- and multi-patient iterations. The mean average error (MAE) ± SD of the best-performing models was 1.34 ± 0.59 mmHg in the single-patient and 5.10 ± 0.11 mmHg in the multi-patient analysis. Ablation analysis was conducted to compare contributions from single physiologic sources and demonstrated statistically indistinguishable performances across the top DL models for each waveform (MAE±SD 6.33 ± 0.73, 6.65 ± 0.96, and 7.30 ± 1.28 mmHg, respectively, for ECG, PPG, and ABP; p = 0.42). Results support the preliminary feasibility and accuracy of DL-enabled continuous noninvasive ICP waveform computation using extracranial physiological waveforms. With refinement and further validation, this method could represent a safer and more accessible alternative to invasive ICP, enabling assessment and treatment in low-resource settings.

Neuromonitoring in the ICU - what, how and why?

PURPOSE OF REVIEW: We selectively review emerging noninvasive neuromonitoring techniques and the evidence that supports their use in the ICU setting. The focus is on neuromonitoring research in patients with acute brain injury. RECENT FINDINGS: Noninvasive intracranial pressure evaluation with optic nerve sheath diameter measurements, transcranial Doppler waveform analysis, or skull mechanical extensometer waveform recordings have potential safety and resource-intensity advantages when compared to standard invasive monitors, however each of these techniques has limitations. Quantitative electroencephalography can be applied for detection of cerebral ischemia and states of covert consciousness. Near-infrared spectroscopy may be leveraged for cerebral oxygenation and autoregulation computation. Automated quantitative pupillometry and heart rate variability analysis have been shown to have diagnostic and/or prognostic significance in selected subtypes of acute brain injury. Finally, artificial intelligence is likely to transform interpretation and deployment of neuromonitoring paradigms individually and when integrated in multimodal paradigms. SUMMARY: The ability to detect brain dysfunction and injury in critically ill patients is being enriched thanks to remarkable advances in neuromonitoring data acquisition and analysis. Studies are needed to validate the accuracy and reliability of these new approaches, and their feasibility and implementation within existing intensive care workflows.

Brain-Computer Interfaces for Communication in Patients with Disorders of Consciousness: A Gap Analysis and Scientific Roadmap.

BACKGROUND: We developed a gap analysis that examines the role of brain-computer interfaces (BCI) in patients with disorders of consciousness (DoC), focusing on their assessment, establishment of communication, and engagement with their environment. METHODS: The Curing Coma Campaign convened a Coma Science work group that included 16 clinicians and neuroscientists with expertise in DoC. The work group met online biweekly and performed a gap analysis of the primary question. RESULTS: We outline a roadmap for assessing BCI readiness in patients with DoC and for advancing the use of BCI devices in patients with DoC. Additionally, we discuss preliminary studies that inform development of BCI solutions for communication and assessment of readiness for use of BCIs in DoC study participants. Special emphasis is placed on the challenges posed by the complex pathophysiologies caused by heterogeneous brain injuries and their impact on neuronal signaling. The differences between one-way and two-way communication are specifically considered. Possible implanted and noninvasive BCI solutions for acute and chronic DoC in adult and pediatric populations are also addressed. CONCLUSIONS: We identify clinical and technical gaps hindering the use of BCI in patients with DoC in each of these contexts and provide a roadmap for research aimed at improving communication for adults and children with DoC, spanning the clinical spectrum from intensive care unit to chronic care.

Clinical practice and effect of carbon dioxide on outcomes in mechanically ventilated acute brain-injured patients: a secondary analysis of the ENIO study.

PURPOSE: The use of arterial partial pressure of carbon dioxide (PaCO2) as a target intervention to manage elevated intracranial pressure (ICP) and its effect on clinical outcomes remain unclear. We aimed to describe targets for PaCO2 in acute brain injured (ABI) patients and assess the occurrence of abnormal PaCO2 values during the first week in the intensive care unit (ICU). The secondary aim was to assess the association of PaCO2 with in-hospital mortality. METHODS: We carried out a secondary analysis of a multicenter prospective observational study involving adult invasively ventilated patients with traumatic brain injury (TBI), subarachnoid hemorrhage (SAH), intracranial hemorrhage (ICH), or ischemic stroke (IS). PaCO2 was collected on day 1, 3, and 7 from ICU admission. Normocapnia was defined as PaCO2 > 35 and to 45 mmHg; mild hypocapnia as 32-35 mmHg; severe hypocapnia as 26-31 mmHg, forced hypocapnia as < 26 mmHg, and hypercapnia as > 45 mmHg. RESULTS: 1476 patients (65.9% male, mean age 52 ± 18 years) were included. On ICU admission, 804 (54.5%) patients were normocapnic (incidence 1.37 episodes per person/day during ICU stay), and 125 (8.5%) and 334 (22.6%) were mild or severe hypocapnic (0.52 and 0.25 episodes/day). Forced hypocapnia and hypercapnia were used in 40 (2.7%) and 173 (11.7%) patients. PaCO2 had a U-shape relationship with in-hospital mortality with only severe hypocapnia and hypercapnia being associated with increased probability of in-hospital mortality (omnibus p value = 0.0009). Important differences were observed across different subgroups of ABI patients. CONCLUSIONS: Normocapnia and mild hypocapnia are common in ABI patients and do not affect patients' outcome. Extreme derangements of PaCO2 values were significantly associated with increased in-hospital mortality.

Individualized Thresholds of Hypoxemia and Hyperoxemia and their Effect on Outcome in Acute Brain Injured Patients: A Secondary Analysis of the ENIO Study.

BACKGROUND: In acute brain injury (ABI), the effects of hypoxemia as a potential cause of secondary brain damage and poor outcome are well documented, whereas the impact of hyperoxemia is unclear. The primary aim of this study was to assess the episodes of hypoxemia and hyperoxemia in patients with ABI during the intensive care unit (ICU) stay and to determine their association with in-hospital mortality. The secondary aim was to identify the optimal thresholds of arterial partial pressure of oxygen (PaO2) predicting in-hospital mortality. METHODS: We conducted a secondary analysis of a prospective multicenter observational cohort study. Adult patients with ABI (traumatic brain injury, subarachnoid aneurysmal hemorrhage, intracranial hemorrhage, ischemic stroke) with available data on PaO2 during the ICU stay were included. Hypoxemia was defined as PaO2 < 80 mm Hg, normoxemia was defined as PaO2 between 80 and 120 mm Hg, mild/moderate hyperoxemia was defined as PaO2 between 121 and 299 mm Hg, and severe hyperoxemia was defined as PaO2 levels ≥ 300 mm Hg. RESULTS: A total of 1,407 patients were included in this study. The mean age was 52 (±18) years, and 929 (66%) were male. Over the ICU stay, the fractions of patients in the study cohort who had at least one episode of hypoxemia, mild/moderate hyperoxemia, and severe hyperoxemia were 31.3%, 53.0%, and 1.7%, respectively. PaO2 values below 92 mm Hg and above 156 mm Hg were associated with an increased probability of in-hospital mortality. Differences were observed among subgroups of patients with ABI, with consistent effects only seen in patients without traumatic brain injury. CONCLUSIONS: In patients with ABI, hypoxemia and mild/moderate hyperoxemia were relatively frequent. Hypoxemia and hyperoxemia during ICU stay may influence in-hospital mortality. However, the small number of oxygen values collected represents a major limitation of the study.

Incidence and Outcomes of Acute Respiratory Distress Syndrome in Brain-Injured Patients Receiving Invasive Ventilation: A Secondary Analysis of the ENIO Study.

Background: Acute respiratory distress syndrome (ARDS) is an important pulmonary complication in brain-injured patients receiving invasive mechanical ventilation (IMV). We aimed to evaluate the incidence and association between ARDS and clinical outcomes in patients with different forms of acute brain injury requiring IMV in the intensive care unit (ICU). Methods: This was a preplanned secondary analysis of a prospective, multicenter, international cohort study (NCT03400904). We included brain-injured patients receiving IMV for ≥ 24 h. ARDS was the main exposure of interest and was identified during index ICU admission using the Berlin definition. We examined the incidence and adjusted association of ARDS with ICU mortality, ICU length of stay, duration of IMV, and extubation failure. Outcomes were evaluated using mixed-effect logistic regression and cause-specific Cox proportional hazards models. Results: 1492 patients from 67 hospitals and 16 countries were included in the analysis, of whom 137 individuals developed ARDS (9.2% of overall cohort). Across countries, the median ARDS incidence was 5.1% (interquartile range [IQR] 0-10; range 0-27.3). ARDS was associated with increased ICU mortality (adjusted odds ratio (OR) 2.66; 95% confidence interval [CI], 1.29-5.48), longer ICU length of stay (adjusted hazard ratio [HR] 0.59; 95% CI, 0.48-0.73), and longer duration of IMV (adjusted HR 0.54; 95% CI, 0.44-0.67). The association between ARDS and extubation failure approached statistical significance (adjusted HR 1.48; 95% CI 0.99-2.21). Higher ARDS severity was associated with incrementally longer ICU length of stay and longer cumulative duration of IMV. Findings remained robust in a sensitivity analysis evaluating the magnitude of unmeasured confounding. Conclusions: In this cohort of acutely brain-injured patients, the incidence of ARDS was similar to that reported in other mixed cohorts of critically ill patients. Development of ARDS was associated with worse outcomes.

Cognitive Motor Dissociation: Gap Analysis and Future Directions.

BACKGROUND: Patients with disorders of consciousness who are behaviorally unresponsive may demonstrate volitional brain responses to motor imagery or motor commands detectable on functional magnetic resonance imaging or electroencephalography. This state of cognitive motor dissociation (CMD) may have prognostic significance. METHODS: The Neurocritical Care Society's Curing Coma Campaign identified an international group of experts who convened in a series of monthly online meetings between September 2021 and April 2023 to examine the science of CMD and identify key knowledge gaps and unmet needs. RESULTS: The group identified major knowledge gaps in CMD research: (1) lack of information about patient experiences and caregiver accounts of CMD, (2) limited epidemiological data on CMD, (3) uncertainty about underlying mechanisms of CMD, (4) methodological variability that limits testing of CMD as a biomarker for prognostication and treatment trials, (5) educational gaps for health care personnel about the incidence and potential prognostic relevance of CMD, and (6) challenges related to identification of patients with CMD who may be able to communicate using brain-computer interfaces. CONCLUSIONS: To improve the management of patients with disorders of consciousness, research efforts should address these mechanistic, epidemiological, bioengineering, and educational gaps to enable large-scale implementation of CMD assessment in clinical practice.

Optimal Design of Clinical Trials Involving Persons with Disorders of Consciousness.

BACKGROUND: Limited data exist regarding the optimal clinical trial design for studies involving persons with disorders of consciousness (DoC), and only a few therapies have been tested in high-quality clinical trials. To address this, the Curing Coma Campaign Clinical Trial Working Group performed a gap analysis on the current state of clinical trials in DoC to identify the optimal clinical design for studies involving persons with DoC. METHODS: The Curing Coma Campaign Clinical Trial Working Group was divided into three subgroups to (1) review clinical trials involving persons with DoC, (2) identify unique challenges in the design of clinical trials involving persons with DoC, and (3) recommend optimal clinical trial designs for DoC. RESULTS: There were 3055 studies screened, and 66 were included in this review. Several knowledge gaps and unique challenges were identified. There is a lack of high-quality clinical trials, and most data regarding patients with DoC are based on observational studies focusing on patients with traumatic brain injury and cardiac arrest. There is a lack of a structured long-term outcome assessment with significant heterogeneity in the methodology, definitions of outcomes, and conduct of studies, especially for long-term follow-up. Another major barrier to conducting clinical trials is the lack of resources, especially in low-income countries. Based on the available data, we recommend incorporating trial designs that use master protocols, sequential multiple assessment randomized trials, and comparative effectiveness research. Adaptive platform trials using a multiarm, multistage approach offer substantial advantages and should make use of biomarkers to assess treatment responses to increase trial efficiency. Finally, sound infrastructure and international collaboration are essential to facilitate the conduct of trials in patients with DoC. CONCLUSIONS: Conduct of trials in patients with DoC should make use of master protocols and adaptive design and establish international registries incorporating standardized assessment tools. This will allow the establishment of evidence-based practice recommendations and decrease variations in care.

Nocardia species distribution and antimicrobial susceptibility within Australia.

BACKGROUND: Nocardia is a ubiquitous saprophyte capable of causing human disease. Disease is primarily respiratory or cutaneous, usually acquired via inhalation or inoculation. Under the influence of environmental and host factors, Nocardia incidence and species distribution demonstrate geographical variation. AIMS: To examine for differences in Nocardia incidence within Western Australia (WA) and analyse species distribution in the context of prior published studies. To analyse antibiogram data from a nationwide passive antimicrobial resistance surveillance program. METHODS: Retrospective extraction of laboratory data for Western Australian Nocardia isolates over a 21-year period. Analysis of Nocardia antimicrobial susceptibility testing data submitted to the Australian Passive Antimicrobial Resistance Surveillance (APAS) program between 2005 and 2022. RESULTS: Nine hundred sixty WA isolates were identified, giving an annual incidence of 3.03 per 100 000 population with apparent latitudinal variation. The four most common species identified within WA and amongst APAS isolates were N. nova, N. cyriacigeorgica, N. brasiliensis and N. farcinica. APAS data demonstrated that all species exhibited high rates of susceptibility to linezolid (100%) and trimethoprim-sulfamethoxazole (98%). Amikacin (>90% susceptibility for all species except N. transvalensis) was the next most active parenteral agent, superior to both carbapenems and third-generation cephalosporins. Susceptibility to oral antimicrobials (other than linezolid) demonstrated significant interspecies variation. CONCLUSIONS: We demonstrate geographical variation in the distribution of Nocardia incidence. Four species predominate in the Australian setting, and nationwide data confirm a high in vitro susceptibility to trimethoprim-sulphamethoxazole and linezolid, justifying their ongoing role as part of first-line empiric therapy.

Development of a core outcome set for ventilation trials in neurocritical care patients with acute brain injury: protocol for a Delphi consensus study of international stakeholders.

INTRODUCTION: There is little consensus and high heterogeneity on the optimal set of relevant clinical outcomes in research studies regarding extubation in neurocritical care patients with brain injury undergoing mechanical ventilation. The aims of this study are to: (1) develop a core outcome set (COS) and (2) reach consensus on a hierarchical composite endpoint for such studies. METHODS AND ANALYSIS: The study will include a broadly representative, international panel of stakeholders with research and clinical expertise in this field and will involve four stages: (1) a scoping review to generate an initial list of outcomes represented in the literature, (2) an investigator meeting to review the outcomes for inclusion in the Delphi surveys, (3) four rounds of online Delphi consensus-building surveys and (4) online consensus meetings to finalise the COS and hierarchical composite endpoint. ETHICS AND DISSEMINATION: This study received ethical approval from the French Society of Anesthesia and Critical Care Medicine Institutional Review Board (SFAR CERAR-IRB 00010254-2023-029). The study results will be disseminated through communication to stakeholders, publication in a peer-reviewed journal, and presentations at conferences. TRIAL REGISTRATION NUMBER: This study is registered with the Core Outcome Measures in Effectiveness Trials (COMET) Initiative.

Mining the contribution of intensive care clinical course to outcome after traumatic brain injury.

Existing methods to characterise the evolving condition of traumatic brain injury (TBI) patients in the intensive care unit (ICU) do not capture the context necessary for individualising treatment. Here, we integrate all heterogenous data stored in medical records (1166 pre-ICU and ICU variables) to model the individualised contribution of clinical course to 6-month functional outcome on the Glasgow Outcome Scale -Extended (GOSE). On a prospective cohort (n = 1550, 65 centres) of TBI patients, we train recurrent neural network models to map a token-embedded time series representation of all variables (including missing values) to an ordinal GOSE prognosis every 2 h. The full range of variables explains up to 52% (95% CI: 50-54%) of the ordinal variance in functional outcome. Up to 91% (95% CI: 90-91%) of this explanation is derived from pre-ICU and admission information (i.e., static variables). Information collected in the ICU (i.e., dynamic variables) increases explanation (by up to 5% [95% CI: 4-6%]), though not enough to counter poorer overall performance in longer-stay (>5.75 days) patients. Highest-contributing variables include physician-based prognoses, CT features, and markers of neurological function. Whilst static information currently accounts for the majority of functional outcome explanation after TBI, data-driven analysis highlights investigative avenues to improve the dynamic characterisation of longer-stay patients. Moreover, our modelling strategy proves useful for converting large patient records into interpretable time series with missing data integration and minimal processing.

Common Data Elements for Disorders of Consciousness: Recommendations from the Working Group on Neuroimaging.

BACKGROUND: Over the past 5 decades, advances in neuroimaging have yielded insights into the pathophysiologic mechanisms that cause disorders of consciousness (DoC) in patients with severe brain injuries. Structural, functional, metabolic, and perfusion imaging studies have revealed specific neuroanatomic regions, such as the brainstem tegmentum, thalamus, posterior cingulate cortex, medial prefrontal cortex, and occipital cortex, where lesions correlate with the current or future state of consciousness. Advanced imaging modalities, such as diffusion tensor imaging, resting-state functional magnetic resonance imaging (fMRI), and task-based fMRI, have been used to improve the accuracy of diagnosis and long-term prognosis, culminating in the endorsement of fMRI for the clinical evaluation of patients with DoC in the 2018 US (task-based fMRI) and 2020 European (task-based and resting-state fMRI) guidelines. As diverse neuroimaging techniques are increasingly used for patients with DoC in research and clinical settings, the need for a standardized approach to reporting results is clear. The success of future multicenter collaborations and international trials fundamentally depends on the implementation of a shared nomenclature and infrastructure. METHODS: To address this need, the Neurocritical Care Society's Curing Coma Campaign convened an international panel of DoC neuroimaging experts to propose common data elements (CDEs) for data collection and reporting in this field. RESULTS: We report the recommendations of this CDE development panel and disseminate CDEs to be used in neuroimaging studies of patients with DoC. CONCLUSIONS: These CDEs will support progress in the field of DoC neuroimaging and facilitate international collaboration.

Association of Noninvasive Respiratory Support with Extubation Outcomes in Brain-injured Patients Receiving Mechanical Ventilation: A Secondary Analysis of the ENIO Prospective Observational Study.

Rationale: Noninvasive respiratory support using a high-flow nasal cannula (HFNC) or noninvasive positive pressure ventilation (NIPPV) can decrease the risk of reintubation in patients being liberated from mechanical ventilation, but effects in patients with acute brain injury (ABI) are unknown. Objectives: To evaluate the association between postextubation noninvasive respiratory support and reintubation in patients with ABI being liberated from mechanical ventilation. Methods: This was a secondary analysis of a prospective, observational study of mechanically ventilated patients with ABI (clinicaltrials.gov identifier NCT03400904). The primary endpoint was reintubation during ICU admission. We used mixed-effects logistic regression models with patient-level covariates and random intercepts for hospital and country to evaluate the association between prophylactic (i.e., planned) HFNC or NIPPV and reintubation. Measurements and Main Results: 1,115 patients were included from 62 hospitals and 19 countries, of whom 267 received HFNC or NIPPV following extubation (23.9%). Compared with conventional oxygen therapy, neither prophylactic HFNC nor NIPPV was associated with decreased odds of reintubation (respectively, odds ratios of 0.97 [95% confidence interval, 0.54-1.73] and 0.63 [0.30-1.32]). Findings remained consistent in sensitivity analyses accounting for alternate adjustment procedures, missing data, shorter time frames of the primary endpoint, and competing risks precluding reintubation. In a Bayesian analysis using skeptical and data-driven priors, the probabilities of reduced reintubation ranged from 17% to 34% for HFNC and from 46% to 74% for NIPPV. Conclusions: In a large cohort of brain-injured patients undergoing liberation from mechanical ventilation, prophylactic use of HFNC and NIPPV were not associated with reintubation. Prospective trials are needed to confirm treatment effects in this population. Primary study registered with www.clinicaltrials.gov (NCT03400904).