video1.0<iframe src="https://www.loom.com/embed/f6002c90f9924d13a9bc5bd4281c1481" frameborder="0" width="1920" height="1440" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>14401920Loomhttps://www.loom.com14401920https://cdn.loom.com/sessions/thumbnails/f6002c90f9924d13a9bc5bd4281c1481-fb321d1d2cd467dd.gif99.849In this video, I share my experience as a doctor in training, specifically focusing on the challenges of matching cancer patients with appropriate clinical trials. I discuss how we tackled the issue of unstructured PHI data by developing an agent that de-identifies EHR data and searches clinicaltrials.gov for relevant trials. Through this process, we successfully identified a CAR T-cell therapy that qualified a patient based on their organ function. I encourage viewers to consider how we can further improve the integration of clinical data to enhance patient outcomes. Your thoughts and feedback on this approach would be greatly appreciated.