A research multi-year project started in March 2018, involving the Department of Energy’s (DOE) Lawrence Livermore (LLNL) https://www.llnl.gov, Lawrence Berkeley (LBNL) https://www.lbnl.gov, and Argonne (ANL) https://www.anl.gov, which are all DOE national laboratories, are going to use DOE’s supercomputing resources, artificial intelligence capabilities, and a precision medicine approach to study TBIs.
At the same time, this project will collaborate with the “Transforming Research and Clinical Knowledge in Traumatic Brain Injury” (TRACKI-TBI) consortium to be led by the University of California, San Francisco (UCSF) along with other universities in the U.S.
According to researchers, it necessary to apply machine learning to TRACK-TBI in order to find a more quantitative way to assess TBI than is currently available because of the complexity of the brain and the need to deal with the tremendous amount of data.
Researchers are using de-identified data obtained from 3,000 TBI patients, data gathered from the consortium led by UCSF, along with data available from the team of researchers at LLNL, LBNL, and ANL. The researchers will first attempt to create a streamlined system in order to share massive amounts of research data among the labs.
Then LLNL will collaborate with LBNL and ANL on developing new data-driven analytic tools and a more efficient encrypted data pipeline that will aim to keep any potential identifying medical information secure in adherence to HIPAA restrictions.
The next step is for the DOE national labs to use the data to develop a predictive model that can be used to categorize or triage patients into risk categories which at that point, can be used to assess potential outcomes.
Researchers also report that this project will serve as a proof of concept for a machine learning model and if successful, could provide information on future models of diseases or disorders other than TBI.
Go to https://tracktbi.ucsf.edu/transforming-research-and-clinical-knowledge-tbi for more information on TRACK-TBI.