Unsupervised learning with GLRM feature selection reveals novel traumatic brain injury phenotypes
This work addresses the need for better injury categorization in TBI research and treatment, though it appears incremental as it builds on existing unsupervised methods with a specific feature selection technique.
The authors tackled the problem of insufficient symptom-based categorization in traumatic brain injury (TBI) by applying unsupervised clustering with GLRM feature selection, revealing four novel TBI phenotypes that correlate to 90-day functional and cognitive status.
Baseline injury categorization is important to traumatic brain injury (TBI) research and treatment. Current categorization is dominated by symptom-based scores that insufficiently capture injury heterogeneity. In this work, we apply unsupervised clustering to identify novel TBI phenotypes. Our approach uses a generalized low-rank model (GLRM) model for feature selection in a procedure analogous to wrapper methods. The resulting clusters reveal four novel TBI phenotypes with distinct feature profiles and that correlate to 90-day functional and cognitive status.