Demystifying the Black Box: The Importance of Interpretability of Predictive Models in Neurocritical Care.

Neurocritical care patients are a complex patient population, and to aid clinical decision-making, many models and scoring systems have previously been developed. More recently, techniques from the field of machine learning have been applied to neurocritical care patient data to develop models with high levels of predictive accuracy. However, although these recent models appear clinically promising, their interpretability has often not been considered and they tend to be black box models, making it extremely difficult to understand how the model came to its conclusion. Interpretable machine learning methods have the potential to provide the means to overcome some of these issues but are largely unexplored within the neurocritical care domain. This article examines existing models used in neurocritical care from the perspective of interpretability. Further, the use of interpretable machine learning will be explored, in particular the potential benefits and drawbacks that the techniques may have when applied to neurocritical care data. Finding a solution to the lack of model explanation, transparency, and accountability is important because these issues have the potential to contribute to model trust and clinical acceptance, and, increasingly, regulation is stipulating a right to explanation for decisions made by models and algorithms. To ensure that the prospective gains from sophisticated predictive models to neurocritical care provision can be realized, it is imperative that interpretability of these models is fully considered.

Evaluation of Software for Automated Measurement of Adherence to ICP-Monitoring Threshold Guideline.

Challenges inherent in clinical guideline development include a long time lag between the key results and incorporation into best practice and the qualitative nature of adherence measurement, meaning it will have no directly measurable impact. To address these issues, a framework has been developed to automatically measure adherence by clinicians in neurological intensive care units to the Brain Trauma Foundation's intracranial pressure (ICP)-monitoring guidelines for severe traumatic brain injury (TBI).The framework processes physiological and treatment data taken from the bedside, standardises the data as a set of process models, then compares these models against similar process models constructed from published guidelines. A similarity metric (i.e. adherence measure) between the two models is calculated, composed of duration and scale of non-adherence.In a pilot clinical validation test, the framework was applied to physiological/treatment data from three TBI patients exhibiting ICP secondary insults at a local neuro-centre where clinical experts coded key clinical interventions/decisions about patient management.The framework identified non-adherence with respect to drug administration in one patient, with a spike in non-adherence due to an inappropriately high dosage; a second patient showed a high severity of guideline non-adherence; and a third patient showed non-adherence due to a low number of associated events and treatment annotations.

Time Series Analysis and Prediction of Intracranial Pressure Using Time-Varying Dynamic Linear Models.

Intracranial pressure (ICP) monitoring is a key clinical tool in the assessment and treatment of patients in a neuro-intensive care unit (neuro-ICU). As such, a deeper understanding of how an individual patient's ICP can be influenced by therapeutic interventions could improve clinical decision-making. A pilot application of a time-varying dynamic linear model was conducted using the BrainIT dataset, a multi-centre European dataset containing temporaneous treatment and vital-sign recordings. The study included 106 patients with a minimum of 27 h of ICP monitoring. The model was trained on the first 24 h of each patient's ICU stay, and then the next 2 h of ICP was forecast. The algorithm enabled switching between three interventional states: analgesia, osmotic therapy and paralysis, with the inclusion of arterial blood pressure, age and gender as exogenous regressors. The overall median absolute error was 2.98 (2.41-5.24) mmHg calculated using all 106 2-h forecasts. This is a novel technique which shows some promise for forecasting ICP with an adequate accuracy of approximately 3 mmHg. Further optimisation is required for the algorithm to become a usable clinical tool.

Use of Direct Intracranial Pressure and Brain Tissue Oxygen Monitoring in Perioperative Management of Patients with Moyamoya Disease.

Intracranial pressure monitoring and brain tissue oxygen monitoring are commonly used in head injury for goal-directed therapies, but there may be more indications for its use. Moyamoya disease involves progressive stenosis of the arterial circulation and formation of collateral vessels that are at risk of hemorrhage. The risk of ischemic events during revascularization surgery and postoperatively is high. Impaired cerebral autoregulation may be one of the factors that are implicated. We present our experience with monitoring of cerebral oxygenation and autoregulation in the pathological hemisphere during the perioperative period in four patients with moyamoya disease.

Telemetric Intracranial Pressure: A Snapshot Does not Give the Full Story.

Telemetric intracranial pressure (ICP) monitors are useful tools in the management of complex hydrocephalus and idiopathic intracranial hypertension (IIH). Clinicians may use them as a "snapshot" screening tool to assess shunt function or ICP. We compared "snapshot" telemetric ICP recordings with extended, in-patient periods of monitoring to determine whether this practice is safe and useful for clinical decision making.

Assessment of Outliers and Detection of Artifactual Network Segments Using Univariate and Multivariate Dispersion Entropy on Physiological Signals.

Network physiology has emerged as a promising paradigm for the extraction of clinically relevant information from physiological signals by moving from univariate to multivariate analysis, allowing for the inspection of interdependencies between organ systems. However, for its successful implementation, the disruptive effects of artifactual outliers, which are a common occurrence in physiological recordings, have to be studied, quantified, and addressed. Within the scope of this study, we utilize Dispersion Entropy (DisEn) to initially quantify the capacity of outlier samples to disrupt the values of univariate and multivariate features extracted with DisEn from physiological network segments consisting of synchronised, electroencephalogram, nasal respiratory, blood pressure, and electrocardiogram signals. The DisEn algorithm is selected due to its efficient computation and good performance in the detection of changes in signals for both univariate and multivariate time-series. The extracted features are then utilised for the training and testing of a logistic regression classifier in univariate and multivariate configurations in an effort to partially automate the detection of artifactual network segments. Our results indicate that outlier samples cause significant disruption in the values of extracted features with multivariate features displaying a certain level of robustness based on the number of signals formulating the network segments from which they are extracted. Furthermore, the deployed classifiers achieve noteworthy performance, where the percentage of correct network segment classification surpasses 95% in a number of experimental setups, with the effectiveness of each configuration being affected by the signal in which outliers are located. Finally, due to the increase in the number of features extracted within the framework of network physiology and the observed impact of artifactual samples in the accuracy of their values, the implementation of algorithmic steps capable of effective feature selection is highlighted as an important area for future research.

Augmentation of Dispersion Entropy for Handling Missing and Outlier Samples in Physiological Signal Monitoring.

Entropy quantification algorithms are becoming a prominent tool for the physiological monitoring of individuals through the effective measurement of irregularity in biological signals. However, to ensure their effective adaptation in monitoring applications, the performance of these algorithms needs to be robust when analysing time-series containing missing and outlier samples, which are common occurrence in physiological monitoring setups such as wearable devices and intensive care units. This paper focuses on augmenting Dispersion Entropy (DisEn) by introducing novel variations of the algorithm for improved performance in such applications. The original algorithm and its variations are tested under different experimental setups that are replicated across heart rate interval, electroencephalogram, and respiratory impedance time-series. Our results indicate that the algorithmic variations of DisEn achieve considerable improvements in performance while our analysis signifies that, in consensus with previous research, outlier samples can have a major impact in the performance of entropy quantification algorithms. Consequently, the presented variations can aid the implementation of DisEn to physiological monitoring applications through the mitigation of the disruptive effect of missing and outlier samples.

Forewarning of hypotensive events using a Bayesian artificial neural network in neurocritical care.

Traumatically brain injured (TBI) patients are at risk from secondary insults. Arterial hypotension, critically low blood pressure, is one of the most dangerous secondary insults and is related to poor outcome in patients. The overall aim of this study was to get proof of the concept that advanced statistical techniques (machine learning) are methods that are able to provide early warning of impending hypotensive events before they occur during neuro-critical care. A Bayesian artificial neural network (BANN) model predicting episodes of hypotension was developed using data from 104 patients selected from the BrainIT multi-center database. Arterial hypotension events were recorded and defined using the Edinburgh University Secondary Insult Grades (EUSIG) physiological adverse event scoring system. The BANN was trained on a random selection of 50% of the available patients (n = 52) and validated on the remaining cohort. A multi-center prospective pilot study (Phase 1, n = 30) was then conducted with the system running live in the clinical environment, followed by a second validation pilot study (Phase 2, n = 49). From these prospectively collected data, a final evaluation study was done on 69 of these patients with 10 patients excluded from the Phase 2 study because of insufficient or invalid data. Each data collection phase was a prospective non-interventional observational study conducted in a live clinical setting to test the data collection systems and the model performance. No prediction information was available to the clinical teams during a patient's stay in the ICU. The final cohort (n = 69), using a decision threshold of 0.4, and including false positive checks, gave a sensitivity of 39.3% (95% CI 32.9-46.1) and a specificity of 91.5% (95% CI 89.0-93.7). Using a decision threshold of 0.3, and false positive correction, gave a sensitivity of 46.6% (95% CI 40.1-53.2) and specificity of 85.6% (95% CI 82.3-88.8). With a decision threshold of 0.3, > 15 min warning of patient instability can be achieved. We have shown, using advanced machine learning techniques running in a live neuro-critical care environment, that it would be possible to give neurointensive teams early warning of potential hypotensive events before they emerge, allowing closer monitoring and earlier clinical assessment in an attempt to prevent the onset of hypotension. The multi-centre clinical infrastructure developed to support the clinical studies provides a solid base for further collaborative research on data quality, false positive correction and the display of early warning data in a clinical setting.

Transcranial bioimpedance measurement in horses: a pilot study.

OBJECTIVE: This pilot study aimed to evaluate the feasibility of transcranial bioimpedance (TCBI) measurement and variability of TCBI values in healthy conscious horses and to study effects of body position and time on TCBI in anaesthetized horses. STUDY DESIGN: Prospective, observational study. ANIMALS: A total of four research horses and 16 client-owned horses presented for surgery. METHODS: After establishing optimal electrode position using computed tomography scans of cadaver heads, TCBI [described using impedance at zero frequency, R0, (Ω)] was measured in four conscious, resting horses to investigate the feasibility and changes in TCBI over time (80 minutes). Data were compared using a paired t test. TCBI was then measured throughout anaesthesia (duration 92 ± 28 minutes) in 16 horses in dorsal and lateral recumbency. Data were analysed using a general linear model; gamma regression was chosen as a model of characteristic impedance [Zc; (Ω)] against time. Data are presented as mean ± standard deviation. RESULTS: No change in R0 was seen in conscious horses (age = 15.3 ± 7.3 years, body mass = 512 ± 38 kg) over 80 minutes. The technique was well tolerated and caused no apparent adverse effects. In 16 horses (age = 7.4 ± 4.7 years; body mass = 479 ± 134 kg) anaesthetized for 92 ± 28 minutes, Zc fell during anaesthesia, decreasing more in horses in lateral recumbency than in horses in dorsal recumbency (p = 0.008). There was no relationship between Zc and body mass or age. CONCLUSIONS AND CLINICAL RELEVANCE: TCBI is readily measured in horses. TCBI did not change with time in conscious horses, but decreased with time in anaesthetized horses; this change was greater in horses in lateral recumbency, indicating that TCBI changes in anaesthetized horses may be related to the effects of recumbency, general anaesthesia, surgery or a combination of these factors.

Transcranial Bioimpedance Measurement as a Non-invasive Estimate of Intracranial Pressure.

OBJECTIVES: We have previously demonstrated a relationship between transcranial bioimpedance (TCB) measurements and intracranial pressure (ICP) in an animal model of raised ICP. The primary objective of this study was to explore the relationship between non-invasive bioelectrical impedance measurements of the brain and skull and ICP in traumatic brain injury (TBI) patients. MATERIALS AND METHODS: Included patients were adults admitted to the Neurological Intensive Care Unit with TBI and undergoing invasive ICP monitoring as part of their routine clinical care. Multi-frequency TCB measurements were performed hourly through bi-temporal electrodes. The bioimpedance parameters of Z c (impedance at the characteristic frequency) and R 0 (resistance to a direct current) were then modelled against ICP using unadjusted and adjusted linear models. RESULTS: One hundred and sixty-eight TCB measurements were available from ten study participants. Using an unadjusted linear modelling approach, there was no significant relationship between measured ICP and Zc or R0. The most significant relationship between ICP and TCB parameters was found by adjusting for multiple patient specific variables and using Zc and R0 normalised per patient (p < 0.0001, r 2 = 0.32). CONCLUSIONS: These pilot results confirm some degree of relationship between TCB parameters and invasively measured ICP. The magnitude of this relationship is small and, on the basis of the current study, TCB is unlikely to provide a clinically useful estimate of ICP in patients admitted with TBI.

Medical Waveform Format Encoding Rules Representation of Neurointensive Care Waveform Data.

OBJECTIVE: Technology in neurointensive care units can collect and store vast amounts of complex patient data. The CHART-ADAPT project is aimed at developing technology that will allow for the collection, analysis and use of these big data at the patient's bedside in neurointensive care units. A requirement of this project is to automatically extract and transfer high-frequency waveform data (e.g. ICP) from monitoring equipment to high performance computing infrastructure for analysis. Currently, no agreed data standard exists in neurointensive care for the description of this type of data. In this pilot study, we investigated the use of Medical Waveform Format Encoding Rules (MFER- www.mfer.org-ISO 11073-92001) as a possible data standard for neurointensive care waveform data. MATERIALS AND METHODS: Several waveform formats were explored (e.g. XML, DICOM waveform) and evaluated for suitability given existing computing infrastructure constraints, e.g. NHS network capacity and the processing capabilities of existing integration software. Key requirements of the format included a compact data size and the use of a recognised standard. The MFER waveform format (ISO/TS 11073-92001) met both requirements. To evaluate the practicality of the MFER waveform format, seven waveform signals (ICP, ECG, ART, CVP, EtCO2, Pleth, Resp) collected over a period of 8 h from a patient at the Institute of Neurological Sciences in Glasgow were converted into MFER waveform format. RESULTS: The MFER waveform format has two main components: sampling information and frame information. Sampling information describes the frequency of the data sampling and the resolution of the data. Frame information describes the data itself; it consists of three elements: data block (the actual data), channel (each type of waveform data occupies a channel) and sequence (the repetition of the data). All seven waveform signals were automatically and successfully converted into the MFER waveform format. One MFER file was created for each minute of data (total of 479 files, 181 KB each). CONCLUSIONS: The MFER waveform format has potential as a lightweight standard for representing high-frequency neurointensive care waveform data. Further work will include a comparison with other waveform data formats and a live trial of using the MFER waveform format to stream patient data over a longer period.

Investigation of the Relationship Between the Burden of Raised ICP and the Length of Stay in a Neuro-Intensive Care Unit.

OBJECTIVES: Raised intracranial pressure (ICP) is well known to be indicative of a poor outcome in traumatic brain injury (TBI). This phenomenon was quantified using a pressure time index (PTI) model of raised ICP burden in a paediatric population. Using the PTI methodology, this pilot study is aimed at investigating the relationship between raised ICP and length of stay (LOS) in adults admitted to a neurological intensive care unit (neuro-ICU). MATERIALS AND METHODS: In 10 patients admitted to the neuro-ICU following TBI, ICP was measured and data from the first 24 h were analysed. The PTI is a bounded area under the curve, where the bound is the threshold limit of interest for the signal. The upper bound of 20 mmHg for ICP is commonly used in clinical practice. To fully investigate the relationship between ICP and LOS, further bounds from 1 to 40 mmHg were used during the PTI calculations. A backwards step Poisson regression model with a log link function was used to find the important thresholds for the prediction of full LOS, measured in hours, in the neuro-ICU. RESULTS: The fit was assessed using a Chi-squared deviance goodness of fit method, which showed a non-significant p value of 0.97, indicating a correctly specified model. The backwards step strategy, minimising the model's Akaike information criteria (AIC) at each change, found that levels 13-16, 18 and 20-21 combined were the most predictive. From this model it can be shown that for every 1 mmHg/h increase in burden, as measured by the PTI, the LOS has a base exponential increase of approximately 2 h, with the largest increases in the LOS given at the 20-mmHg threshold level. CONCLUSIONS: This model demonstrates that increased duration of raised ICP in the early monitoring period is associated with a prolonged LOS in the neuro-ICU. Further validation of the PTI model in a larger cohort is currently underway as part of the CHART-ADAPT project. Second, further adjustment with known predictors of outcome, such as severity of injury, would help to improve the fit and validate the current combination of predictors.

Visualizing Cerebrovascular Autoregulation Insults and Their Association with Outcome in Adult and Paediatric Traumatic Brain Injury.

OBJECTIVE: The aim of this study is to assess visually the impact of duration and intensity of cerebrovascular autoregulation insults on 6-month neurological outcome in severe traumatic brain injury. MATERIAL AND METHODS: Retrospective analysis of prospectively collected minute-by-minute intracranial pressure (ICP) and mean arterial blood pressure data of 259 adult and 99 paediatric traumatic brain injury (TBI) patients from multiple European centres. The relationship of the 6-month Glasgow Outcome Scale with cerebrovascular autoregulation insults (defined as the low-frequency autoregulation index above a certain threshold during a certain time) was visualized in a colour-coded plot. The analysis was performed separately for autoregulation insults occurring with cerebral perfusion pressure (CPP) below 50 mmHg, with ICP above 25 mmHg and for the subset of adult patients that did not undergo decompressive craniectomy. RESULTS: The colour-coded plots showed a time-intensity-dependent association with outcome for cerebrovascular autoregulation insults in adult and paediatric TBI patients. Insults with a low-frequency autoregulation index above 0.2 were associated with worse outcomes and below -0.6 with better outcomes, with and approximately exponentially decreasing transition curve between the two intensity thresholds. All insults were associated with worse outcomes when CPP was below 50 mmHg or ICP was above 25 mmHg. CONCLUSIONS: The colour-coded plots indicate that cerebrovascular autoregulation is disturbed in a dynamic manner, such that duration and intensity play a role in the determination of a zone associated with better neurological outcome.

Cerebral Perfusion Pressure Variability Between Patients and Between Centres.

INTRODUCTION: The aim of this analysis was to investigate to what extent median cerebral perfusion pressure (CPP) differs between severe traumatic brain injury (TBI) patients and between centres, and whether the 2007 change in CPP threshold in the Brain Trauma Foundation guidelines is reflected in patient data collected at several centres over different time periods. METHODS: Data were collected from the Brain-IT database, a multi-centre project between 2003 and 2005, and from a recent project in four centres between 2009 and 2013. For patients nursed with their head up at 30° and with the blood pressure transducer at atrium level, CPP was corrected by 10 mmHg. Median CPP, interquartile ranges and total CPP ranges over the monitoring time were calculated per patient and per centre. RESULTS: Per-centre medians pre-2007 were situated between 50 and 70 mmHg in 6 out of 16 centres, while 10 centres had medians above 70 mmHg and 4 above 80 mmHg. Post-2007, three out of four centres had medians between 60 and 70 mmHg and one above 80 mmHg. One out of two centres with data pre- and post-2007 shifted from a median CPP of 76 mmHg to 60 mmHg, while the other remained at 68-67 mmHg. CONCLUSIONS: CPP data are characterised by a high inter-individual variability, but the data also suggest differences in CPP policies between centres. The 2007 guideline change may have affected policies towards lower CPP in some centres. Deviations from the guidelines occur in the direction of CPP > 70 mmHg.

Early Detection of Increased Intracranial Pressure Episodes in Traumatic Brain Injury: External Validation in an Adult and in a Pediatric Cohort.

OBJECTIVE: A model for early detection of episodes of increased intracranial pressure in traumatic brain injury patients has been previously developed and validated based on retrospective adult patient data from the multicenter Brain-IT database. The purpose of the present study is to validate this early detection model in different cohorts of recently treated adult and pediatric traumatic brain injury patients. DESIGN: Prognostic modeling. Noninterventional, observational, retrospective study. SETTING AND PATIENTS: The adult validation cohort comprised recent traumatic brain injury patients from San Gerardo Hospital in Monza (n = 50), Leuven University Hospital (n = 26), Antwerp University Hospital (n = 19), Tübingen University Hospital (n = 18), and Southern General Hospital in Glasgow (n = 8). The pediatric validation cohort comprised patients from neurosurgical and intensive care centers in Edinburgh and Newcastle (n = 79). INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: The model's performance was evaluated with respect to discrimination, calibration, overall performance, and clinical usefulness. In the recent adult validation cohort, the model retained excellent performance as in the original study. In the pediatric validation cohort, the model retained good discrimination and a positive net benefit, albeit with a performance drop in the remaining criteria. CONCLUSIONS: The obtained external validation results confirm the robustness of the model to predict future increased intracranial pressure events 30 minutes in advance, in adult and pediatric traumatic brain injury patients. These results are a large step toward an early warning system for increased intracranial pressure that can be generally applied. Furthermore, the sparseness of this model that uses only two routinely monitored signals as inputs (intracranial pressure and mean arterial blood pressure) is an additional asset.

Multivariate projection method to investigate inflammation associated with secondary insults and outcome after human traumatic brain injury: a pilot study.

BACKGROUND: Neuroinflammation has been proposed as a possible mechanism of brain damage after traumatic brain injury (TBI), but no consensus has been reached on the most relevant molecules. Furthermore, secondary insults occurring after TBI contribute to worsen neurological outcome in addition to the primary injury. We hypothesized that after TBI, a specific pattern of cytokines is related to secondary insults and outcome. METHODS: A prospective observational clinical study was performed. Secondary insults by computerized multimodality monitoring system and systemic value of different cytokines were collected and analysed in the first week after intensive care unit admission. Neurological outcome was assessed at 6 months (GOSe). Multivariate projection technique was applied to analyse major sources of variation and collinearity within the cytokines dataset without a priori selecting potential relevant molecules. RESULTS: Twenty-nine severe traumatic brain injury patients undergoing intracranial pressure monitoring were studied. In this pilot study, we demonstrated that after TBI, patients who suffered of prolonged and severe secondary brain damage are characterised by a specific pattern of cytokines. Patients evolving to brain death exhibited higher levels of inflammatory mediators compared to both patients with favorable and unfavorable neurological outcome at 6 months. Raised ICP and low cerebral perfusion pressure occurred in 21 % of good monitoring time. Furthermore, the principal components selected by multivariate projection technique were powerful predictors of neurological outcome. CONCLUSIONS: The multivariate projection method represents a valuable methodology to study neuroinflammation pattern occurring after secondary brain damage in severe TBI patients, overcoming multiple putative interactions between mediators and avoiding any subjective selection of relevant molecules.

