Save
Three-dimensional time dependent icp-curve analyses as a new insight in waveform analysis based on an algorithm tagging the start point of any particular intracranial pressure-wave
Author(s): ,
G. Al Assali
Affiliations:
Community Hospital Herdecke, Neurosurgery, Herdecke, Germany
,
B. Petzold
Affiliations:
Community Hospital Herdecke, Neurosurgery, Herdecke, Germany
,
A.L. Tu
Affiliations:
Community Hospital Herdecke, Herdecke, Germany
,
A. Lichota
Affiliations:
Community Hospital Herdecke, Herdecke, Germany
,
F. Edelhäuser
Affiliations:
Community Hospital Herdecke, Herdecke, Germany
,
D. Cysarz
Affiliations:
Witten /Herdecke University, Herdecke, Germany
,
C.M. Friedrich
Affiliations:
Department of Computer Science, University of Applied Sciences and Arts Dortmund, Dortmund, Germany
,
M. Marsch
Affiliations:
Community Hospital Herdecke, Herdecke, Germany
,
W. Scharbrodt
Affiliations:
Witten/Herdecke University, Neurosurgery, Herdecke, Germany
C. Raak
Affiliations:
Institute of integrative Medicine
EANS Academy. Al Assali G. Oct 21, 2018; 225731; EP12004
Ghaith Al Assali
Ghaith Al Assali
Login now to access Regular content available to all registered users.

Access to Privileged content is currently a membership benefit.

Click here to join EANS or renew your membership.
Abstract
Discussion Forum (0)
Rate & Comment (0)
Objective:
The start point identification of any particular intracranial pressure (ICP)-wave is mandatory for an automatically computer based analysis of ICP-waveforms. For the first time we introduce an algorithm that enables an on-time-analysis and three-dimensional graphic account of the ICP-waves.

Methods:
We established a computered system that records ECG and ICP-data with 100Hz to depict ECG and ICP-curves in our intensive care unit. The data was generated from patients with subarachnoid hemorrhage and ICP-probe. As a first step the algorithm identified the r-peak of the ECG by wavelets (WL). As a second step spline fit of ICP-wave was calculated and the first ICP-peek after r-peak was assessed by WL. Lastly the minimum before the first peek was analogously detected by WL and set as a starting point. The starting point of every ICP wave was set to zero and each curve was illustrated on a three dimensional diagram, z-axis representing time course.
To measure the accuracy of the algorithm, both the algorithm and a neurosurgeon marked the start points of ICP-waves analyzing three different 5min recordings of ICP-curves.

Results:
In a first test-recording with a rhythmic ICP-curve the sensivity and specificity of the algorithm were 1,0. Using the ICP-curve of a Patient with arrhythmia absoluta sensivity and specificity were 0,9998.
In comparison the deviation of the neurosurgeon's marks were significantly higher than the algorithm's deviation (p< 0,001). This indicates that an algorithm-set marking is more precise than a person-set marking.

Conclusion:
This is the first introduction of an algorithm setting start points of ICP-waves with high sensivity and specificity. It leads to a three-dimensional time course of the ICP-waves. Thus long-term changes of ICP-curve morphology are visualized and visually based automated learning by artificial intelligence made possible. This will allow for a better understanding of morphological changes of ICP-wave form.
Code of conduct/disclaimer available in General Terms & Conditions
Anonymous User Privacy Preferences

Strictly Necessary Cookies (Always Active)

MULTILEARNING platforms and tools hereinafter referred as “MLG SOFTWARE” are provided to you as pure educational platforms/services requiring cookies to operate. In the case of the MLG SOFTWARE, cookies are essential for the Platform to function properly for the provision of education. If these cookies are disabled, a large subset of the functionality provided by the Platform will either be unavailable or cease to work as expected. The MLG SOFTWARE do not capture non-essential activities such as menu items and listings you click on or pages viewed.


Performance Cookies

Performance cookies are used to analyse how visitors use a website in order to provide a better user experience.



Google Analytics is used for user behavior tracking/reporting. Google Analytics works in parallel and independently from MLG’s features. Google Analytics relies on cookies and these cookies can be used by Google to track users across different platforms/services.


Save Settings