• Mary Jo Pugh, Eamonn Kennedy, Eric M Prager, Jeffrey Humpherys, Kristen Dams-O'Connor, Dallas Hack, Mary Katherine McCafferty, Jessica Wolfe, Kristine Yaffe, Michael McCrea, Adam R Ferguson, Lee Lancashire, Jamshid Ghajar, and Angela Lumba-Brown.
• Informatics, Decision-Enhancement and Analytic Sciences Center, VA Salt Lake City, Salt Lake City, Utah, USA.
• J. Neurotrauma. 2021 Dec 1; 38 (23): 3222-3234.

AbstractIt is widely appreciated that the spectrum of traumatic brain injury (TBI), mild through severe, contains distinct clinical presentations, variably referred to as subtypes, phenotypes, and/or clinical profiles. As part of the Brain Trauma Blueprint TBI State of the Science, we review the current literature on TBI phenotyping with an emphasis on unsupervised methodological approaches, and describe five phenotypes that appear similar across reports. However, we also find the literature contains divergent analysis strategies, inclusion criteria, findings, and use of terms. Further, whereas some studies delineate phenotypes within a specific severity of TBI, others derive phenotypes across the full spectrum of severity. Together, these facts confound direct synthesis of the findings. To overcome this, we introduce PhenoBench, a freely available code repository for the standardization and evaluation of raw phenotyping data. With this review and toolset, we provide a pathway toward robust, data-driven phenotypes that can capture the heterogeneity of TBI, enabling reproducible insights and targeted care.

16 keywords...

hide…