{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/f6002c90f9924d13a9bc5bd4281c1481\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/f6002c90f9924d13a9bc5bd4281c1481-fb321d1d2cd467dd.gif","duration":99.849,"title":"Streamlining Cancer Treatment: Leveraging AI for Clinical Trial Matching","description":"In 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."}