This Project Grant award from the National Institute of Neurological Disorders and Stroke (NINDS) under the Extramural Research Programs in the Neurosciences and Neurological Disorders (CFDA 93.853) aims to develop and test a Fused Imaging and Large Language Foundational Model (FILLM) to enhance the prediction of 90-day outcomes for acute ischemic stroke patients, including those undergoing endovascular therapy. The $124,485 award to The Leland Stanford Junior University will leverage advancements in deep learning and large language models to integrate unstructured clinical notes, imaging data, and structured clinical information. The key objectives are to develop and assess the FILLM model's performance, evaluate its generalizability and bias reduction capabilities, and enable optimal collaboration between the model and clinicians. This project seeks to advance the ability to triage endovascular therapy patients using data-driven approaches and promote more personalized stroke care.