Morphological clustering and analysis of continuous intracranial pressure

Peak detection in intracranial pressure signal waveforms: a comparative study

BACKGROUND

The monitoring and analysis of quasi-periodic biological signals such as electrocardiography (ECG), intracranial pressure (ICP), and cerebral blood flow velocity (CBFV) waveforms plays an important role in the early detection of adverse patient events and contributes to improved care management in the intensive care unit (ICU). This work quantitatively evaluates existing computational frameworks for automatically extracting peaks within ICP waveforms.

METHODS

Peak detection techniques based on state-of-the-art machine learning models were evaluated in terms of robustness to varying noise levels. The evaluation was performed on a dataset of ICP signals assembled from 700 h of monitoring from 64 neurosurgical patients. The groundtruth of the peak locations was established manually on a subset of 13, 611 pulses. Additional evaluation was performed using a simulated dataset of ICP with controlled temporal dynamics and noise.

RESULTS

The quantitative analysis of peak detection algorithms applied to individual waveforms indicates that most techniques provide acceptable accuracy with a mean absolute error (MAE) ≤ 10 ms without noise. In the presence of a higher noise level, however, only kernel spectral regression and random forest remain below that error threshold while the performance of other techniques deteriorates. Our experiments also demonstrated that tracking methods such as Bayesian inference and long short-term memory (LSTM) can be applied continuously and provide additional robustness in situations where single pulse analysis methods fail, such as missing data.

CONCLUSION

While machine learning-based peak detection methods require manually labeled data for training, these models outperform conventional signal processing ones based on handcrafted rules and should be considered for peak detection in modern frameworks. In particular, peak tracking methods that incorporate temporal information between successive periods of the signals have demonstrated in our experiments to provide more robustness to noise and temporary artifacts that commonly arise as part of the monitoring setup in the clinical setting.

Analysis of intracranial pressure pulse waveform in studies on cerebrospinal compliance: a narrative review

Continuous monitoring of mean intracranial pressure (ICP) has been an essential part of neurocritical care for more than half a century. Cerebrospinal pressure-volume compensation, i.e. the ability of the cerebrospinal system to buffer changes in volume without substantial increases in ICP, is considered an important factor in preventing adverse effects on the patient's condition that are associated with ICP elevation. However, existing assessment methods are poorly suited to the management of brain injured patients as they require external manipulation of intracranial volume. In the 1980s, studies suggested that spontaneous short-term variations in the ICP signal over a single cardiac cycle, called the ICP pulse waveform, may provide information on cerebrospinal compensatory reserve. In this review we discuss the approaches that have been proposed so far to derive this information, from pulse amplitude estimation and spectral techniques to most recent advances in morphological analysis based on artificial intelligence solutions. Each method is presented with focus on its clinical significance and the potential for application in standard clinical practice. Finally, we highlight the missing links that need to be addressed in future studies in order for ICP pulse waveform analysis to achieve widespread use in the neurocritical care setting.

A Deep Learning-Based Automated Framework for Subpeak Designation on Intracranial Pressure Signals

The intracranial pressure (ICP) signal, as monitored on patients in intensive care units, contains pulses of cardiac origin, where P1 and P2 subpeaks can often be observed. When calculable, the ratio of their relative amplitudes is an indicator of the patient's cerebral compliance. This characterization is particularly informative for the overall state of the cerebrospinal system. The aim of this study is to develop and assess the performances of a deep learning-based pipeline for P2/P1 ratio computation that only takes a raw ICP signal as an input. The output P2/P1 ratio signal can be discontinuous since P1 and P2 subpeaks are not always visible. The proposed pipeline performs four tasks, namely (i) heartbeat-induced pulse detection, (ii) pulse selection, (iii) P1 and P2 designation, and (iv) signal smoothing and outlier removal. For tasks (i) and (ii), the performance of a recurrent neural network is compared to that of a convolutional neural network. The final algorithm is evaluated on a 4344-pulse testing dataset sampled from 10 patient recordings. Pulse selection is achieved with an area under the curve of 0.90, whereas the subpeak designation algorithm identifies pulses with a P2/P1 ratio > 1 with 97.3% accuracy. Although it still needs to be evaluated on a larger number of labeled recordings, our automated P2/P1 ratio calculation framework appears to be a promising tool that can be easily embedded into bedside monitoring devices.

Intracranial pressure for clinicians: it is not just a number

BACKGROUND

Invasive intracranial pressure (ICP) monitoring is a standard practice in severe brain injury cases, where it allows to derive cerebral perfusion pressure (CPP); ICP-tracing can also provide additional information about intracranial dynamics, forecast episodes of intracranial hypertension and set targets for a tailored therapy to prevent secondary brain injury. Nevertheless, controversies about the advantages of an ICP clinical management are still debated.

FINDINGS

This article reviews recent research on ICP to improve the understanding of the topic and uncover the hidden information in this signal that may be useful in clinical practice. Parameters derived from time-domain as well as frequency domain analysis include compensatory reserve, autoregulation estimation, pulse waveform analysis, and behavior of ICP in time. The possibility to predict the outcome and apply a tailored therapy using a personalised perfusion pressure target is also described.

CONCLUSIONS

ICP is a crucial signal to monitor in severely brain injured patients; a bedside computer can empower standard monitoring giving new metrics that may aid in clinical management, establish a personalized therapy, and help to predict the outcome. Continuous collaboration between engineers and clinicians and application of new technologies to healthcare, is vital to improve the accuracy of current metrics and progress towards better care with individualized dynamic targets.

Automatic identification of intracranial pressure waveform during external ventricular drainage clamping: segmentation via wavelet analysis

Objective. The objective of this study is to develop and validate a method for automatically identifying segments of intracranial pressure (ICP) waveform data from external ventricular drainage (EVD) recordings during intermittent drainage and closure.Methods. The proposed method uses time-frequency analysis through wavelets to distinguish periods of ICP waveform in EVD data. By comparing the frequency compositions of the ICP signals (when the EVD system is clamped) and the artifacts (when the system is open), the algorithm can detect short, uninterrupted segments of ICP waveform from the longer periods of non-measurement data. The method involves applying a wavelet transform, calculating the absolute power in a specific range, using Otsu thresholding to automatically identify a threshold, and performing a morphological operation to remove small segments. Two investigators manually graded the same randomly selected one-hour segments of the resulting processed data. Performance metrics were calculated as a percentage.Results. The study analyzed data from 229 patients who had EVD placed following subarachnoid hemorrhage between June 2006 and December 2012. Of these, 155 (67.7%) were female and 62 (27%) developed delayed cerebral ischemia. A total of 45 150 h of data were segmented. 2044 one-hour segments were randomly selected and evaluated by two investigators (MM and DN). Of those, the evaluators agreed on the classification of 1556 one-hour segments. The algorithm was able to correctly identify 86% (1338 h) of ICP waveform data. 8.2% (128 h) of the time the algorithm either partially or fully failed to segment the ICP waveform. 5.4% (84 h) of data, artifacts were mistakenly identified as ICP waveforms (false positives).Conclusion. The proposed algorithm automates the identification of valid ICP waveform segments of waveform in EVD data and thus enables the inclusion in real-time data analysis for decision support. It also standardizes and makes research data management more efficient.

A Scoping Review of Cerebral Doppler Arterial Waveforms in Infants

Cerebral Doppler ultrasound has been an important tool in pediatric diagnostics and prognostics for decades. Although the Doppler spectrum can provide detailed information on cerebral perfusion, the measured spectrum is often reduced to simple numerical parameters. To help pediatric clinicians recognize the visual characteristics of disease-associated Doppler spectra and identify possible areas for future research, a scoping review of primary studies on cerebral Doppler arterial waveforms in infants was performed. A systematic search in three online bibliographic databases yielded 4898 unique records. Among these, 179 studies included cerebral Doppler spectra for at least five infants below 1 y of age. The studies describe variations in the cerebral waveforms related to physiological changes (43%), pathology (62%) and medical interventions (40%). Characteristics were typically reported as resistance index (64%), peak systolic velocity (43%) or end-diastolic velocity (39%). Most studies focused on the anterior (59%) and middle (42%) cerebral arteries. Our review highlights the need for a more standardized terminology to describe cerebral velocity waveforms and for precise definitions of Doppler parameters. We provide a list of reporting variables that may facilitate unambiguous reports. Future studies may gain from combining multiple Doppler parameters to use more of the information encoded in the Doppler spectrum, investigating the full spectrum itself and using the possibilities for long-term monitoring with Doppler ultrasound.

Development of Traumatic Brain Injury Associated Intracranial Hypertension Prediction Algorithms: A Narrative Review

Traumatic intracranial hypertension (tIH) is a common and potentially lethal complication of moderate to severe traumatic brain injury (m-sTBI). It often develops with little warning and is managed reactively with the tiered application of intracranial pressure (ICP)-lowering interventions administered in response to an ICP rising above a set threshold. For over 45 years, a variety of research groups have worked toward the development of technology to allow for the preemptive management of tIH in the hope of improving patient outcomes. In 2022, the first operationalizable tIH prediction system became a reality. With such a system, ICP lowering interventions could be administered prior to the rise in ICP, thus protecting the patient from potentially damaging tIH episodes and limiting the overall ICP burden experienced. In this review, we discuss related approaches to ICP forecasting and IH prediction algorithms, which collectively provide the foundation for the successful development of an operational tIH prediction system. We also discuss operationalization and the statistical assessment of tIH algorithms. This review will be of relevance to clinicians and researchers interested in development of this technology as well as those with a general interest in the bedside application of machine learning (ML) technology.

Cortical atrophy in chronic subdural hematoma from ultra-structures to physical properties

Several theories have tried to elucidate the mechanisms behind the pathophysiology of chronic subdural hematoma (CSDH). However, this process is complex and remains mostly unknown. In this study we performed a retrospective randomised analysis comparing the cortical atrophy of 190 patients with unilateral CSDH, with 190 healthy controls. To evaluate the extent of cortical atrophy, CT scan images were utilised to develop an index that is the ratio of the maximum diameter sum of 3 cisterns divided by the maximum diameter of the skull at the temporal lobe level. Also, we reported, for the first time, the ultrastructural analyses of the CSDH using a combination of immunohistochemistry methods and transmission electron microscopy techniques. Internal validation was performed to confirm the assessment of the different degrees of cortical atrophy. Relative Cortical Atrophy Index (RCA index) refers to the sum of the maximum diameter of three cisterns (insular cistern, longitudinal cerebral fissure and cerebral sulci greatest) with the temporal bones' greatest internal distance. This index, strongly related to age in healthy controls, is positively correlated to the preoperative and post-operative maximum diameter of hematoma and the midline shift in CSDH patients. On the contrary, it negatively correlates to the Karnofsky Performance Status (KPS). The Area Under the Receiver Operating Characteristics (AUROC) showed that RCA index effectively differentiated cases from controls. Immunohistochemistry analysis showed that the newly formed CD-31 positive microvessels are higher in number than the CD34-positive microvessels in the CSDH inner membrane than in the outer membrane. Ultrastructural observations highlight the presence of a chronic inflammatory state mainly in the CSDH inner membrane. Integrating these results, we have obtained an etiopathogenetic model of CSDH. Cortical atrophy appears to be the triggering factor activating the cascade of transendothelial cellular filtration, inflammation, membrane formation and neovascularisation leading to the CSDH formation.

Peak appearance time in pulse waveforms of intracranial pressure and cerebral blood flow velocity

The shape of the pulse waveforms of intracranial pressure (ICP) and cerebral blood flow velocity (CBFV) typically contains three characteristic peaks. It was reported that alterations in cerebral hemodynamics may influence the shape of the pulse waveforms by changing peaks' configuration. However, the changes in peak appearance time (PAT) in ICP and CBFV pulses are only described superficially. We analyzed retrospectively ICP and CBFV signals recorded in traumatic brain injury patients during decrease in ICP induced by hypocapnia (n = 11) and rise in ICP during episodes of ICP plateau waves (n = 8). All three peaks were manually annotated in over 48 thousand individual pulses. The changes in PAT were compared between periods of vasoconstriction (expected during hypocapnia) and vasodilation (expected during ICP plateau waves) and their corresponding baselines. Correlation coefficient (r_S) analysis between mean ICP and mean PATs was performed in each individual recording. Vasodilation prolonged PAT of the first peaks of ICP and CBFV pulses and the third peak of CBFV pulse. It also accelerated PAT of the third peak of ICP pulse. In contrast, vasoconstriction shortened appearance time of the first peaks of ICP and CBFV pulses and the second peak of ICP pulses. Analysis of individual recordings demonstrated positive association between changes in PAT of all three peaks in the CBFV pulse and mean ICP (r_S range: 0.32-0.79 for significant correlations). Further study is needed to test whether PAT of the CBFV pulse may serve as an indicator of changes in ICP-this may open a perspective for non-invasive monitoring of alterations in mean ICP.

Dynamic Intracranial Pressure Waveform Morphology Predicts Ventriculitis

BACKGROUND

Intracranial pressure waveform morphology reflects compliance, which can be decreased by ventriculitis. We investigated whether morphologic analysis of intracranial pressure dynamics predicts the onset of ventriculitis.

METHODS

Ventriculitis was defined as culture or Gram stain positive cerebrospinal fluid, warranting treatment. We developed a pipeline to automatically isolate segments of intracranial pressure waveforms from extraventricular catheters, extract dominant pulses, and obtain morphologically similar groupings. We used a previously validated clinician-supervised active learning paradigm to identify metaclusters of triphasic, single-peak, or artifactual peaks. Metacluster distributions were concatenated with temperature and routine blood laboratory values to create feature vectors. A L2-regularized logistic regression classifier was trained to distinguish patients with ventriculitis from matched controls, and the discriminative performance using area under receiver operating characteristic curve with bootstrapping cross-validation was reported.

RESULTS

Fifty-eight patients were included for analysis. Twenty-seven patients with ventriculitis from two centers were identified. Thirty-one patients with catheters but without ventriculitis were selected as matched controls based on age, sex, and primary diagnosis. There were 1590 h of segmented data, including 396,130 dominant pulses in patients with ventriculitis and 557,435 pulses in patients without ventriculitis. There were significant differences in metacluster distribution comparing before culture-positivity versus during culture-positivity (p < 0.001) and after culture-positivity (p < 0.001). The classifier demonstrated good discrimination with median area under receiver operating characteristic 0.70 (interquartile range 0.55-0.80). There were 1.5 true alerts (ventriculitis detected) for every false alert.

CONCLUSIONS

Intracranial pressure waveform morphology analysis can classify ventriculitis without cerebrospinal fluid sampling.

Analysis of relative changes in pulse shapes of intracranial pressure and cerebral blood flow velocity

Objective.Analysis of relative changes in the shapes of pulse waveforms of intracranial pressure (ICP) and transcranial Doppler cerebral blood flow velocity (CBFV) may provide information on intracranial compliance. We tested this hypothesis, introducing an index named the ratio of pulse slopes (RPS) that is based on inclinations of the ascending parts of the ICP and CBFV pulse waveforms. It has hypothetically a simple interpretation: a value of 1 indicates good compliance and a value less than 1, reduced compliance. Here, we investigated the usefulness of RPS for assessment of intracranial compliance.Approach.ICP and CBFV signals recorded simultaneously in 30 normal-pressure hydrocephalus patients during infusion tests were retrospectively analysed. CBFV was measured in the middle cerebral artery. Changes in RPS during the test were compared with changes in the height ratio of the first and second peak of the ICP pulse (P1/P2) and the shape of the ICP pulse was classified from normal (1) to pathological (4). Values are medians (lower, upper quartiles).Main results.There was a significant correlation between baseline RPS and intracranial elasticity (R = -0.55,p = 0.0018). During the infusion tests, both RPS and P1/P2 decreased with rising ICP [RPS, 0.80 (0.56, 0.92) versus 0.63 (0.44, 0.80),p = 0.00015; P1/P2, 0.58 (0.50, 0.91) versus 0.52 (0.36, 0.71),p = 0.00009] while the ICP pulses became more pathological in shape [class: 3 (2, 3) versus 3 (3, 4),p = 0.04]. The magnitude of the decrease in RPS during infusion was inversely correlated with baseline P1/P2 (R = -0.40,p < 0.03).Significance.During infusion, the slopes of the ascending parts of ICP and CBFV pulses become increasingly divergent with a shift in opposite directions. RPS seems to be a promising methodological tool for monitoring intracranial compliance with no additional volumetric manipulation required.

Foundations of Time Series Analysis

For almost a century, classical statistical methods including exponential smoothing and autoregression integrated moving averages (ARIMA) have been predominant in the analysis of time series (TS) and in the pursuit of forecasting future events from historical data. TS are chronological sequences of observations, and TS data are therefore prevalent in many aspects of clinical medicine and academic neuroscience. With the rise of highly complex and nonlinear datasets, machine learning (ML) methods have become increasingly popular for prediction or pattern detection and within neurosciences, including neurosurgery. ML methods regularly outperform classical methods and have been successfully applied to, inter alia, predict physiological responses in intracranial pressure monitoring or to identify seizures in EEGs. Implementing nonparametric methods for TS analysis in clinical practice can benefit clinical decision making and sharpen our diagnostic armory.

Intracranial pressure analysis software: A mapping study and proposal

Introduction Intracranial pressure (ICP) monitoring and analysis are techniques that are, each year, applied to millions of patients with pathologies with million of patients annually. The detection of the so called A and B-waves, and the analysis of subtle changes in C-waves, which are present in ICP waveform, may indicate decreased intracranial compliance, and may improve the clinical outcome. Despite the advances in the field of computerized data analysis, the visual screening of ICP continues to be the means principally employed to detect these waves. To the best of our knowledge, no review study has addressed automated ICP analysis in sufficient detail and a need to research the state of the art of ICP analysis has, therefore, been identified. Methodology This paper presents a systematic mapping study to provide answers to 7 research questions: publication time, venue and source trends, medical tasks undertaken, research methods used, computational systems developed, validation methodology, tools and systems employed for evaluation and research problems identified. An ICP software prototype is presented and evaluated as a consequence of the results. Results A total of 23 papers, published between 1990 and 2020, were selected from 6 online databases. After analyzing these papers, the following information was obtained: diagnosis and monitoring medical tasks were addressed to the same extent, and the main research method used was evaluation research. Several computational systems were identified in the papers, the main one being image classification, while the main analysis objective was single pulse analysis. Correlation with expert analysis was the most frequent validation method, and few of the papers stated the use of a published dataset. Few authors referred to the tools used to build or evaluate the proposed solutions. The most frequent research problem was the need for new analysis methods. These results have inspired us to propose a software prototype with which provide an automated solution that integrates ICP analysis and monitoring techniques. Conclusions The papers in this study were selected and classified with regard to ICP automated analysis methods. Several research gaps were identified, which the authors of this study have employed as a based on which to recommend future work. Furthermore, this study has identified the need for an empirical comparison between methods, which will require the use and development of certain standard metrics. An in-depth analysis conducted by means of systematic literature review is also required. The software prototype evaluation provided positive results, showing that the prototype may be a reliable system for A-wave detection.

Automated Detection and Screening of Traumatic Brain Injury (TBI) Using Computed Tomography Images: A Comprehensive Review and Future Perspectives

Traumatic brain injury (TBI) occurs due to the disruption in the normal functioning of the brain by sudden external forces. The primary and secondary injuries due to TBI include intracranial hematoma (ICH), raised intracranial pressure (ICP), and midline shift (MLS), which can result in significant lifetime disabilities and death. Hence, early diagnosis of TBI is crucial to improve patient outcome. Computed tomography (CT) is the preferred modality of choice to assess the severity of TBI. However, manual visualization and inspection of hematoma and its complications from CT scans is a highly operator-dependent and time-consuming task, which can lead to an inappropriate or delayed prognosis. The development of computer aided diagnosis (CAD) systems could be helpful for accurate, early management of TBI. In this paper, a systematic review of prevailing CAD systems for the detection of hematoma, raised ICP, and MLS in non-contrast axial CT brain images is presented. We also suggest future research to enhance the performance of CAD for early and accurate TBI diagnosis.

End-to-End Automatic Morphological Classification of Intracranial Pressure Pulse Waveforms Using Deep Learning

OBJECTIVE

Mean intracranial pressure (ICP) is commonly used in the management of patients with intracranial pathologies. However, the shape of the ICP signal over a single cardiac cycle, called ICP pulse waveform, also contains information on the state of the craniospinal space. In this study we aimed to propose an end-to-end approach to classification of ICP waveforms and assess its potential clinical applicability.

METHODS

ICP pulse waveforms obtained from long-term ICP recordings of 50 neurointensive care unit (NICU) patients were manually classified into four classes ranging from normal to pathological. An additional class was introduced to simultaneously identify artifacts. Several deep learning models and data representations were evaluated. An independent testing dataset was used to assess the performance of final models. Occurrence of different waveform types was compared with the patients clinical outcome.

RESULTS

Residual Neural Network using 1-D ICP signal as input was identified as the best performing model with accuracy of 93\% in the validation and 82\% in the testing dataset. Patients with unfavorable outcome exhibited significantly lower incidence of normal waveforms compared to the favorable outcome group at ICP levels below 20 mm Hg (median [first-third quartile]: 6 [1-37] \% vs. 56 [12-71] \%, p=0.005).

CONCLUSIONS

Results of this study confirm the possibility of analyzing ICP pulse waveform morphology in long-term recordings of NICU patients. Proposed approach could potentially be used to provide additional information on the state of patients with intracranial pathologies beyond mean ICP.

Analysis of Cardio-Cerebral Crosstalk Events in an Adult Cohort from the CENTER-TBI Study

OBJECTIVE

In a previous study, we observed the presence of simultaneous increases in intracranial pressure (ICP) and the heart rate (HR), which we denominated cardio-cerebral crosstalk (CC), and we related the number of such events to patient outcomes in a paediatric cohort. In this chapter, we present an extension of this work to an adult cohort from the Collaborative European NeuroTrauma Effectiveness Research in TBI (CENTER-TBI) study.

METHODS

We implemented a sliding window algorithm to detect CC events. We considered subwindows of 10-min observations. If simultaneous increases of at least 20% in ICP and HR occurred with respect to the minimum ICP and HR values in the time windows, a CC event was detected. Correlation between the number of CC events and mortality was then obtained.

RESULTS

The cohort consisted of 226 adults (aged 16-85 years). The number of CC events that were detected varied (mean 50, standard deviation 58). A point biserial correlation coefficient of -0.13 between mortality and CC was found. Although the correlation was weaker than that seen in the paediatric cohort (-0.30), the negative direction was replicated.

CONCLUSION

In this work, we first extracted CC events from ICP and HR observations of adult patients with traumatic brain injury and related the number of CC events to patient outcomes. Consistency with the previous results in the paediatric cohort was observed. The more crosstalk events occurred, the better the patient outcome was.

Intracranial pressure waveform characteristics in idiopathic normal pressure hydrocephalus and late-onset idiopathic aqueductal stenosis

Background

Idiopathic normal pressure hydrocephalus (iNPH) and late-onset idiopathic aqueductal stenosis (LIAS) are two forms of chronic adult hydrocephalus of different aetiology. We analysed overnight intracranial pressure (ICP) monitoring to elucidate ICP waveform changes characteristic for iNPH and LIAS to better understand pathophysiological processes of both diseases.

Methods

98 patients with iNPH and 14 patients with LIAS from two neurosurgical centres were included. All patients underwent diagnostic overnight computerised ICP monitoring with calculation of mean ICP, ICP heartbeat related pulse wave amplitude calculated in the frequency domain (AMP) and the time domain (MWA), index of cerebrospinal compensatory reserve (RAP) and power of slow vasogenic waves (SLOW).

Results

ICP was higher in LIAS than iNPH patients (9.3 ± 3.0 mmHg versus 5.4 ± 4.2 mmHg, p = 0.001). AMP and MWA were higher in iNPH versus LIAS (2.36 ± 0.91 mmHg versus 1.81 ± 0.59 mmHg for AMP, p = 0.012; 6.0 ± 2.0 mmHg versus 4.9 ± 1.2 mmHg for MWA, p = 0.049). RAP and SLOW indicated impaired reserve capacity and compliance in both diseases, but did not differ between groups. INPH patients were older than LIAS patients (77 ± 6 years versus 54 ± 14 years, p < 0.001).

Conclusions

ICP is higher in LIAS than in iNPH patients, likely due to the chronically obstructed CSF flow through the aqueduct, but still in a range considered normal. Interestingly, AMP/MWA was higher in iNPH patients, suggesting a possible role of high ICP pulse pressure amplitudes in iNPH pathophysiology. Cerebrospinal reserve capacity and intracranial compliance is impaired in both groups and the pressure-volume relationship might be shifted towards lower ICP values in iNPH. The physiological influence of age on ICP and AMP/MWA requires further research.

Use of Clustering to Investigate Changes in Intracranial Pressure Waveform Morphology in Patients with Ventriculitis

OBJECTIVE

This study aimed to examine whether changes in intracranial pressure (ICP) waveform morphologies can be used as a biomarker for early detection of ventriculitis.

METHODS

Consecutive patients (N = 1653) were prospectively enrolled in a hemorrhage outcomes study from 2006 to 2018. Of these, 435 patients (26%) required external ventricular drains (EVDs) and 76 (17.5% of those with EVDs) had ventriculitis treated with antibiotics. Nineteen patients (25% of those with ventriculitis) showed culture-positive cerebrospinal fluid (CSF) and were included in the present analysis. CSF was routinely cultured three times per week and additionally if infection was suspected. EVDs were left open for drainage, with ICP assessed hourly by clamping. Using wavelet analysis, we extracted uninterrupted segments of ICP waveforms. We extracted dominant pulses from continuous high-resolution data, using morphological clustering analysis of intracranial pressure (MOCAIP). Then we applied k-means clustering, using the dynamic time warping distance to obtain morphologically similar groupings. Finally, metaclusters and further-split clusters (when equipoise existed) were categorized for broad comparison by clinician consensus.

RESULTS

We extracted 275,911 dominant pulses from 459.9 h of EVD data. Of these, 112,898 pulses (40.9%) occurred before culture positivity, 41,300 pulses (15.0%) occurred during culture positivity, and 121,713 pulses (44.1%) occurred after it. K-means identified 20 clusters, which were further grouped into metaclusters: tri-/biphasic, single-peak, and artifactual waveforms. Prior to ventriculitis, 61.8% of dominant pulses were tri-/biphasic; this percentage reduced to 22.6% during ventriculitis and 28.4% after it (p < 0.0001). One day before the first positive cultures were collected, the distribution of metaclusters changed to include more single-peak and artifactual ICP waveforms (p < 0.0001).

CONCLUSION

The distribution of ICP waveform morphology changes significantly prior to clinical diagnosis of ventriculitis and may be a potential biomarker.

Patient-adaptable intracranial pressure morphology analysis using a probabilistic model-based approach

OBJECTIVE

We present a framework for analyzing the morphology of intracranial pressure (ICP). The analysis of ICP signals is challenging due to the non-linear and non-Gaussian characteristics of the signal dynamics, inevitable corruption by noise and artifacts, and variations in ICP pulse morphology among individuals with different neurological conditions. Existing frameworks make unrealistic assumptions regarding ICP dynamics and are not tuned for individual patients.

APPROACH

We propose a dynamic Bayesian network for automated detection of three major ICP pulsatile components. The proposed model captures the non-linear and non-Gaussian dynamics of ICP morphology and further adapts to a patient as the individual's ICP measurements are received. To make the approach more robust, we leverage evidence reversal and present an inference algorithm to obtain the posterior distribution over the locations of pulsatile components.

MAIN RESULTS

We evaluate our approach on a dataset with over 700 h of recordings from 66 neurological patients, where the pulsatile components were annotated by prior studies. The algorithm obtains accuracies of 96.56%, 92.39%, and 94.04% for the detection of each pulsatile component in the test set, showing significant improvement over existing approaches.

SIGNIFICANCE

Continuous ICP monitoring is essential in guiding the treatment of neurological conditions such as traumatic brain injuries. An automated approach for ICP morphology analysis is a step towards enhancing patient care with minimal supervision. Compared to previous methods, our framework offers several advantages. It learns the parameters that model each patient's ICP in an unsupervised manner, resulting in an accurate morphology analysis. The Bayesian model-based framework provides uncertainty estimates and reveals interesting facts about the ICP dynamics. The framework can readily be applied to replace existing morphological analysis methods and support the use of ICP pulse morphological features to aid the monitoring of pathophysiological changes of relevance to the care of patients with acute brain injuries.

Intracranial Pressure Monitoring Signals After Traumatic Brain Injury: A Narrative Overview and Conceptual Data Science Framework

Continuous intracranial pressure (ICP) monitoring is a cornerstone of neurocritical care after severe brain injuries such as traumatic brain injury and acts as a biomarker of secondary brain injury. With the rapid development of artificial intelligent (AI) approaches to data analysis, the acquisition, storage, real-time analysis, and interpretation of physiological signal data can bring insights to the field of neurocritical care bioinformatics. We review the existing literature on the quantification and analysis of the ICP waveform and present an integrated framework to incorporate signal processing tools, advanced statistical methods, and machine learning techniques in order to comprehensively understand the ICP signal and its clinical importance. Our goals were to identify the strengths and pitfalls of existing methods for data cleaning, information extraction, and application. In particular, we describe the use of ICP signal analytics to detect intracranial hypertension and to predict both short-term intracranial hypertension and long-term clinical outcome. We provide a well-organized roadmap for future researchers based on existing literature and a computational approach to clinically-relevant biomedical signal data.

Neurocritical Care: Bench to Bedside (Eds. Claude Hemphill, Michael James) Integrating and Using Big Data in Neurocritical Care

The critical care environment drives huge volumes of data, and clinicians are tasked with quickly processing this data and responding to it urgently. The neurocritical care environment increasingly involves EEG, multimodal intracranial monitoring, and complex imaging which preclude comprehensive human synthesis, and requires new concepts to integrate data into clinical care. By definition, Big Data is data that cannot be handled using traditional infrastructures and is characterized by the volume, variety, velocity, and variability of the data being produced. Big Data in the neurocritical care unit requires rethinking of data storage infrastructures and the development of tools and analytics to drive advancements in the field. Preprocessing, feature extraction, statistical inference, and analytic tools are required in order to achieve the primary goals of Big Data for clinical use: description, prediction, and prescription. Barriers to its use at bedside include a lack of infrastructure development within the healthcare industry, lack of standardization of data inputs, and ultimately existential and scientific concerns about the outputs that result from the use of tools such as artificial intelligence. However, as implied by the fundamental theorem of biomedical informatics, physicians remain central to the development and utility of Big Data to improve patient care.

Estimating intracranial pressure using pulsatile cerebral blood flow measured with diffuse correlation spectroscopy

Measuring intracranial pressure (ICP) is necessary for the treatment of severe head injury but measurement systems are highly invasive and introduce risk of infection and complications. We developed a non-invasive alternative for quantifying ICP using measurements of cerebral blood flow (CBF) by diffuse correlation spectroscopy. The recorded cardiac pulsation waveform in CBF undergoes morphological changes in response to ICP changes. We used the pulse shape to train a randomized regression forest to estimate the underlying ICP and demonstrate in five non-human primates that DCS-based estimation can explain over 90% of the variance in invasively measured ICP.

Toward automated classification of pathological transcranial Doppler waveform morphology via spectral clustering

Cerebral Blood Flow Velocity waveforms acquired via Transcranial Doppler (TCD) can provide evidence for cerebrovascular occlusion and stenosis. Thrombolysis in Brain Ischemia (TIBI) flow grades are widely used for this purpose, but require subjective assessment by expert evaluators to be reliable. In this work we seek to determine whether TCD morphology can be objectively assessed using an unsupervised machine learning approach to waveform categorization. TCD beat waveforms were recorded at multiple depths from the Middle Cerebral Arteries of 106 subjects; 33 with Large Vessel Occlusion (LVO). From each waveform, three morphological features were extracted, quantifying onset of maximal velocity, systolic canopy length, and the number/prominence of peaks/troughs. Spectral clustering identified groups implicit in the resultant three-dimensional feature space, with gap statistic criteria establishing the optimal cluster number. We found that gap statistic disparity was maximized at four clusters, referred to as flow types I, II, III, and IV. Types I and II were primarily composed of control subject waveforms, whereas types III and IV derived mainly from LVO patients. Cluster morphologies for types I and IV aligned clearly with Normal and Blunted TIBI flows, respectively. Types II and III represented commonly observed flow-types not delineated by TIBI, which nonetheless deviate from normal and blunted flows. We conclude that important morphological variability exists beyond that currently quantified by TIBI in populations experiencing or at-risk for acute ischemic stroke, and posit that the observed flow-types provide the foundation for objective methods of real-time automated flow type classification.

Forecasting intracranial hypertension using multi-scale waveform metrics

OBJECTIVE

Acute intracranial hypertension is an important risk factor of secondary brain damage after traumatic brain injury. Hypertensive episodes are often diagnosed reactively, leading to late detection and lost time for intervention planning. A pro-active approach that predicts critical events several hours ahead of time could assist in directing attention to patients at risk.

APPROACH

We developed a prediction framework that forecasts onsets of acute intracranial hypertension in the next 8 h. It jointly uses cerebral auto-regulation indices, spectral energies and morphological pulse metrics to describe the neurological state of the patient. One-minute base windows were compressed by computing signal metrics, and then stored in a multi-scale history, from which physiological features were derived.

MAIN RESULTS

Our model predicted events up to 8 h in advance with an alarm recall rate of 90% at a precision of 30% in the MIMIC-III waveform database, improving upon two baselines from the literature. We found that features derived from high-frequency waveforms substantially improved the prediction performance over simple statistical summaries of low-frequency time series, and each of the three feature classes contributed to the performance gain. The inclusion of long-term history up to 8 h was especially important.

SIGNIFICANCE

Our results highlight the importance of information contained in high-frequency waveforms in the neurological intensive care unit. They could motivate future studies on pre-hypertensive patterns and the design of new alarm algorithms for critical events in the injured brain.

Morphological changes of intracranial pressure quantifies vasodilatory effect of verapamil to treat cerebral vasospasm

INTRODUCTION

After aneurysmal subarachnoid hemorrhage (SAH), both proximal and distal cerebral vasospasm can contribute to the development of delayed cerebral ischemia. Intra-arterial (IA) vasodilators are a mainstay of treatment for distal arterial vasospasm, but no methods of assessing the efficacy of interventions in real time have been established.

OBJECTIVE

To introduce a new method for continuous intraprocedural assessment of endovascular treatment for cerebral vasospasm.

METHODS

The premise of our approach was that distal cerebral arterial changes induce a consistent pattern in the morphological changes of intracranial pressure (ICP) pulse. This premise was demonstrated using a published algorithm in previous papers. In this study, we applied the algorithm to calculate the likelihood of cerebral vasodilation (VDI) and cerebral vasoconstriction (VCI) from intraprocedural ICP signals that are synchronized with injection of the IA vasodilator, verapamil. Cerebral blood flow velocities (CBFVs) on bilateral cerebral arteries were studied before and after IA therapy.

RESULTS

192 recordings of patients with SAH were reviewed, and 27 recordings had high-quality ICP waveforms. The VCI was significantly lower after the first verapamil injection (0.47±0.017) than VCI at baseline (0.49±0.020, p<0.001). A larger dose of injected verapamil resulted in a larger and longer VDI increase. CBFV of the middle cerebral artery increases across the days before the injection of verapamil and decreases after IA therapy.

CONCLUSION

This study provides preliminary validation of an algorithm for continuous assessment of distal cerebral arterial changes in response to IA vasodilator infusion in patients with vasospasm and aneurysmal SAH.

Evaluation of a New Catheter for Simultaneous Intracranial Pressure Monitoring and Cerebral Spinal Fluid Drainage: A Pilot Study

OBJECTIVES

Intracranial pressure (ICP) monitoring is a common practice when treating intracranial pathology with risk of elevated ICP. External ventricular drain (EVD) insertion is a standard approach for both monitoring ICP and draining cerebrospinal fluid (CSF). However, the conventional EVD cannot serve these two purposes simultaneously because it cannot accurately measure ICP and its pulsatile waveform while the EVD is open to CSF drainage. A new Integra^® Camino^® FLEX Ventricular Catheter (Integra Lifesciences, County Offaly, Ireland) with a double-lumen construction has been recently introduced into the market, and it can monitor ICP waveforms even during CSF drainage. The aim of this study was to evaluate and validate this new FLEX catheter for ICP monitoring in a neurological intensive care unit.

METHODS

Six patients with 34 EVD open/close episodes were retrospectively analyzed. Continuous ICP was detected in two ways: through the FLEX sensor at the tip (ICP_f) and through a fluid-coupled manometer within the FLEX catheter, functioning as a conventional EVD (ICP_e). The morphologies of ICP_f and ICP_e pulses were extracted using Morphological Clustering and Analysis of ICP algorithm, an algorithm that has been validated in previous publications. The mean ICP and waveform shapes of ICP pulses detected through the two systems were compared. Bland-Altman plots were used to assess the agreement of the two systems.

RESULTS

A significant linear relationship existed between mean ICP_f and mean ICP_e, which can be described as: mICP_f = 0.81 × mICP_e + 1.67 (r = 0.79). The Bland-Altman plot revealed that no significant difference existed between the two ICPs (average of [ICP_e-ICP_f] was - 1.69 mmHg, 95% limits of agreement: - 7.94 to 4.56 mmHg). The amplitudes of the landmarks of ICP pulse waveforms from the two systems showed strong, linear relationship (r ranging from 0.89 to 0.94).

CONCLUSIONS

This study compared a new FLEX ventricular catheter with conventional fluid-coupled manometer for ICP waveform monitoring. Strong concordance in ICP value and waveform morphology between the two systems indicates that this catheter can be used for reliability for both clinical and research applications.

Cerebral Vascular Changes During Acute Intracranial Pressure Drop

OBJECTIVE

This study applied a new external ventricular catheter, which allows intracranial pressure (ICP) monitoring and cerebral spinal fluid (CSF) drainage simultaneously, to study cerebral vascular responses during acute CSF drainage.

METHODS

Six patients with 34 external ventricular drain (EVD) opening sessions were retrospectively analyzed. A published algorithm was used to extract morphological features of ICP recordings, and a template-matching algorithm was applied to calculate the likelihood of cerebral vasodilation index (VDI) and cerebral vasoconstriction index (VCI) based on the changes of ICP waveforms during CSF drainage. Power change (∆P) of ICP B-waves after EVD opening was also calculated. Cerebral autoregulation (CA) was assessed through phase difference between arterial blood pressure (ABP) and ICP using a previously published wavelet-based algorithm.

RESULTS

The result showed that acute CSF drainage reduced mean ICP (P = 0.016) increased VCI (P = 0.02) and reduced ICP B-wave power (P = 0.016) significantly. VCI reacted to ICP changes negatively when ICP was between 10 and 25 mmHg, and VCI remained unchanged when ICP was outside the 10-25 mmHg range. VCI negatively (r = - 0.44) and VDI positively (r = 0.82) correlated with ∆P of ICP B-waves, indicating that stronger vasoconstriction resulted in bigger power drop in ICP B-waves. Better CA prior to EVD opening triggered bigger drop in the power of ICP B-waves (r = - 0.612).

CONCLUSIONS

This study demonstrates that acute CSF drainage reduces mean ICP, and results in vasoconstriction which can be detected through an index, VCI. Cerebral vessels actively respond to ICP changes or cerebral perfusion pressure (CPP) changes in a certain range; beyond which, the vessels are insensitive to the changes in ICP and CPP.

B waves: a systematic review of terminology, characteristics, and analysis methods

Background

Although B waves were introduced as a concept in the analysis of intracranial pressure (ICP) recordings nearly 60 years ago, there is still a lack consensus on precise definitions, terminology, amplitude, frequency or origin. Several competing terms exist, addressing either their probable physiological origin or their physical characteristics. To better understand B wave characteristics and ease their detection, a literature review was carried out.

Methods

A systematic review protocol including search strategy and eligibility criteria was prepared in advance. A literature search was carried out using PubMed/MEDLINE, with the following search terms: B waves + review filter, slow waves + review filter, ICP B waves, slow ICP waves, slow vasogenic waves, Lundberg B waves, MOCAIP.

Results

In total, 19 different terms were found, B waves being the most common. These terminologies appear to be interchangeable and seem to be used indiscriminately, with some papers using more than five different terms. Definitions and etiologies are still unclear, which makes systematic and standardized detection difficult.

Conclusions

Two future lines of action are available for automating macro-pattern identification in ICP signals: achieving strict agreement on morphological characteristics of “traditional” B waveforms, or starting a new with a fresh computerized approach for recognition of new clinically relevant patterns.

Objective Assessment of Beat Quality in Transcranial Doppler Measurement of Blood Flow Velocity in Cerebral Arteries

OBJECTIVE

Transcranial Doppler (TCD) ultrasonography measures pulsatile cerebral blood flow velocity in the arteries and veins of the head and neck. Similar to other real-time measurement modalities, especially in healthcare, the identification of high-quality signals is essential for clinical interpretation. Our goal is to identify poor quality beats and remove them prior to further analysis of the TCD signal.

METHODS

We selected objective features for this purpose including Euclidean distance between individual and average beat waveforms, cross-correlation between individual and average beat waveforms, ratio of the high-frequency power to the total beat power, beat length, and variance of the diastolic portion of the beat waveform. We developed an iterative outlier detection algorithm to identify and remove the beats that are different from others in a recording. Finally, we tested the algorithm on a dataset consisting of more than 15 h of TCD data recorded from 48 stroke and 34 in-hospital control subjects.

RESULTS

We assessed the performance of the algorithm in the improvement of estimation of clinically important TCD parameters by comparing them to that of manual beat annotation. The results show that there is a strong correlation between the two, that demonstrates the algorithm has successfully recovered the clinically important features. We obtained significant improvement in estimating the TCD parameters using the algorithm accepted beats compared to using all beats.

SIGNIFICANCE

Our algorithm provides a valuable tool to clinicians for automated detection of the reliable portion of the data. Moreover, it can be used as a pre-processing tool to improve the data quality for automated diagnosis of pathologic beat waveforms using machine learning.

Artifact removal from neurophysiological signals: impact on intracranial and arterial pressure monitoring in traumatic brain injury

OBJECTIVE

Monitoring intracranial and arterial blood pressure (ICP and ABP, respectively) provides crucial information regarding the neurological status of patients with traumatic brain injury (TBI). However, these signals are often heavily affected by artifacts, which may significantly reduce the reliability of the clinical determinations derived from the signals. The goal of this work was to eliminate signal artifacts from continuous ICP and ABP monitoring via deep learning techniques and to assess the changes in the prognostic capacities of clinical parameters after artifact elimination.

METHODS

The first 24 hours of monitoring ICP and ABP in a total of 309 patients with TBI was retrospectively analyzed. An artifact elimination model for ICP and ABP was constructed via a stacked convolutional autoencoder (SCAE) and convolutional neural network (CNN) with 10-fold cross-validation tests. The prevalence and prognostic capacity of ICP- and ABP-related clinical events were compared before and after artifact elimination.

RESULTS

The proposed SCAE-CNN model exhibited reliable accuracy in eliminating ABP and ICP artifacts (net prediction rates of 97% and 94%, respectively). The prevalence of ICP- and ABP-related clinical events (i.e., systemic hypotension, intracranial hypertension, cerebral hypoperfusion, and poor cerebrovascular reactivity) all decreased significantly after artifact removal.

CONCLUSIONS

The SCAE-CNN model can be reliably used to eliminate artifacts, which significantly improves the reliability and efficacy of ICP- and ABP-derived clinical parameters for prognostic determinations after TBI.

Data-Augmented Modeling of Intracranial Pressure

Precise management of patients with cerebral diseases often requires intracranial pressure (ICP) monitoring, which is highly invasive and requires a specialized ICU setting. The ability to noninvasively estimate ICP is highly compelling as an alternative to, or screening for, invasive ICP measurement. Most existing approaches for noninvasive ICP estimation aim to build a regression function that maps noninvasive measurements to an ICP estimate using statistical learning techniques. These data-based approaches have met limited success, likely because the amount of training data needed is onerous for this complex applications. In this work, we discuss an alternative strategy that aims to better utilize noninvasive measurement data by leveraging mechanistic understanding of physiology. Specifically, we developed a Bayesian framework that combines a multiscale model of intracranial physiology with noninvasive measurements of cerebral blood flow using transcranial Doppler. Virtual experiments with synthetic data are conducted to verify and analyze the proposed framework. A preliminary clinical application study on two patients is also performed in which we demonstrate the ability of this method to improve ICP prediction.

An active learning framework for enhancing identification of non-artifactual intracranial pressure waveforms

OBJECTIVE

Intracranial pressure (ICP) is an important and established clinical measurement that is used in the management of severe acute brain injury. ICP waveforms are usually triphasic and are susceptible to artifact because of transient catheter malfunction or routine patient care. Existing methods for artifact detection include threshold-based, stability-based, or template matching, and result in higher false positives (when there is variability in the ICP waveforms) or higher false negatives (when the ICP waveforms lack complete triphasic components but are valid).

APPROACH

We hypothesized that artifact labeling of ICP waveforms can be optimized by an active learning approach which includes interactive querying of domain experts to identify a manageable number of informative training examples.

MAIN RESULTS

The resulting active learning based framework identified non-artifactual ICP pulses with a superior AUC of 0.96 + 0.012, compared to existing methods: template matching (AUC: 0.71 + 0.04), ICP stability (AUC: 0.51 + 0.036) and threshold-based (AUC: 0.5 + 0.02).

SIGNIFICANCE

The proposed active learning framework will support real-time ICP-derived analytics by improving precision of artifact-labelling.

Continuous wavelet transform in the study of the time-scale properties of intracranial pressure in hydrocephalus

Normal pressure hydrocephalus (NPH) encompasses a heterogeneous group of disorders generally characterized by clinical symptoms, ventriculomegaly and anomalous cerebrospinal fluid (CSF) dynamics. Lumbar infusion tests (ITs) are frequently performed in the preoperatory evaluation of patients who show NPH features. The analysis of intracranial pressure (ICP) signals recorded during ITs could be useful to better understand the pathophysiology underlying NPH and to assist treatment decisions. In this study, 131 ICP signals recorded during ITs were analysed using two continuous wavelet transform (CWT)-derived parameters: Jensen divergence (JD) and spectral flux (SF). These parameters were studied in two frequency bands, associated with different components of the signal: B₁(0.15-0.3 Hz), related to respiratory blood pressure oscillations; and B₂ (0.67-2.5 Hz), related to ICP pulse waves. Statistically significant differences (p < 1.70 × 10^-3, Bonferroni-corrected Wilcoxon signed-rank tests) in pairwise comparisons between phases of ITs were found using the mean and standard deviation of JD and SF. These differences were mainly found in B₂, where a lower irregularity and variability, together with less prominent time-frequency fluctuations, were found in the hypertension phase of ITs. Our results suggest that wavelet analysis could be useful for understanding CSF dynamics in NPH.This article is part of the theme issue 'Redundancy rules: the continuous wavelet transform comes of age'.

Intracranial pressure changes after mild traumatic brain injury: a systematic review

OBJECTIVE

Intracranial pressure (ICP) after mild traumatic brain injury (mTBI) is poorly studied due to lack of sensitive non-invasive methods. The purpose of this review was to summarize the existing knowledge of changes in ICP after mTBI. Literature selection: PubMed, Embase, CINAHL, and Scopus were searched by three reviewers independently up to December 2016.

INCLUSION CRITERIA

animal and human studies measuring ICP and brain oedema after an mTBI.

EXCLUSION CRITERIA

moderate and severe forms of traumatic brain injury, repeat samples, and studies that measured ICP at the time of impact but not after. Study quality was assessed using Downs and Black criteria.

RESULTS

Of 1067 papers, 9 studies were included. In human studies, one provided direct evidence on increased, one provided indirect evidence of increased, and two provided indirect evidence of decreased ICP. In animal studies, three studies provided direct evidence of increased, one provided indirect evidence of increased, and one provided indirect evidence of no change in ICP.

CONCLUSION

The existing research suggests that there may be increased ICP after mTBI and animal studies suggest an elevation for days which returns to baseline, which corresponds with functional and symptomatic recovery. Future human studies using sensitive indirect methods to measure ICP longitudinally after mTBI are needed.

Simultaneous Transients of Intracranial Pressure and Heart Rate in Traumatic Brain Injury: Methods of Analysis

OBJECTIVES

The detection of increasing intracranial pressure (ICP) is important in preventing secondary brain injuries. Before mean ICP increases critically, transient ICP elevations may be observed. We have observed ICP transients of less than 10 min duration ,which occurred simultaneously with transient increases in heart rate (HR). These simultaneous events in HR and ICP suggest a direct interaction or communication between the heart and the brain.

METHODS

This chapter describes four mathematical methods and their applicability in detecting the above heart-brain cross-talk events during long-term monitoring of ICP.

RESULTS

Recurrence plots, cross-correlation function and wavelet analysis confirmed the relationship between ICP and HR time series. Using the peaks detection algorithm with a sliding window approach we found an average of 37 cross-talk events (± SD 39). The number of events detected varied among patients, from 1 to more than 150 events.

CONCLUSION

Our analysis suggested that the peaks detection algorithm based on a sliding window approach is feasible for detecting simultaneous peaks, e.g. cross-talk events in the ICP and HR signals.

Characterization of Shape Differences Among ICP Pulses Predicts Outcome of External Ventricular Drainage Weaning Trial

BACKGROUND

External ventricular drains (EVD) are widely used to manage intracranial pressure (ICP) and hydrocephalus for aneurysmal subarachnoid hemorrhage (aSAH) patients. After days of use, a decision is made to remove the EVD or replace it with a shunt, involving EVD weaning and CT imaging to observe ventricular size and clinical status. This practice may lead to prolonged hospital stay, extra radiation exposure, and neurological insult due to ICP elevation. This study aims to apply a validated morphological clustering analysis of ICP pulse (MOCAIP) algorithm to detect signatures from the pulse waveform to differentiate an intact CSF circulatory system from an abnormal one during EVD weaning.

METHODS

We performed a retrospective study with 50 aSAH patients with reported weaning trial admitted to our institution between 03/2013 and 08/2014. By reviewing clinical notes and pre/post-brain imaging results, 32 patients were determined as having passed the weaning trial and 18 patients as having failed the trial. MOCAIP algorithm was applied to ICP signals to form a series of artifact-free dominant pulses. Finally, pulses with similar mean ICP were identified, and amplitude, Euclidean, and geodesic inter-pulse distances were calculated in a 4-h moving window.

RESULTS

While the traditional measure of mean ICP failed to differentiate the two groups of patients, the proposed amplitude and morphological inter-pulse measures presented significant differences (p ≤ 0.004). Moreover, receiver operating characteristic (ROC) analyses showed their usability to predict the outcome of the EVD weaning trial (AUC 0.85, p < 0.001).

CONCLUSIONS

Patients with an impaired CSF system showed a larger mean and variability of inter-pulse distances, indicating frequent changes on the morphology of pulses. This technique may provide a method to rapidly determine if patients will need placement of a shunt or can simply have the EVD removed.

A multiplex network approach for the analysis of intracranial pressure and heart rate data in traumatic brain injured patients

BACKGROUND

We present a multiplex network model for the analysis of Intracranial Pressure (ICP) and Heart Rate (HR) behaviour after severe brain traumatic injuries in pediatric patients. The ICP monitoring is of vital importance for checking life threathening conditions, and understanding the behaviour of these parameters is crucial for a successful intervention of the clinician. Our own observations, exhibit cross-talks interaction events happening between HR and ICP, i.e. transients in which both the ICP and the HR showed an increase of 20% with respect to their baseline value in the window considered. We used a complex event processing methodology, to investigate the relationship between HR and ICP, after traumatic brain injuries (TBI). In particular our goal has been to analyse events of simultaneous increase by HR and ICP (i.e. cross-talks), modelling the two time series as a unique multiplex network system (Lacasa et al., Sci Rep 5:15508-15508, 2014).

METHODS AND DATA

We used a complex network approach based on visibility graphs (Lacasa et al., Sci Rep 5:15508-15508, 2014) to model and study the behaviour of our system and to investigate how and if network topological measures can give information on the possible detection of crosstalks events taking place in the system. Each time series was converted as a layer in a multiplex network. We therefore studied the network structure, focusing on the behaviour of the two time series in the cross-talks events windows detected. We used a dataset of 27 TBI pediatric patients, admitted to Addenbrooke's Hospital, Cambridge, Pediatric Intensive Care Unit (PICU) between August 2012 and December 2014.

RESULTS

Following a preliminary statistical exploration of the two time series of ICP and HR, we analysed the multiplex network proposed, focusing on two standard topological network metrics: the mutual interaction, and the average edge overlap (Lacasa et al., Sci Rep 5:15508-15508, 2014). We compared results obtained for these two indicators, considering windows in which a cross talks event between HR and ICP was detected with windows in which cross talks events were not present. The analysis of such metrics gave us interesting insights on the time series behaviour. More specifically we observed an increase in the value of the mutual interaction in the case of cross talk as compared to non cross talk. This seems to suggest that mutual interaction could be a potentially interesting "marker" for cross talks events.

Intracranial pressure monitoring after primary decompressive craniectomy in traumatic brain injury: a clinical study

BACKGROUND

Intracranial pressure (ICP) monitoring represents an important tool in the management of traumatic brain injury (TBI). Although current information exists regarding ICP monitoring in secondary decompressive craniectomy (DC), little is known after primary DC following emergency hematoma evacuation.

METHODS

Retrospective analysis of prospectively collected data. Inclusion criteria were age ≥18 years and admission to the intensive care unit (ICU) for TBI and ICP monitoring after primary DC. Exclusion criteria were ICU length of stay (LOS) <1 day and pregnancy. Major objectives were: (1) to analyze changes in ICP/cerebral perfusion pressure (CPP) after primary DC, (2) to evaluate the relationship between ICP/CPP and neurological outcome and (3) to characterize and evaluate ICP-driven therapies after DC.

RESULTS

A total of 34 patients were enrolled. Over 308 days of ICP/CPP monitoring, 130 days with at least one episode of intracranial hypertension (26 patients, 76.5%) and 57 days with at least one episode of CPP <60 mmHg (22 patients, 64.7%) were recorded. A statistically significant relationship was discovered between the Glasgow Outcome Scale (GOS) scores and mean post-decompression ICP (p < 0.04) and between GOS and CPP minimum (CPPmin) (p < 0.04). After DC, persisting intracranial hypertension was treated with: barbiturate coma (n = 7, 20.6%), external ventricular drain (EVD) (n = 4, 11.8%), DC diameter widening (n = 1, 2.9%) and removal of newly formed hematomas (n = 3, 8.8%).

CONCLUSION

Intracranial hypertension and/or low CPP occurs frequently after primary DC; their occurence is associated with an unfavorable neurological outcome. ICP monitoring appears useful in guiding therapy after primary DC.

The best marker for guiding the clinical management of patients with raised intracranial pressure-the RAP index or the mean pulse amplitude?

Raised intracranial pressure is a common problem in a variety of neurosurgical conditions including traumatic brain injury, hydrocephalus and intracranial haemorrhage. The clinical management of these patients is guided by a variety of haemodynamic, biochemical and clinical factors. However to date there is no single parameter that is used to guide clinical management of patients with raised intracranial pressure (ICP). However, the role of ICP indices, specifically the mean pulse amplitude (AMP) and RAP index [correlation coefficient (R) between AMP amplitude (A) and mean ICP pressure (P); index of compensatory reserve], as an indicator of true ICP has been investigated. Whilst the RAP index has been used both as a descriptor of neurological deterioration in TBI patients and as a way of characterising the compensatory reserve in hydrocephalus, more recent studies have highlighted the limitation of the RAP index due to the influence that baseline effect errors have on the mean ICP, which is used in the calculation of the RAP index. These studies have suggested that the ICP mean pulse amplitude may be a more accurate marker of true intracranial pressure due to the fact that it is uninfluenced by the mean ICP and, therefore, the AMP may be a more reliable marker than the RAP index for guiding the clinical management of patients with raised ICP. Although further investigation needs to be undertaken in order to fully assess the role of ICP indices in guiding the clinical management of patients with raised ICP, the studies undertaken to date provide an insight into the potential role of ICP indices to treat raised ICP proactively rather than reactively and therefore help prevent or minimise secondary brain injury.

Effect of infusion tests on the dynamical properties of intracranial pressure in hydrocephalus

BACKGROUND AND OBJECTIVE

Hydrocephalus comprises a number of conditions characterised by clinical symptoms, dilated ventricles and anomalous cerebrospinal fluid (CSF) dynamics. Infusion tests (ITs) are usually performed to study CSF circulation and in the preoperatory evaluation of patients with hydrocephalus. The study of intracranial pressure (ICP) signals recorded during ITs could be useful to gain insight into the underlying pathophysiology of this condition and to further support treatment decisions. In this study, two wavelet parameters, wavelet turbulence (WT) and wavelet entropy (WE), were analysed in order to characterise the variability, irregularity and similarity in spectral content of ICP signals in hydrocephalus.

