Morphological clustering and analysis of continuous intracranial pressure

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.

Morphological Feature Extraction From a Continuous Intracranial Pressure Pulse via a Peak Clustering Algorithm

OBJECTIVE

An increase in intracranial pressure (ICP) is frequently observed in patients with severe traumatic brain injury (TBI). The information derived from the observation of temporal changes in the mean ICP is insufficient for assessment of the compensatory reserve of the injured brain. This assessment can be achieved via continuous morphological analysis of the pulse waveform of the ICP.

METHODS

Continuous arterial blood pressure (ABP) and ICP recordings from 292 TBI patients were analyzed. The algorithm extracted morphological landmarks (peaks, troughs, and flats) from the ICP. Among the extracted peaks, P1, P2, and P3 were assigned through peak clustering. The performance of the proposed method was validated through a comparison of the algorithm-defined peaks and those manually identified by experienced observers.

RESULTS

The proposed algorithm successfully identified the three distinguishing peaks of the ICP with satisfactory accuracy (95.3%, 87.8%, and 87.5% for P1, P2, and P3, respectively), even from minimally filtered raw signals.

CONCLUSION

The algorithm extracted the morphological features from both ABP and ICP recordings with high accuracy.

SIGNIFICANCE

The ABP and ICP pulse waveforms can be simultaneously analyzed in real time using the proposed algorithm. The morphological features from these signals may aid the continuous care of patients with TBI.

Characterization of the relationship between intracranial pressure and electroencephalographic monitoring in burst-suppressed patients

BACKGROUND

The objective of this study is to characterize the relationship between ICP and EEG METHODS: Simultaneous ICP and EEG data were obtained from burst-suppressed patients and segmented by EEG bursts. Segments were categorized as increasing/decreasing and peak/valley to investigate relationship between ICP changes and EEG burst duration. A generalized ICP response was obtained by averaging all segments time-aligned at burst onsets. A vasodilatation index (VDI) was derived from the ICP pulse waveform and calculated on a sliding interval to investigate cerebrovascular changes post-burst.

RESULTS

Data from two patients contained 309 bursts. 246 ICP segments initially increased, of which 154 peaked. 63 ICP segments decreased, and zero reached a valley. The change in ICP (0.54 ± 0.85 mmHg) was significantly correlated with the burst duration (p < 0.001). Characterization of the ICP segments showed a peak at 8.1 s and a return to baseline at 14.7 s. The VDI for increasing segments was significantly elevated (median 0.56, IQR 0.31, p < 0.001) and correlated with burst duration (p < 0.001).

CONCLUSIONS

Changes in the ICP and pulse waveform shape after EEG burst suggest that these signals can be related within the context of neurovascular coupling.

SIGNIFICANCE

Existence of a physiological relationship between ICP and EEG may allow the study of neurovascular coupling in acute brain injury patients.

Monitoring of intracranial pressure in patients with traumatic brain injury

Since Monro published his observations on the nature of the contents of the intracranial space in 1783, there has been investigation of the unique relationship between the contents of the skull and the intracranial pressure (ICP). This is particularly true following traumatic brain injury (TBI), where it is clear that elevated ICP due to the underlying pathological processes is associated with a poorer clinical outcome. Consequently, there is considerable interest in monitoring and manipulating ICP in patients with TBI. The two techniques most commonly used in clinical practice to monitor ICP are via an intraventricular or intraparenchymal catheter with a microtransducer system. Both of these techniques are invasive and are thus associated with complications such as hemorrhage and infection. For this reason, significant research effort has been directed toward development of a non-invasive method to measure ICP. The principle aims of ICP monitoring in TBI are to allow early detection of secondary hemorrhage and to guide therapies that limit intracranial hypertension (ICH) and optimize cerebral perfusion. However, information from the ICP value and the ICP waveform can also be used to assess the intracranial volume-pressure relationship, estimate cerebrovascular pressure reactivity, and attempt to forecast future episodes of ICH.

Is there any association between cerebral vasoconstriction/vasodilatation and microdialysis Lactate to Pyruvate ratio increase?

BACKGROUND

Although abnormally high Lactate/Pyruvate ratio (LPR) could indicate cerebral ischemia for brain injury patients, there is a debate on what is primary factor responsible for LPR increase.

METHODS

A data analysis experiment is taken to test whether any association between cerebral vasodilatation/vasoconstriction and LPR increase exists. We studied 4,316 microdialysis data samples collected in an average interval of 1.3 h from 30 severe traumatic brain injury (TBI) patients. The LPR increase episodes were automatically identified using a moving time-window of 5 samples. A novel pulse morphological template matching (PMTM) algorithm was applied to the intracranial pressure (ICP) data of the corresponding patients to assess the occurrence of cerebral vasodilatation and vasoconstriction during the identified LPR increase episodes. Several analyses were performed to evaluate the association between cerebral vasoconstriction/vasodilatation and LPR increase.

RESULTS

Results revealed that although more than half of the LPR increase episodes are not associated with any detected cerebral vasoconstriction/vasodilatation, when a vaso-change happens in association of LPR increase, it is more likely that this vaso-change is in the form of vasoconstriction rather than vasodilatation. Also for few subjects with dominant number of vasoconstriction episodes, a causality relationship between vasoconstriction and LPR increase were observed (vasoconstriction precedes LPR increase).

CONCLUSIONS

Using continuous intracranial pressure monitoring and our pulse morphological template matching (PMTM) algorithm could be potentially helpful in teasing out whether culprit cerebral vascular changes precede metabolic crisis for traumatic brain injury patients and hence guiding the management of this condition.

Reproduction of consistent pulse-waveform changes using a computational model of the cerebral circulatory system

Due to the inaccessibility of the cranial vault, it is difficult to study cerebral blood flow dynamics directly. A mathematical model can be useful to study these dynamics. The model presented here is a novel combination of a one-dimensional fluid flow model representing the major vessels of the circle of Willis (CoW), with six individually parameterized auto-regulatory models of the distal vascular beds. This model has the unique ability to simulate high temporal resolution flow and velocity waveforms, amenable to pulse-waveform analysis, as well as sophisticated phenomena such as auto-regulation. Previous work with human patients has shown that vasodilation induced by CO2 inhalation causes 12 consistent pulse-waveform changes as measured by the morphological clustering and analysis of intracranial pressure algorithm. To validate this model, we simulated vasodilation and successfully reproduced 9 out of the 12 pulse-waveform changes. A subsequent sensitivity analysis found that these 12 pulse-waveform changes were most affected by the parameters associated with the shape of the smooth muscle tension response and vessel elasticity, providing insight into the physiological mechanisms responsible for observed changes in the pulse-waveform shape.

A case-control study of non-monitored ECG metrics preceding in-hospital bradyasystolic cardiac arrest: implication for predictive monitor alarms

OBJECTIVES

We investigated whether additional electrocardiographic (ECG) metrics not available on current patient monitors could predict bradyasystolic cardiac arrest in hospitalized adult patients.

METHODS

A retrospective case-control design was used to study eight ECG metrics from 22 adult bradyasystolic patients and their 45 control patients. The eight ECG metrics included heart rate, QRS width, interval from P-wave peak to QRS onset (PRp), heart rate-corrected interval from QRS onset to T-wave peak (QTpc), amplitude of QRS peak (rAmp), amplitude of P-wave (pAmp), amplitude of T-wave (tAmp), and absolute difference in the ECG amplitudes at QRS onset and offset divided by rAmp, that is, relative J-point amplitude (relJAmp). We derived the maximal true-positive rate (TPR) of detecting cardiac arrest at a globally minimal false-positive rate (FPR) for each metric and for the absolute slope values resulted from a linear fitting of the time series of these metrics. We also recorded the first time crossing the detection threshold to the time of arrest as lead time.

RESULTS

Conditions of relJAmp >20% and PRp >196.6 ms, respectively, achieved a TPR of 22.7% and 27.3% with zero FPRs. The lead prediction time of these two conditions was 5.7 ± 6.8 hours and 8.0 ± 7.2 hours, respectively. Performance of triggers based on the absolute slope values depended on the window length used for linear fitting. rAmp slope of a 2-hour window, PRp slope of a 30-minute window, and relJAmp slope of a 2-hour window achieved the best TPR of 27.3% (FPR = 2.3%, lead time = 6.5 ± 5.7 hours), 14.3% (FPR=0.0%, lead time = 10.9 ± 10.9), and 18.2% (FPR = 2.3%, lead time = 8.8 ± 9.8), respectively. McNemar test showed that only relJAmp >20.0% is significantly different from the baseline trigger of HR >149.3 bpm (p=0.046). In addition, metrics-based and slope-based triggers were complementary as an "OR" combination of two single-metric triggers raised the TPR up to 45.4% with zero FPR.

CONCLUSIONS

It is feasible to compute additional metrics from continuous ECG from bedside monitors. These additional parameters can provide highly specific triggers for predicting bradyasystolic cardiac arrest. Complementary triggers based on the slope of trending of these ECG metrics can further increase the sensitivity without incurring false positives.

Single pulse analysis of intracranial pressure for a hydrocephalus implant

The intracranial pressure (ICP) waveform contains important diagnostic information. Changes in ICP are associated with changes of the pulse waveform. This change has explicitly been observed in 13 infusion tests by analyzing 100 Hz ICP data. An algorithm is proposed which automatically extracts the pulse waves and categorizes them into predefined patterns. A developed algorithm determined 88 %±8 % (mean ±SD) of all classified pulse waves correctly on predefined patterns. This algorithm has low computational cost and is independent of a pressure drift in the sensor by using only the relationship between special waveform characteristics. Hence, it could be implemented on a microcontroller of a future electromechanic hydrocephalus shunt system to control the drainage of cerebrospinal fluid (CSF).

Subpeak regional analysis of intracranial pressure waveform morphology based on cerebrospinal fluid hydrodynamics in the cerebral aqueduct and prepontine cistern

The objective of this study is to investigate the relationship between intracranial pressure (ICP) pulse waveform morphology and selected hydrodynamic metrics of cerebrospinal fluid (CSF) movement using a novel method for ICP pulse pressure regional analysis based on the Morphological Clustering and Analysis of Continuous Intracranial Pulse (MOCAIP) algorithm.

Machine learning techniques for arterial pressure waveform analysis

The Arterial Pressure Waveform (APW) can provide essential information about arterial wall integrity and arterial stiffness. Most of APW analysis frameworks individually process each hemodynamic parameter and do not evaluate inter-dependencies in the overall pulse morphology. The key contribution of this work is the use of machine learning algorithms to deal with vectorized features extracted from APW. With this purpose, we follow a five-step evaluation methodology: (1) a custom-designed, non-invasive, electromechanical device was used in the data collection from 50 subjects; (2) the acquired position and amplitude of onset, Systolic Peak (SP), Point of Inflection (Pi) and Dicrotic Wave (DW) were used for the computation of some morphological attributes; (3) pre-processing work on the datasets was performed in order to reduce the number of input features and increase the model accuracy by selecting the most relevant ones; (4) classification of the dataset was carried out using four different machine learning algorithms: Random Forest, BayesNet (probabilistic), J48 (decision tree) and RIPPER (rule-based induction); and (5) we evaluate the trained models, using the majority-voting system, comparatively to the respective calculated Augmentation Index (AIx). Classification algorithms have been proved to be efficient, in particular Random Forest has shown good accuracy (96.95%) and high area under the curve (AUC) of a Receiver Operating Characteristic (ROC) curve (0.961). Finally, during validation tests, a correlation between high risk labels, retrieved from the multi-parametric approach, and positive AIx values was verified. This approach gives allowance for designing new hemodynamic morphology vectors and techniques for multiple APW analysis, thus improving the arterial pulse understanding, especially when compared to traditional single-parameter analysis, where the failure in one parameter measurement component, such as Pi, can jeopardize the whole evaluation.

Semi-supervised detection of intracranial pressure alarms using waveform dynamics

Patient monitoring systems in intensive care units (ICU) are usually set to trigger alarms when abnormal values are detected. Alarms are generated by threshold-crossing rules that lead to high false alarm rates. This is a recognized issue that causes alarm fatigue, waste of human resources, and increased patient risks. Recently developed smart alarm models require alarms to be validated by experts during the training phase. The manual annotation process involved is time-consuming and virtually impossible to achieve for the thousands of alarms recorded in the ICU every week. To tackle this problem, we investigate in this study if the use of semi-supervised learning methods, that can naturally integrate unlabeled data samples in the model, can be used to improve the accuracy of the alarm detection. As a proof of concept, the detection system is evaluated on intracranial pressure (ICP) signal alarms. Specific morphological and trending features are extracted from the ICP signal waveform to capture the dynamic of the signal prior to alarms. This study is based on a comprehensive dataset of 4791 manually labeled alarms recorded from 108 neurosurgical patients. A comparative analysis is provided between kernel spectral regression (SR-KDA) and support vector machine (SVM) both modified for the semi-supervised setting. Results obtained during the experimental evaluations indicate that the two models can significantly reduce false alarms using unlabeled samples; especially in the presence of a restrained number of labeled examples. At a true alarm recognition rate of 99%, the false alarm reduction rates improved from 9% (supervised) to 27% (semi-supervised) for SR-KDA, and from 3% (supervised) to 16% (semi-supervised) for SVM.

Analysis of Intracranial Pressure

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

Continuous detection of cerebral vasodilatation and vasoconstriction using intracranial pulse morphological template matching

Although accurate and continuous assessment of cerebral vasculature status is highly desirable for managing cerebral vascular diseases, no such method exists for current clinical practice. The present work introduces a novel method for real-time detection of cerebral vasodilatation and vasoconstriction using pulse morphological template matching. Templates consisting of morphological metrics of cerebral blood flow velocity (CBFV) pulse, measured at middle cerebral artery using Transcranial Doppler, are obtained by applying a morphological clustering and analysis of intracranial pulse algorithm to the data collected during induced vasodilatation and vasoconstriction in a controlled setting. These templates were then employed to define a vasodilatation index (VDI) and a vasoconstriction index (VCI) for any inquiry data segment as the percentage of the metrics demonstrating a trend consistent with those obtained from the training dataset. The validation of the proposed method on a dataset of CBFV signals of 27 healthy subjects, collected with a similar protocol as that of training dataset, during hyperventilation (and CO₂ rebreathing tests) shows a sensitivity of 92% (and 82%) for detection of vasodilatation (and vasoconstriction) and the specificity of 90% (and 92%), respectively. Moreover, the proposed method of detection of vasodilatation (vasoconstriction) is capable of rejecting all the cases associated with vasoconstriction (vasodilatation) and outperforms other two conventional techniques by at least 7% for vasodilatation and 19% for vasoconstriction.

Noninvasive intracranial hypertension detection utilizing semisupervised learning

Intracranial pressure (ICP) monitoring is an established clinical practice in managing patients with risk of acute ICP elevation although the clinically accepted way of measuring ICP remains invasive. However, the invasive nature of ICP measurement obviates its application in many clinical circumstances such as diagnosis of idiopathic intracranial hypertension (IH). We propose a noninvasive diagnostic tool for IH based on the morphological analysis of cerebral blood flow velocity waveforms. We mainly compare two types of IH detection methods: one based on the traditional supervised learning approach and the other based on the semisupervised learning approach. Our simulation results demonstrate that the predictive accuracy (area under the curve) of the semisupervised IH detection method can be as high as 92% while that of the supervised IH detection method is only around 82%. It should be noted that the predictive accuracy of the pulsatility index (PI)-based IH detection method is as low as 59%. Although the predictive accuracy is a widely used accuracy measurement, it does not consider clinical consequences of necessary and unnecessary treatments. For this reason, we have adopted the decision curve analysis to address this issue. The decision curve analysis results show that the semisupervised IH detection method is not only more accurate, but also clinically more useful than the supervised IH detection method or the PI-based IH detection method.

Steady-state indicators of the intracranial pressure dynamic system using geodesic distance of the ICP pulse waveform

Normal functioning of the brain depends on the homeostasis (∼ steady state) of its various physiological sub-systems, one of which is the intracranial pressure (ICP) dynamic system. The ICP dynamic system of an injured brain is susceptible to various acute changes that should ideally be detected by ICP monitoring even for comatose patients. However, the status quo of ICP monitoring solely targets mean ICP. We aimed to demonstrate a novel approach to detect acute deviation from steady state of an ICP dynamic system in an absence of significant mean ICP changes. We hypothesized that steady state of ICP dynamic systems is reflected as ICP pulses of similar mean ICP levels resembling each other for a given subject. A general framework was used to derive such a steady-state indicator that can accommodate different metrics of inter-pulse distance and different statistics of the distance histograms. In addition to conventional Euclidean distance and Pearson correlation, geodesic distance between pulses was introduced as a novel metric. These different ways of calculating steady-state indicators under the proposed framework were evaluated on three types of continuous ICP recordings: (1) those between two consecutive brain imaging studies that demonstrated acute ventricular enlargement for slit ventricle syndrome (SVS) patients undergoing a trial of shunt externalization and clamping (SVS+); (2) those between consecutive brain imaging studies from the SVS patients under the same trial but without ventricular enlargement (SVS-); (3) overnight recordings from normal pressure hydrocephalus (NPH) patients. It was observed that only the standard deviation of geodesic distance correctly differentiated between SVS+ and SVS- and between SVS+ and NPH while avoiding discriminating between SVS- and NPH. It was also found that 45% SVS+ cases had a multimodal geodesic distance histogram while none of SVS- and 3.8% of NPH cases had such a multimodal histogram. Pulses with a large number of distant pulses for the five multimodal-histogram SVS+ cases fell in short time windows indicating that acute ventricular changes may have occurred in these confined time windows during which no significant changes of mean ICP were observed. In contrast, the pulses with a large number of distant pulses for the two multimodal-histogram NPH cases did not cluster temporally. In conclusion, the geodesic inter-pulse distance is a promising metric to quantify distance intrinsic to the underneath geometric structure of ICP signals and hence is a more suitable way to derive a steady-state indicator of an ICP dynamic system.

Intracranial pressure pulse waveform correlates with aqueductal cerebrospinal fluid stroke volume

This study identifies a novel relationship between cerebrospinal fluid (CSF) stroke volume through the cerebral aqueduct and the characteristic peaks of the intracranial pulse (ICP) waveform. ICP waveform analysis has become much more advanced in recent years; however, clinical practice remains restricted to mean ICP, mainly due to the lack of physiological understanding of the ICP waveform. Therefore, the present study set out to shed some light on the physiological meaning of ICP morphological metrics derived by the morphological clustering and analysis of continuous intracranial pulse (MOCAIP) algorithm by investigating their relationships with a well defined physiological variable, i.e., the stroke volume of CSF through the cerebral aqueduct. Seven patients received both overnight ICP monitoring along with a phase-contrast MRI (PC-MRI) of the cerebral aqueduct to quantify aqueductal stroke volume (ASV). Waveform morphological analysis of the ICP signal was performed by the MOCAIP algorithm. Following extraction of morphological metrics from the ICP signal, nine temporal ICP metrics and two amplitude-based metrics were compared with the ASV via Spearman's rank correlation. Of the nine temporal metrics correlated with the ASV, only the width of the P2 region (ICP-Wi2) reached significance. Furthermore, both ICP pulse pressure amplitude and mean ICP did not reach significance. In this study, we showed the width of the second peak (ICP-Wi2) of an ICP pulse wave is positively related to the volume of CSF movement through the cerebral aqueduct. This finding is an initial step in bridging the gap between ICP waveform morphology research and clinical practice.

Reducing false intracranial pressure alarms using morphological waveform features

False alarms produced by patient monitoring systems in intensive care units are a major issue that causes alarm fatigue, waste of human resources, and increased patient risks. While alarms are typically triggered by manually adjusted thresholds, the trend and patterns observed prior to threshold crossing are generally not used by current systems. This study introduces and evaluates, a smart alarm detection system for intracranial pressure signal (ICP) that is based on advanced pattern recognition methods. Models are trained in a supervised fashion from a comprehensive dataset of 4791 manually labeled alarm episodes extracted from 108 neurosurgical patients. The comparative analysis provided between spectral regression, kernel spectral regression, and support vector machines indicates the significant improvement of the proposed framework in detecting false ICP alarms in comparison to a threshold-based technique that is conventionally used. Another contribution of this work is to exploit an adaptive discretization to reduce the dimensionality of the input features. The resulting features lead to a decrease of 30% of false ICP alarms without compromising sensitivity.

A new approach for investigating intracranial pressure signal: filtering and morphological features extraction from continuous recording

Nowadays, the Intracranial Pressure (ICP) monitoring has become the most common method of investigation for both traumatic and chronic neural pathologies. ICP signals are typically triphasic, that is, in a single waveform, three subpeaks can be identified. This work outlines a new algorithm to identify subpeaks from the ICP recordings and to extract a number of 20 meaningful parameter trends. The validity of the implemented method has been proved through a comparison between the automatic subpeaks identification by the algorithm and the manually marked subpeaks by a neurosurgeon. The automatic marking system has identified subpeaks for the 63.74% (mean value) of pulse waves, providing the position and amplitude of each identified subpeak within a tolerance of ±7 samples. This automatic system provides a feature set to be used by classification software to obtain more precise and easier diagnosis in all those cases that involve brain damages or diseases.

Intracranial hypertension prediction using extremely randomized decision trees

Intracranial pressure (ICP) elevation (intracranial hypertension, IH) in neurocritical care is typically treated in a reactive fashion; it is only delivered after bedside clinicians notice prolonged ICP elevation. A proactive solution is desirable to improve the treatment of intracranial hypertension. Several studies have shown that the waveform morphology of the intracranial pressure pulse holds predictors about future intracranial hypertension and could therefore be used to alert the bedside clinician of a likely occurrence of the elevation in the immediate future. In this paper, a computational framework is proposed to predict prolonged intracranial hypertension based on morphological waveform features computed from the ICP. A key contribution of this work is to exploit an ensemble classifier method based on extremely randomized decision trees (Extra-Trees). Experiments on a representative set of 30 patients admitted for various intracranial pressure related conditions demonstrate the effectiveness of the predicting framework on ICP pulses acquired under clinical conditions and the superior results of the proposed approach in comparison to linear and AdaBoost classifiers.

Automated extraction of decision rules for predicting lumbar drain outcome by analyzing overnight intracranial pressure

BACKGROUND

Extended lumbar drain (ELD) has become a popular pre-shunt workup test to help diagnose normal pressure hydrocephalus (NPH). Unfortunately, this procedure requires a substantial time investment for both the family and hospital. In this study, we investigate how accurate the prediction of ELD outcome can be achieved by using simple decision rules automatically derived from pulse morphological metrics of overnight ICP recordings. Our ultimate goal is to test the hypothesis that overnight ICP monitoring, empowered by subsequent signal analysis, could be an alternative to ELD.

METHODS

The present study involved 54 patients with both ELD and overnight ICP recordings; the ICP morphological analysis was performed using the MOCAIP algorithm. Furthermore, the distribution of individual metric from the overnight recording was characterized using five aggregation functions (features). Then an algorithm was developed to automatically discover the most accurate "if-then" decision rule for each of the five feature functions. In addition, the best combination of two decision rules, either using "AND" or "OR" operator, was obtained.

FINDINGS

Rules based on five individual feature functions achieved an accuracy of 70.4%, 72.2%, 74.1%, 72.2%, and 79.6% respectively. However, "OR" combination of two features improved accuracy to 88.9%.

CONCLUSION

We showed an algorithm to discover decision rules that can potentially predict ELD outcome.

Bayesian tracking of intracranial pressure signal morphology

BACKGROUND

The waveform morphology of intracranial pressure (ICP) pulses holds essential informations about intracranial and cerebrovascular pathophysiological variations. Most of current ICP pulse analysis frameworks process each pulse independently and therefore do not exploit the temporal dependency existing between successive pulses. We propose a probabilistic framework that exploits this temporal dependency to track ICP waveform morphology in terms of its three peaks.

MATERIAL

ICP and electrocardiogram (ECG) signals were recorded from a total of 128 patients treated for various intracranial pressure related conditions.

METHODS

The tracking is posed as inference in a graphical model that associates a random variable to the position of each peak. A key contribution is to exploit a nonparametric Bayesian inference algorithm that offers robustness and real time performance. A simple, yet effective learning procedure estimates the statistical, nonlinear, dependencies between the peaks in a nonparametric way using evidence collected from manually annotated pulses.

RESULTS

Experiments demonstrate the effectiveness of the tracking framework on real ICP pulses and its robustness to occlusion and missing peaks. On artificialy distorted ICP sequences, the average error in latency in comparision with MOCAIP detector was reduced as follows: 11.88-8.09 ms, 11.80-6.90 ms, and 11.76-7.46 ms for the first, second, and third peak, respectively.

CONCLUSION

The proposed tracking algorithm sucessfuly increases the temporal resolution of detecting ICP pulse morphological changes from the minute-level to the beat-level.

Lack of consistent intracranial pressure pulse morphological changes during episodes of microdialysis lactate/pyruvate ratio increase

Lactate/pyruvate ratio (LPR) from microdialysis is a well-established marker of cerebral metabolic crisis. For brain injury patients, abnormally high LPR could indicate cerebral ischemia or failure of O(2) uptake. However, there is a debate on the primary factor responsible for LPR increase. Exploiting the potential of using the morphology of a high temporal resolution signal such as intracranial pulse (ICP) to characterize cerebrovascular changes, a data analysis experiment is taken to test whether consistent changes in ICP pulse morphological metrics accompany the LPR increase. We studied 3517 h of LPR and continuous ICP data from 19 severe traumatic brain injury patients. Our morphological clustering and analysis of intracranial pressure (MOCAIP) algorithm was applied to ICP pulses, which were matched in time to the LPR measurements, and 128 pulse morphological metrics were extracted. We automatically identified the episodes of LPR increases using a moving time window of 10-20 h. We then studied the trending patterns of each of the 128 ICP MOCAIP metrics within these identified periods and determined them to be one of the following three types: increasing, decreasing or no trend. A binomial test was employed to investigate whether any MOCAIP metrics show a consistent trend among all episodes of LPR increase per patient. Regardless of the selected values for different parameters of the proposed method, for the majority of the subjects in the study (78%), none of the ICP metrics show any consistent trend during the episodes of LPR increase. Even for the few subjects who have at least one ICP metric with a consistent trend during the LPR increase episodes, the number of such metrics is small and varies from subject to subject. Given the fact that ICP pulse morphology is influenced by the cerebral vasculature, our results suggest that a dominant cerebral vascular cause may be behind the changes in LPR when LPR trends correlate with ICP pulse morphological changes. However, the incidence of such correlation seems to be low.

Consistent changes in intracranial pressure waveform morphology induced by acute hypercapnic cerebral vasodilatation

BACKGROUND

Intracranial pressure (ICP) remains a pivotal physiological signal for managing brain injury and subarachnoid hemorrhage (SAH) patients in neurocritical care units. Given the vascular origin of the ICP, changes in ICP waveform morphology could be used to infer cerebrovascular changes. Clinical validation of this association in the setting of brain trauma, and SAH is challenging due to the multi-factorial influences on, and uncertainty of, the state of the cerebral vasculature.

METHODS

To gain a more controlled setting, in this articel, we study ICP signals recorded in four uninjured patients undergoing a CO2 inhalation challenge in which hypercapnia induced acute cerebral vasodilatation. We apply our morphological clustering and analysis of intracranial pressure (MOCAIP) algorithm to identify six landmarks on individual ICP pulses (based on the three established ICP sub-peaks; P1, P2, and P3) and extract 128 ICP morphological metrics. Then by comparing baseline, test, and post-test data, we assess the consistency and rate of change for each individual metric.

RESULTS

Acute vasodilatation causes consistent changes in a total of 72 ICP pulse morphological metrics and the P2 sub-region responds to cerebral vascular changes in the most consistent way with the greatest change as compared to P1 and P3 sub-regions.

CONCLUSIONS

Since the dilation/constriction of the cerebral vasculature resulted in detectable consistent changes in ICP MOCIAP metrics, by an extended monitoring practice of ICP that includes characterizing ICP pulse morphology, one can potentially detect cerebrovascular changes, continuously, for patients under neurocritical care.

Waveform descriptor for pulse onset detection of intracranial pressure signal

We present an algorithm to identify the onset of intracranial pressure (ICP) pulses. The algorithm creates a waveform descriptor to extract the feature of each local minimum of the waveform and then identifies the onset by comparing the feature with a customized template. The waveform descriptor is derived by transforming the vectors connecting a given point and the local waveform samples around it into log-polar coordinates and ranking them into uniform bins. Using an ICP dataset consisting of 40933 normal beats and 306 segments of artifacts and noise, we investigated the performance of our algorithm (waveform descriptor, WD), global minimum within a sliding window (GM) and two other algorithms originally proposed for arterial blood pressure (ABP) signal (slope sum function, SSF and pulse waveform delineator, PUD). As a result, all the four algorithms showed good performance and WD showed overall better one. At a tolerance level of 30 ms (i.e., the predicted onset and ground truth were considered as correctly matched if the distance between the two was equal or less than 30 ms), WD achieved a sensitivity of 0.9723 and PPV of 0.9475, GM achieved a sensitivity of 0.9226 and PPV of 0.8968, PUD achieved a sensitivity of 0.9599 and PPV of 0.9327 and SSF, a sensitivity of 0.9720 and PPV of 0.9136. The evaluation indicates that the algorithms are effective for identifying the onset of ICP pulses.

The pulsating brain: A review of experimental and clinical studies of intracranial pulsatility

The maintenance of adequate blood flow to the brain is critical for normal brain function; cerebral blood flow, its regulation and the effect of alteration in this flow with disease have been studied extensively and are very well understood. This flow is not steady, however; the systolic increase in blood pressure over the cardiac cycle causes regular variations in blood flow into and throughout the brain that are synchronous with the heart beat. Because the brain is contained within the fixed skull, these pulsations in flow and pressure are in turn transferred into brain tissue and all of the fluids contained therein including cerebrospinal fluid. While intracranial pulsatility has not been a primary focus of the clinical community, considerable data have accrued over the last sixty years and new applications are emerging to this day. Investigators have found it a useful marker in certain diseases, particularly in hydrocephalus and traumatic brain injury where large changes in intracranial pressure and in the biomechanical properties of the brain can lead to significant changes in pressure and flow pulsatility. In this work, we review the history of intracranial pulsatility beginning with its discovery and early characterization, consider the specific technologies such as transcranial Doppler and phase contrast MRI used to assess various aspects of brain pulsations, and examine the experimental and clinical studies which have used pulsatility to better understand brain function in health and with disease.

