Unsupervised learning with GLRM feature selection reveals novel traumatic brain injury phenotypes

TL;DR

This study employs unsupervised clustering with GLRM-based feature selection to identify four new traumatic brain injury phenotypes, which are associated with different functional and cognitive outcomes at 90 days.

Contribution

It introduces a novel unsupervised approach using GLRM for feature selection to uncover previously unrecognized TBI phenotypes.

Findings

Four distinct TBI phenotypes identified

Phenotypes correlate with 90-day functional outcomes

GLRM-based feature selection improves clustering accuracy

Abstract

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.