A1 Refereed original research article in a scientific journal
Dynamic prediction of mortality after traumatic brain injury using a machine learning algorithm
Authors: Raj Rahul, Wennervirta Jenni M, Tjerkaski Jonathan, Luoto Teemu M, Posti Jussi P, Nelson David W, Takala Riikka, Bendel Stepani, Thelin Eric P, Luostarinen Teemu, Korja Miikka
Publisher: NATURE PORTFOLIO
Publication year: 2022
Journal: npj Digital Medicine
Journal name in source: NPJ DIGITAL MEDICINE
Journal acronym: NPJ DIGIT MED
Article number: 96
Volume: 5
Issue: 1
Number of pages: 8
ISSN: 2398-6352
DOI: https://doi.org/10.1038/s41746-022-00652-3
Web address : https://www.nature.com/articles/s41746-022-00652-3
Self-archived copy’s web address: https://research.utu.fi/converis/portal/detail/Publication/175999655
Intensive care for patients with traumatic brain injury (TBI) aims to optimize intracranial pressure (ICP) and cerebral perfusion pressure (CPP). The transformation of ICP and CPP time-series data into a dynamic prediction model could aid clinicians to make more data-driven treatment decisions. We retrained and externally validated a machine learning model to dynamically predict the risk of mortality in patients with TBI. Retraining was done in 686 patients with 62,000 h of data and validation was done in two international cohorts including 638 patients with 60,000 h of data. The area under the receiver operating characteristic curve increased with time to 0.79 and 0.73 and the precision recall curve increased with time to 0.57 and 0.64 in the Swedish and American validation cohorts, respectively. The rate of false positives decreased to <= 2.5%. The algorithm provides dynamic mortality predictions during intensive care that improved with increasing data and may have a role as a clinical decision support tool.
Downloadable publication This is an electronic reprint of the original article. |  |
