Related Experiment Video
Updated: May 11, 2026
14:08
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
42.4K
Classification of intracranial pressure epochs using a novel machine learning framework.
Rohan Mathur1,2,3, Sudha Yellapantula4, Lin Cheng5,6,7,8
1Division of Neurosciences Critical Care, Johns Hopkins University School of Medicine, Baltimore, MD, USA. rmathur2@jhmi.edu.
NPJ Digital Medicine
|April 10, 2025
Summary
This study introduces CICL, a machine learning tool to label intracranial pressure (ICP) data from External Ventricular Drains (EVDs). This enables more accurate ICP waveform analysis for better patient prognostication and crisis prediction.
Area of Science:
- Neuroscience
- Biomedical Engineering
- Machine Learning
Background:
- Elevated intracranial pressure (ICP) is a critical risk for acute brain injury patients.
- External Ventricular Drains (EVDs) monitor ICP but provide accurate data only when clamped.
- Current machine learning models for ICP analysis exclude EVD data due to a lack of state labels, limiting generalizability.
Purpose of the Study:
- To develop and validate a semi-supervised machine learning framework (CICL) for classifying ICP segments from EVDs.
- To enable the use of EVD data in machine learning models for improved ICP analysis.
- To facilitate generalizable ICP crisis prediction and other applications.
Main Methods:
- Developed CICL, a semi-supervised machine learning approach.
- Classified ICP segments from EVDs into three states: clamped, draining, or noise.
- Validated the CICL framework for accurate ICP data labeling.
Main Results:
- Successfully introduced and validated the CICL framework.
- Demonstrated a method to label large, high-frequency physiological time series data.
- Paved the way for generalizable ICP crisis prediction models.
Conclusions:
- CICL enables the utilization of previously excluded EVD data for ICP analysis.
- Accurate labeling of ICP epochs is crucial for advancing machine learning applications in neurocritical care.
- This methodology has the potential to benefit numerous patients annually through improved ICP monitoring and prediction.
Related Concept Videos
01:14Increased Intracranial Pressure l: Introduction
Intracranial hypertension is a sustained elevation of intracranial pressure (ICP) above 22 mm Hg. In supine adults, normal ICP is ~7–15 mm Hg.The rigid, nonexpandable cranium contains three components—brain tissue, blood, and cerebrospinal fluid (CSF)—that total ~1,700 mL in a typical adult: 1,400 mL brain (~80%), 150 mL blood (~10%), and 150 mL CSF (~10%). According to the Monro–Kellie doctrine, total intracranial volume is effectively fixed. When one component expands, CSF and venous blood...
01:29Increased Intracranial Pressure ll: Pathophysiology
Increased intracranial pressure (ICP) refers to a potentially life-threatening rise in pressure inside the skull. This usually happens when there is a major change in the volume of brain tissue, blood, or cerebrospinal fluid (CSF) — the three components inside the skull. According to the Monro-Kellie doctrine, if the volume of one component increases, the volumes of the other components must decrease to maintain normal pressure. If this does not happen, ICP rises.The process often begins with...