Meeting Banner
Abstract #1064

Hypothesis-driven or regression-driven machine learning? What technique to choose? Insights from Professional Fighters Brain Health Study

Virendra R Mishra1, Xiaowei Zhuang1, Dietmar Cordes1, Aaron Ritter1, and Charles Bernick2
1Cleveland Clinic Lou Ruvo Center for Brain Health, Las Vegas, NV, United States, 2University of Washington - Seattle, Seattle, WA, United States

Whether routinely obtained T1-derived volumetric and cortical thickness measures can identify boxers with neuropsychological impairment using machine-learning (ML) techniques in active male boxers is currently unknown. We utilized conventionally acquired MPRAGE data from 72 impaired and 72 nonimpaired boxers, and identified regions that have significantly different cortical thickness, volumetric differences, and cortical thickness and brain volumes correlated with exposure to fighting and neuropsychological scores. Further, we investigated whether these regression-defined regions or prior hypothesis-defined brain regions can identify boxers with neuropsychological deficits. Hypothesis-driven regions with random forest algorithm outperformed other ML techniques with either regression of hypothesis-driven feature selection.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords