Cerebral compliance assessment from intracranial pressure waveform analysis: Is a positional shift-related increase in intracranial pressure predictable?

Abstract

Real-time monitoring of intracranial pressure (ICP) is a routine part of neurocritical care in the management of brain injury. While mainly used to detect episodes of intracranial hypertension, the ICP signal is also indicative of the volume-pressure relationship within the cerebrospinal system, often referred to as intracranial compliance (ICC). Several ICP signal descriptors have been proposed in the literature as surrogates of ICC, but the possibilities of combining these are still unexplored. In the present study, a rapid ICC assessment consisting of a 30-degree postural shift was performed on a cohort of 54 brain-injured patients. 73 ICP signal features were calculated over the 20 minutes prior to the ICC test. After a selection step, different combinations of these features were provided as inputs to classification models. The goal was to predict the level of induced ICP elevation, which was categorized into three classes: less than 7 mmHg ("good ICC"), between 7 and 10 mmHg ("medium ICC"), and more than 10 mmHg ("poor ICC"). A logistic regression model fed with a combination of 5 ICP signal features discriminated the "poor ICC" class with an area under the receiving operator curve (AUROC) of 0.80 (95%-CI: [0.73-0.87]). The overall one-versus-one classification task was achieved with an averaged AUROC of 0.72 (95%-CI: [0.61-0.83]). Adding more features to the input set and/or using nonlinear machine learning algorithms did not significantly improve classification performance. This study highlights the potential value of analyzing the ICP signal independently to extract information about ICC status. At the patient's bedside, such univariate signal analysis could be implemented without dependence on a specific setup.

Fig 1. Feature extraction and selection process.

ICC: Intracranial compliance, AMP: ICP Pulse amplitude, RAP: RAP index, RAQ: RAQ index, HCD: Heart cycle duration, P2/P1: P2/P1 ratio, EEMD: Ensemble empirical mode decomposition, IQR: Interquartile range, PE: Permutation entropy, MP: Missing patterns, IA: Instantaneous amplitude, TE: Teager energy, FC: Frequency centroid, FSD: Frequency standard deviation, SVM: Support vector machine.

Fig 2. Seven intrinsic mode functions (IMF) iteratively extracted from a 60-second intracranial pressure signal with ensemble empirical mode decomposition.

Fig 3. Example of a strong intracranial pressure morphology change induced by a 30° postural shift.

Fig 4. Intrinsic mode functions (IMF) frequency centroids calculated from the intracranial pressure signals monitored in the 20 minutes preceding the positional shift.

Each histogram corresponds to an IMF centroid distribution over the whole dataset.

Fig 5. Correlation matrix over the ten best ranked features.

IMF: Intrinsic Mode Function. Hurst: Hurst Exponent. FSD: Frequency Standard Deviation.

Fig 6. Spearman correlation coefficients between the ten highest ranked ICP signal features and five biological variables.

IMF: Intrinsic Mode Function, FSD: Frequency Standard Deviation, MAP: Mean Arterial Pressure, CPP: Cerebral Perfusion Pressure.

Fig 7. Area under the receiver operating curve of the classifiers as a function of the number of input features.

Models were evaluated here on their ability to discriminate patients with impaired intracranial compliance (“poor compliance” class). SVM: Support Vector Machine. Shaded areas correspond to a 95% confidence interval.