Prediction of outcome utilizing both physiological and biochemical parameters in severe head injury

Multivariate modeling and prediction of cerebral physiology in acute traumatic neural injury: A scoping review

Traumatic brain injury (TBI) poses a significant global public health challenge necessitating a profound understanding of cerebral physiology. The dynamic nature of TBI demands sophisticated methodologies for modeling and predicting cerebral signals to unravel intricate pathophysiology and predict secondary injury mechanisms prior to their occurrence. In this comprehensive scoping review, we focus specifically on multivariate cerebral physiologic signal analysis in the context of multi-modal monitoring (MMM) in TBI, exploring a range of techniques including multivariate statistical time-series models and machine learning algorithms. Conducting a comprehensive search across databases yielded 7 studies for evaluation, encompassing diverse cerebral physiologic signals and parameters from TBI patients. Among these, five studies concentrated on modeling cerebral physiologic signals using statistical time-series models, while the remaining two studies primarily delved into intracranial pressure (ICP) prediction through machine learning models. Autoregressive models were predominantly utilized in the modeling studies. In the context of prediction studies, logistic regression and Gaussian processes (GP) emerged as the predominant choice in both research endeavors, with their performance being evaluated against each other in one study and other models such as random forest, and decision tree in the other study. Notably among these models, random forest model, an ensemble learning approach, demonstrated superior performance across various metrics. Additionally, a notable gap was identified concerning the absence of studies focusing on prediction for multivariate outcomes. This review addresses existing knowledge gaps and sets the stage for future research in advancing cerebral physiologic signal analysis for neurocritical care improvement.

Using metabolomics to predict severe traumatic brain injury outcome (GOSE) at 3 and 12 months

BACKGROUND

Prognostication is very important to clinicians and families during the early management of severe traumatic brain injury (sTBI), however, there are no gold standard biomarkers to determine prognosis in sTBI. As has been demonstrated in several diseases, early measurement of serum metabolomic profiles can be used as sensitive and specific biomarkers to predict outcomes.

METHODS

We prospectively enrolled 59 adults with sTBI (Glasgow coma scale, GCS ≤ 8) in a multicenter Canadian TBI (CanTBI) study. Serum samples were drawn for metabolomic profiling on the 1st and 4th days following injury. The Glasgow outcome scale extended (GOSE) was collected at 3- and 12-months post-injury. Targeted direct infusion liquid chromatography-tandem mass spectrometry (DI/LC-MS/MS) and untargeted proton nuclear magnetic resonance spectroscopy (¹H-NMR) were used to profile serum metabolites. Multivariate analysis was used to determine the association between serum metabolomics and GOSE, dichotomized into favorable (GOSE 5-8) and unfavorable (GOSE 1-4), outcomes.

RESULTS

Serum metabolic profiles on days 1 and 4 post-injury were highly predictive (Q² > 0.4-0.5) and highly accurate (AUC > 0.99) to predict GOSE outcome at 3- and 12-months post-injury and mortality at 3 months. The metabolic profiles on day 4 were more predictive (Q² > 0.55) than those measured on day 1 post-injury. Unfavorable outcomes were associated with considerable metabolite changes from day 1 to day 4 compared to favorable outcomes. Increased lysophosphatidylcholines, acylcarnitines, energy-related metabolites (glucose, lactate), aromatic amino acids, and glutamate were associated with poor outcomes and mortality.

DISCUSSION

Metabolomic profiles were strongly associated with the prognosis of GOSE outcome at 3 and 12 months and mortality following sTBI in adults. The metabolic phenotypes on day 4 post-injury were more predictive and significant for predicting the sTBI outcome compared to the day 1 sample. This may reflect the larger contribution of secondary brain injury (day 4) to sTBI outcome. Patients with unfavorable outcomes demonstrated more metabolite changes from day 1 to day 4 post-injury. These findings highlighted increased concentration of neurobiomarkers such as N-acetylaspartate (NAA) and tyrosine, decreased concentrations of ketone bodies, and decreased urea cycle metabolites on day 4 presenting potential metabolites to predict the outcome. The current findings strongly support the use of serum metabolomics, that are shown to be better than clinical data, in determining prognosis in adults with sTBI in the early days post-injury. Our findings, however, require validation in a larger cohort of adults with sTBI to be used for clinical practice.

Chinese Head Trauma Data Bank: Effect of Gender on the Outcome of Patients With Acute Traumatic Brain Injury

Gender may be related with the outcome of patients with acute traumatic brain injury (TBI). We explored the effect of gender on the outcome of 7145 patients with acute TBI. There was no statistical difference between male and female sex in the causes of trauma, age, Glasgow Coma Scale score, computed tomgraphy findings, and surgical management. The mortality of 7145 patients with acute TBI in males and females was 7.48% and 7.22%, respectively, with the corresponding unfavorable outcomes of 16.05% and 17.23%, respectively (p > 0.05 in both cases). The mortality of 1626 patients with severe TBI in males and females was 19.68% and 20.72%, respectively, with the corresponding unfavorable outcomes of 46.96% and 48.85%, respectively (p > 0.05 in both cases). Our data suggest that sex does not play a role in the outcome of patients with acute TBI.

Role of Intraoperative ICP And CPP Measurement for Predicting Surgical Outcome in Severe Traumatic Brain Injury

Introduction Traumatic brain injury (TBI) is one of the leading causes of mortality and disability worldwide, and optimizing the management of these patients is a continuing challenge. Intraoperative intracranial pressure (ICP) and cerebral perfusion pressure (CPP) were evaluated for use as prognostic indicators after surgery for severe TBI. Although ICP and CPP monitoring is standard postsurgery treatment for TBI, very few studies have reported the use of ICP and CPP values monitored during surgery.

Objectives The objectives of this study were to evaluate the use of intraoperative ICP and CPP values as prognostic indicators and as subjective guidelines for managing severe TBI.

Materials and Methods All patients with severe TBI who underwent surgical decompression and ICP monitoring intraoperatively were included in our study from 2017 to 2018. We measured ICP and CPP values after creation of the first burr hole, after hematoma evacuation, and after wound closure.

Results From the analysis of receiver-operated characteristic (ROC) curves, we observed that ICP initial (cutoff > 28 mm Hg) and CPP initial (cutoff < 44.5 mm Hg) are the best predictors of unfavorable outcomes. Favorable outcome (Glasgow outcome scale [GOS] 4 and 5) and unfavorable outcome (GOS 1–3) after 6 months were achieved in 64.1 and 35.8% of patients, respectively. There was significant difference between the ICP and CPP values which are measured after the first burrhole, after hematoma evacuation, and after scalp closure in both favorable and unfavorable outcomes. The highest positive Pearson’s correlation coefficient is found between GOS and ICP and CPP after first burr hole.

Conclusion Monitoring ICP and CPP during surgery improves management in patients with severe TBI and provides an early prognostic indicator in such patients.

A Critical Review for Developing Accurate and Dynamic Predictive Models Using Machine Learning Methods in Medicine and Health Care

Recently, Artificial Intelligence (AI) has been used widely in medicine and health care sector. In machine learning, the classification or prediction is a major field of AI. Today, the study of existing predictive models based on machine learning methods is extremely active. Doctors need accurate predictions for the outcomes of their patients' diseases. In addition, for accurate predictions, timing is another significant factor that influences treatment decisions. In this paper, existing predictive models in medicine and health care have critically reviewed. Furthermore, the most famous machine learning methods have explained, and the confusion between a statistical approach and machine learning has clarified. A review of related literature reveals that the predictions of existing predictive models differ even when the same dataset is used. Therefore, existing predictive models are essential, and current methods must be improved.

Sleep Features on Continuous Electroencephalography Predict Rehabilitation Outcomes After Severe Traumatic Brain Injury

OBJECTIVE

Sleep characteristics detected by electroencephalography (EEG) may be predictive of neurological recovery and rehabilitation outcomes after traumatic brain injury (TBI). We sought to determine whether sleep features were associated with greater access to rehabilitation therapies and better functional outcomes after severe TBI.

METHODS

We retrospectively reviewed records of patients admitted with severe TBI who underwent 24 or more hours of continuous EEG (cEEG) monitoring within 14 days of injury for sleep elements and ictal activity. Patient outcomes included discharge disposition and modified Rankin Scale (mRS).

RESULTS

A total of 64 patients underwent cEEG monitoring for a mean of 50.6 hours. Status epilepticus or electrographic seizures detected by cEEG were associated with poor outcomes (death or discharge to skilled nursing facility). Sleep characteristics were present in 19 (30%) and associated with better outcome (89% discharged to home/acute rehabilitation; P = .0002). Lack of sleep elements on cEEG correlated with a poor outcome or mRS > 4 at hospital discharge (P = .012). Of those patients who were transferred to skilled nursing/acute rehabilitation, sleep architecture on cEEG associated with a shorter inpatient hospital stay (20 days vs 27 days) and earlier participation in therapy (9.8 days vs 13.2 days postinjury). Multivariable analyses indicated that sleep features on cEEG predicted functional outcomes independent of admission Glasgow Coma Scale and ictal-interictal activity.