Forecasting ICP elevation based on prescient changes of intracranial pressure waveform morphology

Interventions of intracranial pressure (ICP) elevation in neurocritical care is currently delivered only after healthcare professionals notice sustained and significant mean ICP elevation. This paper uses the morphological clustering and analysis of ICP (MOCAIP) algorithm to derive 24 metrics characterizing morphology of ICP pulses and test the hypothesis that preintracranial hypertension (Pre-IH) segments of ICP can be differentiated, using these morphological metrics, from control segments that were not associated with any ICP elevation or at least 1 h prior to ICP elevation. Furthermore, we investigate whether a global optimization algorithm could effectively find the optimal subset of these morphological metrics to achieve better classification performance as compared to using full set of MOCAIP metrics. The results showed that Pre-IH segments, using the optimal subset of metrics found by the differential evolution algorithm, can be differentiated from control segments at a specificity of 99% and sensitivity of 37% for these Pre-IH segments 5 min prior to the ICP elevation. While the sensitivity decreased to 21% for Pre-IH segments, 20 min prior to ICP elevation, the high specificity of 99% was retained. The performance using the full set of MOCAIP metrics was shown inferior to results achieved using the optimal subset of metrics. This paper demonstrated that advanced ICP pulse analysis combined with machine learning could potentially leads to the forecasting of ICP elevation so that a proactive ICP management could be realized based on these accurate forecasts.

Inter-subject correlation exists between morphological metrics of cerebral blood flow velocity and intracranial pressure pulses

BACKGROUND

The prototypical intracranial pressure (ICP) pulse morphology has been well known to be triphasic. Several studies suggest that the morphology of ICP pulse reflects the physiological and pathophysiological conditions of the intracranial dynamics. Recently, there has been a renaissance of studying ICP pulse using new ICP signal processing technologies in various clinical contexts. Cerebral blood flow velocity (CBFV) pulse is another important pulsatile signal originated from the complex circulatory systems of cerebral blood flow. However, CBFV pulse morphology has not been well studied mainly due to the noise level and lack of signal processing techniques.

METHODS

Our group recently developed a technique called the morphological clustering and analysis of intracranial pressure that can extract a comprehensive set of pulse morphological metrics. We extend this algorithm to extract various morphological metrics from ICP and CBFV pulses that were simultaneously recorded from 47 brain injury patients and investigate the mutual correlation between those metrics utilizing the robust percentage bend correlation analysis.

RESULTS

Our results show that CBFV pulses are also triphasic as ICP pulses and 15.2% of 128 pulse morphological metrics extracted from ICP and CBFV pulses are highly correlated (P < 0.01) in an inter-subject fashion. In addition, mean ICP does not correlate (P = 0.45) with the pulsatility index of CBFV pulses but correlates (P < 0.05) with several novel CBFV pulse morphological metrics such as the time interval between the onset of CBFV pulses and ECG QRS peak.

CONCLUSIONS

Our results suggest that characterizing CBFV pulse morphology is clinically important because it may offer a potential noninvasive alternative to assess various aspects of ICP such as mean ICP.

Robust peak recognition in intracranial pressure signals

Background

The waveform morphology of intracranial pressure pulses (ICP) is an essential indicator for monitoring, and forecasting critical intracranial and cerebrovascular pathophysiological variations. While current ICP pulse analysis frameworks offer satisfying results on most of the pulses, we observed that the performance of several of them deteriorates significantly on abnormal, or simply more challenging pulses.

Methods

This paper provides two contributions to this problem. First, it introduces MOCAIP++, a generic ICP pulse processing framework that generalizes MOCAIP (Morphological Clustering and Analysis of ICP Pulse). Its strength is to integrate several peak recognition methods to describe ICP morphology, and to exploit different ICP features to improve peak recognition. Second, it investigates the effect of incorporating, automatically identified, challenging pulses into the training set of peak recognition models.

Results

Experiments on a large dataset of ICP signals, as well as on a representative collection of sampled challenging ICP pulses, demonstrate that both contributions are complementary and significantly improve peak recognition performance in clinical conditions.

Conclusion

The proposed framework allows to extract more reliable statistics about the ICP waveform morphology on challenging pulses to investigate the predictive power of these pulses on the condition of the patient.

Pattern recognition of overnight intracranial pressure slow waves using morphological features of intracranial pressure pulse

This study aimed to develop a new approach to detect intracranial pressure (ICP) slow waves based on morphological changes of ICP pulse waveforms. A recently proposed Morphological Clustering and Analysis of ICP Pulse (MOCAIP) algorithm was utilized to calculate a set of metrics that characterize ICP pulse morphology. A regularized linear quadratic classifier was used to test the hypothesis that classification between ICP slow wave and flat ICP could be achieved using features composed of mean values and dispersion of 24 MOCAIP metrics. To optimize the classification performance, three feature selection techniques (differential evolution, discriminant analysis and analysis of variance) were applied to find an optimal set of MOCAIP metrics under different criteria. In addition, we selected three sets of metrics common to those found by combination of two selection methods, to be used as classification features (differential evolution and analysis of variance, discriminant analysis and analysis of variance, and combination of differential evolution and discriminant analysis). To test the approach, a total of 276 selections of ICP recordings corresponding to two patterns without waves and containing slow waves were obtained from overnight ICP studies of 44 hydrocephalus patients performed at the UCLA Adult Hydrocephalus Center. Our results showed that the best classification performance of differentiation of slow waves from the ICP recording without slow waves was obtained using the combination of metrics common to both differential evolution and analysis of variance methods; achieving an accuracy of 89%, specificity 96%, and sensitivity 83%.

