Umeå University's logo

umu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • apa-6th-edition.csl
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Probabilistic prediction of increased intracranial pressure in patients with severe traumatic brain injury
Umeå University, Faculty of Social Sciences, Umeå School of Business and Economics (USBE), Statistics. Umeå University, Faculty of Medicine, Department of Radiation Sciences, Radiation Physics.ORCID iD: 0000-0003-1654-9148
Umeå University, Faculty of Medicine, Department of Clinical Sciences, Neurosciences.ORCID iD: 0000-0003-3528-8502
Umeå University, Faculty of Medicine, Department of Radiation Sciences, Radiation Physics.ORCID iD: 0000-0002-3486-5251
2022 (English)In: Scientific Reports, E-ISSN 2045-2322, Vol. 12, no 1, article id 9600Article in journal (Refereed) Published
Abstract [en]

Traumatic brain injury (TBI) causes alteration in brain functions. Generally, at intensive care units (ICU), intracranial pressure (ICP) is monitored and treated to avoid increases in ICP with associated poor clinical outcome. The aim was to develop a model which could predict future ICP levels of individual patients in the ICU, to warn treating clinicians before secondary injuries occur. A simple and explainable, probabilistic Markov model was developed for the prediction task ICP ≥ 20 mmHg. Predictions were made for 10-min intervals during 60 min, based on preceding hour of ICP. A prediction enhancement method was developed to compensate for data imbalance. The model was evaluated on 29 patients with severe TBI. With random data selection from all patients (80/20% training/testing) the specificity of the model was high (0.94–0.95) and the sensitivity good to high (0.73–0.87). Performance was similar (0.90–0.95 and 0.73–0.89 respectively) when the leave-oneout cross-validation was applied. The new model could predict increased levels of ICP in a reliable manner and the enhancement method further improved the predictions. Further advantages are the straightforward expandability of the model, enabling inclusion of other time series data and/or static parameters. Next step is evaluation on more patients and inclusion of parameters other than ICP.

Place, publisher, year, edition, pages
Nature Publishing Group, 2022. Vol. 12, no 1, article id 9600
National Category
Probability Theory and Statistics Infectious Medicine
Research subject
Statistics; Biomedical Radiation Science
Identifiers
URN: urn:nbn:se:umu:diva-199774DOI: 10.1038/s41598-022-13732-xISI: 000809441100084PubMedID: 35688885Scopus ID: 2-s2.0-85131791681OAI: oai:DiVA.org:umu-199774DiVA, id: diva2:1699584
Funder
Region VästerbottenAvailable from: 2022-09-28 Created: 2022-09-28 Last updated: 2022-09-28Bibliographically approved

Open Access in DiVA

fulltext(1231 kB)120 downloads
File information
File name FULLTEXT01.pdfFile size 1231 kBChecksum SHA-512
d1b77d0018308b7f499603d287fd68fecd6aedfb57b4b69f0078c6b563277c391bb9a45771d0a105bf492b91d628e49a354049019f28be1fb6b48e707af3a4de
Type fulltextMimetype application/pdf

Other links

Publisher's full textPubMedScopus

Authority records

Wijayatunga, PriyanthaKoskinen, Lars-Owe D.Sundström, Nina

Search in DiVA

By author/editor
Wijayatunga, PriyanthaKoskinen, Lars-Owe D.Sundström, Nina
By organisation
StatisticsRadiation PhysicsNeurosciences
In the same journal
Scientific Reports
Probability Theory and StatisticsInfectious Medicine

Search outside of DiVA

GoogleGoogle Scholar
Total: 120 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 291 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • apa-6th-edition.csl
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf