Incorporating Immunoproteins in the Development of Classification Models of Progression of Intracranial Hemorrhage After Traumatic Brain Injury.
H E Hinson, Peter Li, Loren Myers and 3 others
PMID 33656476WHAT IT FOUND
Adding blood protein markers did not improve prediction of early hemorrhage progression after brain injury.
The tested models did not beat a no-information baseline.
Key findings
01The models with and without added protein marker groups did not outperform the no-information model.
02Protein marker groups were not associated with the original hemorrhage progression outcome, though one group was associated with the adjusted outcome.
03Patients with adjusted hemorrhage progression had lower admission Glasgow Coma Scale scores and more basal cistern compression, skull fracture, or axial hemorrhage.
STILL TO COME
How it was doneWhat they found
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
Only 106 patients were analysed, so the study was underpowered as a pilot. The analysis of hemorrhage progression was retrospective, even though the parent cohort was prospective. The study used two outcome definitions, and the adjusted definition reclassified 6 patients. The immune proteins were measured in batch later, not at the bedside, so the study does not show current clinical usability. Patients included both isolated traumatic brain injury and multiple injuries, which may make the biological signal harder to detect. The models used a simple linear approach, which may not be optimal for predicting hemorrhage progression.
Declared interests
The authors declared no conflicts of interest. The article is listed as N.I.H. extramural-supported.
The easy way to misread this
Do not conclude that immune protein markers are ready to guide acute decisions after brain injury. The models did not outperform a no-information baseline, and the study was a small retrospective pilot.