Intracranial pressure pulse morphological features improved detection of decreased cerebral blood flow

We investigated whether intracranial pressure (ICP) pulse morphological metrics could be used to realize continuous detection of low cerebral blood flow. Sixty-three acutely brain injured patients with ICP monitoring, daily (133)Xenon cerebral blood flow (CBF) and daily transcranial Doppler (TCD) assessments were studied. Their ICP recordings were time-aligned with the CBF and TCD measurements so that a 1 h ICP segment near the CBF and TCD measurements was obtained. Each of these recordings was processed by the Morphological Cluster and Analysis of Intracranial Pressure (MOCAIP) algorithm to extract pulse morphological metrics. Then the differential evolution algorithm was used to find the optimal combination of the metrics that provided, using the regularized linear discriminant analysis, the largest combined positive predictivity and sensitivity. At a CBF threshold of 20 ml/min/100 g, a sensitivity of 81.8 +/- 0.9% and a specificity of 50.1 +/- 0.2% were obtained using the optimal combination of conventional TCD and blood analysis metrics as input to a regularized linear classifier. However, using the optimal combination of the MOCAIP metrics alone we were able to achieve a sensitivity of 92.5 +/- 0.7% and a specificity of 84.8 +/- 0.8%. Searching the optimal combination of all available metrics, we achieved the best result that was marginally better than those from using MOCAIP alone. This study demonstrated that the potential role of ICP monitoring may be extended to provide an indicator of low global cerebral blood perfusion.

A robust approach toward recognizing valid arterial-blood-pressure pulses

We propose a projection method based on singular value decomposition (SVD) to validate arterial blood pressure (ABP) signal in order to avoid artifacts and noise in subsequent processing. The projection has been done on 567 validated ABP beats collected from 51 patients hospitalized in University of California, Los Angeles Medical Center. Then, we compare the performance of the proposed projection method with that of a previously developed algorithm, signal abnormality index (SAI), which is a value- and trend-based approach, and has shown to be effective in cleaning the ABP waveforms. The testing dataset consists of 1336 ten-second ABP segments (18 472 ABP beats) of both valid and invalid pulses selected randomly from multiparameter intelligent monitoring for intensive care II database. The proposed projection approach that validates the signal based on the shape of the waveform achieves a true positive rate (TPR) of 99.06%, 5.43% higher than that of the SAI, and a false positive rate (FPR) of 7.69%, 17.38% lower than that of SAI. Integration of some of the SAI-value-based abnormality conditions to the validation process of SVD-based method can further improve the performance by reducing the FPR to 3.92%, while keeping the TPR at the high rate of 99.05%.

A subspace decomposition approach toward recognizing valid pulsatile signals

Following recent studies, the automatic analysis of intracranial pressure (ICP) pulses appears to be a promising tool for the prediction of critical intracranial and cerebrovascular pathophysiological variations during the management of many neurological disorders. A pulse analysis framework has been recently developed to automatically extract morphological features of ICP pulses. The algorithm is capable of enhancing the quality of ICP signals, recognizing valid (not contaminated with noise or artifacts) ICP pulses and designating the locations of the three ICP sub-peaks in a pulse. This paper extends the algorithm by proposing a singular value decomposition (SVD) technique to replace the correlation-based approach originally utilized in recognizing valid ICP pulses. The validation of the proposed method is conducted on a large database of ICP signals built from 700 h of recordings from 67 neurosurgical patients. A comparative analysis of the valid ICP recognition using the proposed SVD technique and the correlation-based method demonstrates a significant improvement in terms of (1) accuracy (61.96% reduction in the false positive rate while keeping the true positive rate as high as 99.08%) and (2) computational time (91.14% less time consumption), all in favor of the proposed method. Finally, this SVD-based valid pulse recognition can be potentially applied to process pulsatile signals other than ICP because no proprietary ICP features are incorporated in the algorithm.

Regression analysis for peak designation in pulsatile pressure signals

Following recent studies, the automatic analysis of intracranial pressure (ICP) pulses appears to be a promising tool for forecasting critical intracranial and cerebrovascular pathophysiological variations during the management of many disorders. A pulse analysis framework has been recently developed to automatically extract morphological features of ICP pulses. The algorithm is able to enhance the quality of ICP signals, to segment ICP pulses, and to designate the locations of the three ICP sub-peaks in a pulse. This paper extends this algorithm by utilizing machine learning techniques to replace Gaussian priors used in the peak designation process with more versatile regression models. The experimental evaluations are conducted on a database of ICP signals built from 700 h of recordings from 64 neurosurgical patients. A comparative analysis of different state-of-the-art regression analysis methods is conducted and the best approach is then compared to the original pulse analysis algorithm. The results demonstrate a significant improvement in terms of accuracy in favor of our regression-based recognition framework. It reaches an average peak designation accuracy of 99% using a kernel spectral regression against 93% for the original algorithm.

Nonlinear regression for sub-peak detection of intracranial pressure signals

The management of many neurological disorders such as traumatic brain injuries relies on the continuous measurement of intracranial pressure (ICP). Following recent studies, the automatic analysis of ICP pulse seems to be a promising tool for forecasting intracranial and cerebrovascular pathophysiological changes. MOCAIP algorithm has recently been developed to automatically extract ICP morphological features in real time. The algorithm is capable of enhancing ICP signal quality, recognizing legitimate ICP pulses, and designating the three peaks in an ICP pulse. This paper extends MOCAIP by using a regression model instead of Gaussian priors during the peak designation to improve the accuracy of the process. The experimental evaluations of the proposed algorithm are performed on a ICP signal database built from 700 hours of recordings from 66 neurosurgical patients. They indicate that the use of a regression model significantly increases the peak designation accuracy.