Team Alpaca

Traumatic brain injury (TBI) is a leading cause of mortality and permanent neurological disability in the world, with over 50 million cases reported annually worldwide. Among TBI patients admitted to the Intensive Care Unit (ICU), 66% will die or suffer moderate-to-severe long-term neurological detriment within 6 months of discharge due to the lack of a reliable way to preempt patient decline. However, current models to predict a patient’s neurological recovery after TBI do not incorporate physiological time series data collected in the ICU. The aims of this project are two-fold: first, we would like to leverage features extracted from large, high-dimensional, and high-resolution data in a large, drivemulticenter ICU database to predict a patient’s neurological condition and survival at the end of their ICU stay. Second, we aim to determine to identify TBI disease subtypes and map them to specific recovery trajectories. These aims will be accomplished using both supervised and unsupervised machine learning algorithms.