Multi-resolution Convolution Methodology for ICP Waveform Morphology Analysis.

Intracranial pressure (ICP) monitoring is a key clinical tool in the assessment and treatment of patients in neurointensive care. ICP morphology analysis can be useful in the classification of waveform features.A methodology for the decomposition of an ICP signal into clinically relevant dimensions has been devised that allows the identification of important ICP waveform types. It has three main components. First, multi-resolution convolution analysis is used for the main signal decomposition. Then, an impulse function is created, with multiple parameters, that can represent any form in the signal under analysis. Finally, a simple, localised optimisation technique is used to find morphologies of interest in the decomposed data.A pilot application of this methodology using a simple signal has been performed. This has shown that the technique works with performance receiver operator characteristic area under the curve values for each of the waveform types: plateau wave, B wave and high and low compliance states of 0.936, 0.694, 0.676 and 0.698, respectively.This is a novel technique that showed some promise during the pilot analysis. However, it requires further optimisation to become a usable clinical tool for the automated analysis of ICP signals.

Identification of Clinically Relevant Groups of Patients Through the Application of Cluster Analysis to a Complex Traumatic Brain Injury Data Set.

In neurological intensive care units (NICUs) we are collecting an ever increasing quantity of data. These range from patient demographics and physiological monitoring to treatment strategies and outcomes. The BrainIT database is an example of this type of rich data source. It contains validated data on 264 patients who suffered traumatic brain injury (TBI) admitted to 22 NICUs in 11 European countries between March 2003 and July 2005 [1, 6].

Automatic Calculation of Hydrostatic Pressure Gradient in Patients with Head Injury: A Pilot Study.

The non-surgical management of patients with traumatic brain injury is the treatment and prevention of secondary insults, such as low cerebral perfusion pressure (CPP). Most clinical pressure monitoring systems measure pressure relative to atmospheric pressure. If a patient is managed with their head tilted up, relative to their arterial pressure transducer, then a hydrostatic pressure gradient (HPG) can act against arterial pressure and cause significant errors in calculated CPP.To correct for HPG, the arterial pressure transducer should be placed level with the intracranial pressure transducer. However, this is not always achieved. In this chapter, we describe a pilot study investigating the application of speckled computing (or "specks") for the automatic monitoring of the patient's head tilt and subsequent automatic calculation of HPG. In future applications this will allow us to automatically correct CPP to take into account any HPG.

Can Optimal Cerebral Perfusion Pressure in Patients with Severe Traumatic Brain Injury Be Calculated Based on Minute-by-Minute Data Monitoring?

BACKGROUND: The concept of CPPopt, a variable cerebral perfusion pressure (CPP) target based on cerebrovascular autoregulatory capacity in severe traumatic brain injury (TBI), is promising. CPPopt calculation is based on the continuous plotting of the pressure reactivity Index (PRx) against CPP and requires processing of waveform quality data. The aim of this study is to investigate whether CPPopt can also be calculated based on minute-by-minute data. METHODS: A low-resolution autoregulation index (LAx) was defined as the minute-by-minute intracranial pressure-mean arterial pressure correlation over varying time intervals. A matrix of LAx-CPP plots was built using different LAx values and varying time windows. CPPopt was calculated as the weighted average of the CPPopt values resulting from each plot. The method was assessed in a database of 21 patients with TBI with 60-Hz data. RESULTS: No significant difference was observed between PRx-based and LAx-based CPPopt values. The new method was able to issue a CPPopt recommendation throughout almost the entire monitoring time. The absolute difference between CPP and CPPopt was inversely associated with survival. CONCLUSION: CPPopt calculation based on standard resolution data compared well with PRx-based CPPopt and may represent a promising alternative method, avoiding the need for waveform quality data capture. Further validation of this new method is required.