METHODS

One hundred and twelve ICP signals were analysed using WT and WE. These parameters were calculated in two frequency bands: B1 (0.15-0.3 Hz) and B2 (0.67-2.5 Hz). Each signal was divided into four artefact-free epochs corresponding to the basal, early infusion, plateau and recovery phases of the IT. We calculated the mean and standard deviation of WT and WE and analysed whether these parameters revealed differences between epochs of the IT.

RESULTS

Statistically significant differences (p < 1.70⋅10(-3), Bonferroni-corrected Wilcoxon signed-rank tests) in pairwise comparisons between phases of ITs were found using the mean and standard deviation of WT and WE. These differences were mainly found in B2.

CONCLUSIONS

Wavelet parameters like WT and WE revealed changes in the signal time-scale representation during ITs. Statistically significant differences were mainly found in B2, associated with ICP pulse waves, and included a higher degree of similarity in the spectral content, together with a lower irregularity and variability in the plateau phase with respect to the basal phase.

Intracranial pressure, its components and cerebrospinal fluid pressure-volume compensation

Clinical measurement of intracranial pressure (ICP) is often performed to aid diagnosis of hydrocephalus. This review discusses analysis of ICP and its components' for the investigation of cerebrospinal fluid (CSF) dynamics. The role of pulse, slow and respiratory waveforms of ICP in diagnosis, prognostication and management of hydrocephalus is presented. Two methods related to ICP measurement are listed: an overnight monitoring of ICP and a constant-rate infusion study. Due to the dynamic nature of ICP, a 'snapshot' manometric measurement of ICP is of limited use as it might lead to unreliable results. Therefore, monitoring of ICP over longer time combined with analysis of its waveforms provides more detailed information on the state of pressure-volume compensation. The infusion study implements ICP signal processing and CSF circulation model analysis in order to assess the cerebrospinal dynamics variables, such as CSF outflow resistance, compliance of CSF space, pressure amplitude, reference pressure, and CSF formation. These parameters act as an aid tool in diagnosis and prognostication of hydrocephalus and can be helpful in the assessment of a shunt malfunction.

A Coupled Lumped-Parameter and Distributed Network Model for Cerebral Pulse-Wave Hemodynamics

The cerebral circulation is unique in its ability to maintain blood flow to the brain under widely varying physiologic conditions. Incorporating this autoregulatory response is necessary for cerebral blood flow (CBF) modeling, as well as investigations into pathological conditions. We discuss a one-dimensional (1D) nonlinear model of blood flow in the cerebral arteries coupled to autoregulatory lumped-parameter (LP) networks. The LP networks incorporate intracranial pressure (ICP), cerebrospinal fluid (CSF), and cortical collateral blood flow models. The overall model is used to evaluate changes in CBF due to occlusions in the middle cerebral artery (MCA) and common carotid artery (CCA). Velocity waveforms at the CCA and internal carotid artery (ICA) were examined prior and post MCA occlusion. Evident waveform changes due to the occlusion were observed, providing insight into cerebral vasospasm monitoring by morphological changes of the velocity or pressure waveforms. The role of modeling of collateral blood flows through cortical pathways and communicating arteries was also studied. When the MCA was occluded, the cortical collateral flow had an important compensatory role, whereas the communicating arteries in the circle of Willis (CoW) became more important when the CCA was occluded. To validate the model, simulations were conducted to reproduce a clinical test to assess dynamic autoregulatory function, and results demonstrated agreement with published measurements.

Noise reduction in intracranial pressure signal using causal shape manifolds

We present the Iterative/Causal Subspace Tracking framework (I/CST) for reducing noise in continuously monitored quasi-periodic biosignals. Signal reconstruction of the basic segments of the noisy signal (e.g. beats) is achieved by projection to a reduced space on which probabilistic tracking is performed. The attractiveness of the presented method lies in the fact that the subspace, or manifold, is learned by incorporating temporal, morphological, and signal elevation constraints, so that segment samples with similar shapes, and that are close in time and elevation, are also close in the subspace representation. Evaluation of the algorithm's effectiveness on the intracranial pressure (ICP) signal serves as a practical illustration of how it can operate in clinical conditions on routinely acquired biosignals. The reconstruction accuracy of the system is evaluated on an idealized 20-min ICP recording established from the average ICP of patients monitored for various ICP related conditions. The reconstruction accuracy of the ground truth signal is tested in presence of varying levels of additive white Gaussian noise (AWGN) and Poisson noise processes, and measures significant increases of 758% and 396% in the average signal-to-noise ratio (SNR).

Intracranial pressure wave morphological classification: automated analysis and clinical validation

BACKGROUND

Recently, different software has been developed to automatically analyze multiple intracranial pressure (ICP) parameters, but the suggested methods are frequently complex and have no clinical correlation. The objective of this study was to assess the clinical value of a new morphological classification of the cerebrospinal fluid pulse pressure waveform (CSFPPW), comparing it to the elastance index (EI) and CSF-outflow resistance (Rout), and to test the efficacy of an automatic ICP analysis.

METHODS

An artificial neural network (ANN) was trained to classify 60 CSFPPWs in four different classes, according to their morphology, and its efficacy was compared to an expert examiner's classification. The morphology of CSFPPW, recorded in 60 patients at baseline, was compared to EI and Rout calculated at the end of an intraventricular infusion test to validate the utility of the proposed classification in patients' clinical evaluation.

RESULTS

The overall concordance in CSFPPW classification between the expert examiner and the ANN was 88.3 %. An elevation of EI was statistically related to morphological class' progression. All patients showing pathological baseline CSFPPW (class IV) revealed an alteration of CSF hydrodynamics at the end of their infusion test.

CONCLUSIONS

The proposed morphological classification estimates the global ICP wave and its ability to reflect or predict an alteration in CSF hydrodynamics. An ANN can be trained to efficiently recognize four different CSF wave morphologies. This classification seems helpful and accurate for diagnostic use.

Characterization of Cerebral Vascular Response to EEG Bursts Using ICP Pulse Waveform Template Matching

Neurovascular coupling is the relationship between the activity of the brain and the subsequent change in blood flow to the active region. The most common methods of detecting neurovascular coupling are cumbersome and noncontinuous. However, the integration of intracranial pressure (ICP) and electroencephalography (EEG) may serve as an indirect measure of neurovascular coupling.This study used data collected from burst-suppressed patients who received both ICP and depth EEG monitoring. An adaptive thresholding algorithm was used to detect the start and end of each EEG burst. The morphological clustering and analysis of ICP and pulse morphological template-matching algorithms were then applied to derive several metrics describing the shape of the ICP pulse waveform and track how it changed following an EEG burst. These changes were compared using a template obtained from patients undergoing CO2-induced vasodilation.All segments exhibited a significant period of vasodilation within 1-2 s after burst, and 4 of 5 had a significant period of vasoconstriction within 4-11 s of the EEG burst, suggesting that there might be a characteristic response of vasodilation and subsequent vasoconstriction after a spontaneous EEG burst. Furthermore, these findings demonstrate the potential of integrated EEG and ICP as an indirect measure of neurovascular coupling.

Outcome Prediction for Patients with Traumatic Brain Injury with Dynamic Features from Intracranial Pressure and Arterial Blood Pressure Signals: A Gaussian Process Approach

Previous work has been demonstrated that tracking features describing the dynamic and time-varying patterns in brain monitoring signals provide additional predictive information beyond that derived from static features based on snapshot measurements. To achieve more accurate predictions of outcomes of patients with traumatic brain injury (TBI), we proposed a statistical framework to extract dynamic features from brain monitoring signals based on the framework of Gaussian processes (GPs). GPs provide an explicit probabilistic, nonparametric Bayesian approach to metric regression problems. This not only provides probabilistic predictions, but also gives the ability to cope with missing data and infer model parameters such as those that control the function's shape, noise level and dynamics of the signal. Through experimental evaluation, we have demonstrated that dynamic features extracted from GPs provide additional predictive information in addition to the features based on the pressure reactivity index (PRx). Significant improvements in patient outcome prediction were achieved by combining GP-based and PRx-based dynamic features. In particular, compared with the a baseline PRx-based model, the combined model achieved over 30 % improvement in prediction accuracy and sensitivity and over 20 % improvement in specificity and the area under the receiver operating characteristic curve.