Related Experiment Video
Updated: Jun 10, 2026

A Detailed Protocol for Physiological Parameters Acquisition and Analysis in Neurosurgical Critical Patients
Published on: October 17, 2017
Forecasting ICP elevation based on prescient changes of intracranial pressure waveform morphology
Xiao Hu1, Peng Xu, Shadnaz Asgari
1Neural Systems and Dynamics Laboratory, Department of Neurosurgery, David Geffen School of Medicine, University of California, Los Angeles, CA 90024, USA.
This study introduces a novel algorithm to analyze intracranial pressure (ICP) pulses, enabling early detection of potential ICP elevation. This could lead to proactive neurocritical care management.
Area of Science:
- Neuroscience
- Medical Technology
- Data Science
Background:
- Intracranial pressure (ICP) interventions are typically reactive, occurring after sustained ICP elevation is detected.
- Current methods lack the ability to predict impending ICP increases, limiting proactive management in neurocritical care.
Purpose of the Study:
- To develop and validate a method for differentiating pre-intracranial hypertension (Pre-IH) ICP segments from normal ICP segments.
- To identify an optimal subset of ICP morphological metrics for improved classification performance.
- To explore the potential for forecasting ICP elevation for proactive management.
Main Methods:
- Utilized the Morphological Clustering and Analysis of ICP (MOCAIP) algorithm to extract 24 morphological metrics from ICP pulses.
- Employed a global optimization algorithm (differential evolution) to find the optimal subset of MOCAIP metrics.
- Compared classification performance using the full MOCAIP metric set versus the optimized subset.
Main Results:
- The optimal subset of MOCAIP metrics differentiated Pre-IH segments from control segments with 99% specificity and 37% sensitivity at 5 minutes prior to ICP elevation.
- Specificity remained high (99%) at 20 minutes prior, though sensitivity decreased to 21%.
- The optimized subset outperformed the full set of MOCAIP metrics in classification accuracy.
Conclusions:
- Advanced ICP pulse analysis using MOCAIP metrics and machine learning can potentially forecast ICP elevation.
- This forecasting capability may enable proactive ICP management strategies in neurocritical care.
- The study highlights the efficacy of optimized feature subsets for improved predictive performance.
Related Concept Videos
Increased Intracranial Pressure ll: Pathophysiology
Increased Intracranial Pressure l: Introduction
Cerebral Edema ll: Pathophysiology
Cerebral Edema l: Introduction