CONCLUSION

The presence of sleep features in the acute period after TBI indicates earlier participation in rehabilitative therapies and a better functional recovery. By contrast, status epilepticus, other ictal activity, or absent sleep architecture may portend a worse prognosis. Whether sleep elements detected by EEG predict long-term prognosis remains to be determined.

Utilization of temporal information for intracranial pressure development trend forecasting in traumatic brain injury

Objective. Our primary objective is to demonstrate and statistically justify that forecasting models that utilize temporal information of the historical readings of ICP and related parameters are superior, in terms of performance, compared with models that do not make use of temporal information.

Microdialysis in the neurocritical care unit

Effective monitoring is critical for neurologically compromised patients, and several techniques are available. One of these tools, cerebral microdialysis (MD), was designed to detect derangements in cerebral metabolism. Although this monitoring device began as a research instrument, favorable results and utility have broadened its clinical applications. Combined with other brain monitoring techniques, MD can be used to estimate cerebral vulnerability, to assess tissue outcome, and possibly to prevent secondary ischemic injury by guiding therapy. This article reviews the literature regarding the past, present, and future uses of MD along with its advantages and disadvantages in the intensive care unit setting.

Analysis of Intracranial Pressure

The monitoring of intracranial pressure (ICP) is an important tool in medicine for its ability to portray the brain’s compliance status. The bedside monitor displays the ICP waveform and intermittent mean values to guide physicians in the management of patients, particularly those having sustained a traumatic brain injury. Researchers in the fields of engineering and physics have investigated various mathematical analysis techniques applicable to the waveform in order to extract additional diagnostic and prognostic information, although they largely remain limited to research applications. The purpose of this review is to present the current techniques used to monitor and interpret ICP and explore the potential of using advanced mathematical techniques to provide information about system perturbations from states of homeostasis. We discuss the limits of each proposed technique and we propose that nonlinear analysis could be a reliable approach to describe ICP signals over time, with the fractal dimension as a potential predictive clinically meaningful biomarker. Our goal is to stimulate translational research that can move modern analysis of ICP using these techniques into widespread practical use, and to investigate to the clinical utility of a tool capable of simplifying multiple variables obtained from various sensors.

'Long' pressure reactivity index (L-PRx) as a measure of autoregulation correlates with outcome in traumatic brain injury patients

BACKGROUND

Cerebral autoregulation and, consequently, cerebrovascular pressure reactivity, can be disturbed after traumatic brain injury (TBI). Continuous monitoring of autoregulation has shown its clinical importance as an independent predictor of neurological outcome. The cerebral pressure reactivity index (PRx) reflects that changes in seconds of cerebrovascular reactivity have prognostic significance. Using an alternative algorithm similar to PRx, we investigate whether the utilization of lower-frequency changes of the order of minutes of mean arterial blood pressure (MAP) and intracranial pressure (ICP) could have a prognostic value in TBI patients.

MATERIALS AND METHODS

Head-injured patients requiring continued advanced multimodal monitoring, including hemodynamic, ICP and microdialysis (MD) monitoring, were analyzed retrospectively. A low-frequency sample pressure reactivity index (L-PRx) was calculated, using 20-min averages of MAP and ICP data as a linear Pearson's correlation. The mean values per patient were correlated to outcome at 6 months after injury. Differences of monitoring parameters between non-survivors and survivors were compared.

RESULTS

A total of 29 patients (mean age 37.2 years, 26 males) suffering from TBI were monitored for a mean of 109.6 h (16-236 h, SD ± 60.4). Mean L-PRx was found to be of 0.1 (-0.2 to 0.6, SD ± 0.20), six patients presented impaired (>0.2) values. The averaged L-PRx correlated significantly with ICP (r = 0.467, p = 0.011) and 6-month outcome (r = -0.556, p = 0.002). Significant statistical differences were found in L-PRx, cerebral perfusion pressure (CPP), lactate, and lactate-pyruvate ratio when comparing patients who died (n = 5) and patients who survived.

CONCLUSIONS

L-PRx correlates with the 6-month outcome in TBI patients. Very slow changes of MAP and ICP may contain important autoregulation information. L-PRx may be an alternative algorithm for the estimation of cerebral autoregulation and clinical prognosis.

Go green! Reusing brain monitoring data containing missing values: a feasibility study with traumatic brain injury patients

BACKGROUND

Despite the wealth of information carried, periodic brain monitoring data are often incomplete with a significant amount of missing values. Incomplete monitoring data are usually discarded to ensure purity of data. However, this approach leads to the loss of statistical power, potentially biased study and a great waste of resources. Thus, we propose to reuse incomplete brain monitoring data by imputing the missing values - a green solution! To support our proposal, we have conducted a feasibility study to investigate the reusability of incomplete brain monitoring data based on the estimated imputation error.

MATERIALS AND METHODS

Seventy-seven patients, who underwent invasive monitoring of ICP, MAP, PbtO (2) and brain temperature (BTemp) for more than 24 consecutive hours and were connected to a bedside computerized system, were selected for the study. In the feasibility study, the imputation error is experimentally assessed with simulated missing values and 17 state-of-the-art predictive methods. A framework is developed for neuroclinicians and neurosurgeons to determine the best re-usage strategy and predictive methods based on our feasibility study.

RESULTS/CONCLUSION

The monitoring data of MAP and BTemp are more reliable for reuse than ICP and PbtO (2); and, for ICP and PbtO (2) data, a more cautious re-usage strategy should be employed. We also observe that, for the scenarios tested, the lazy learning method, K-STAR, and the tree-based method, M5P, are consistently 2 of the best among the 17 predictive methods investigated in this study.

[Severe traumatic brain injury]

Traumatic brain injury is a leading cause of morbidity and mortality, especially under 45 years of age. The primary brain injury occurs at the moment of trauma and is defined by the direct damage to tissue. In contrast, secondary brain injury develops over time and is accessible to therapeutic interventions. Patients with severe traumatic brain injury have to be transferred to a specialized trauma centre in order to perform appropriate diagnostic and therapeutic procedures. These include surgical management of lesions (e.g. haematoma evacuation) as well as specific neurointensive care. Neurointensive care medicine principles such as treatment of increased intracranial pressure and advanced invasive neuromonitoring of brain tissue have to be followed.

Chinese Head Trauma Data Bank: effect of hyperthermia on the outcome of acute head trauma patients

Hyperthermia may accentuate the detrimental consequences of brain injury and worsen the outcome of patients with acute head trauma, especially severe traumatic brain injury (TBI). We explored the effect of different magnitudes and durations of hyperthermia in the first 3 days after injury on the outcome of 7145 patients with acute head trauma, including 1626 with severe TBI. The differences in mortality and unfavorable outcome between the normothermia group, mild fever group, moderate fever group, and high fever group were statistically significant (p<0.001). The mortality and unfavorable outcome of severe TBI patients in the groups also differed significantly (p<0.001). The mortality and unfavorable outcome of patients with 1 day, 2 days, and 3 days of high fever were significantly increased (p<0.01). Our data strongly indicate that both degree and duration of early post-trauma hyperthermia are closely correlated with the outcome of acute TBI patients, especially severely injured ones, which indicates that hyperthermia may play a detrimental role in the delayed mechanisms of damage after acute TBI. Prevention of early hyperthermia after acute head trauma is therefore essential to the management of TBI patients.

Analyses of cerebral microdialysis in patients with traumatic brain injury: relations to intracranial pressure, cerebral perfusion pressure and catheter placement

BACKGROUND

Cerebral microdialysis (MD) is used to monitor local brain chemistry of patients with traumatic brain injury (TBI). Despite an extensive literature on cerebral MD in the clinical setting, it remains unclear how individual levels of real-time MD data are to be interpreted. Intracranial pressure (ICP) and cerebral perfusion pressure (CPP) are important continuous brain monitors in neurointensive care. They are used as surrogate monitors of cerebral blood flow and have an established relation to outcome. The purpose of this study was to investigate the relations between MD parameters and ICP and/or CPP in patients with TBI.

METHODS

Cerebral MD, ICP and CPP were monitored in 90 patients with TBI. Data were extensively analyzed, using over 7,350 samples of complete (hourly) MD data sets (glucose, lactate, pyruvate and glycerol) to seek representations of ICP, CPP and MD that were best correlated. MD catheter positions were located on computed tomography scans as pericontusional or nonpericontusional. MD markers were analyzed for correlations to ICP and CPP using time series regression analysis, mixed effects models and nonlinear (artificial neural networks) computer-based pattern recognition methods.

RESULTS

Despite much data indicating highly perturbed metabolism, MD shows weak correlations to ICP and CPP. In contrast, the autocorrelation of MD is high for all markers, even at up to 30 future hours. Consequently, subject identity alone explains 52% to 75% of MD marker variance. This indicates that the dominant metabolic processes monitored with MD are long-term, spanning days or longer. In comparison, short-term (differenced or Δ) changes of MD vs. CPP are significantly correlated in pericontusional locations, but with less than 1% explained variance. Moreover, CPP and ICP were significantly related to outcome based on Glasgow Outcome Scale scores, while no significant relations were found between outcome and MD.

CONCLUSIONS

The multitude of highly perturbed local chemistry seen with MD in patients with TBI predominately represents long-term metabolic patterns and is weakly correlated to ICP and CPP. This suggests that disturbances other than pressure and/or flow have a dominant influence on MD levels in patients with TBI.