Neuroanesthesia & neurocritical care
Automated Measurement of Cerebral Hemorrhagic Contusions and Outcomes After Traumatic Brain Injury in the Transforming Research and Clinical Knowledge in TBI (TRACK-TBI) Study
Authors' conclusion
These findings suggest that CT-based automated contusion measurement may be an immediately translatable strategy for improving TBI prognostic models.
Study context
- Population
- Adults aged 17 years or older with moderate or severe traumatic brain injury (TBI) (GCS 3–12) and contusions on brain computed tomography (CT), TRACK-TBI study
- Participants
- 291 adults
- Comparison
- IMPACT score with vs without automated contusion volumes
- Outcome
- Glasgow Outcome Scale-Extended (GOSE) score of 4 or less
- Follow-up
- 6 months after injury
Methodological detailsmulticentre, 18 US level 1 trauma centres, automated AI contusion measurement (Brain Lesion Analysis and Segmentation Tool for Computed Tomography (BLAST-CT))
- Multicentre
- 18 US level 1 trauma centres
- Automated AI contusion measurement (BLAST-CT)
Performance
As reported in the abstract
Discrimination of unfavourable outcome (GOSE ≤4) · 6 months
IMPACT + temporal contusion volumes
0.86
AUC
IMPACT
0.84
AUC
P = 0.03
Further findings
Disability heat map of contusion locations (sparse canonical correlation analysis)
- Strongest association with unfavourable outcomes within the bilateral temporal and medial frontal lobes
Original publication
Automated Measurement of Cerebral Hemorrhagic Contusions and Outcomes After Traumatic Brain Injury in the TRACK-TBI Study. JAMA Netw Open. Published 1 August 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →