{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/52c90fd5fb3a45d19b424927d50e60b1\" frameborder=\"0\" width=\"1672\" height=\"1254\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1254,"width":1672,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1254,"thumbnail_width":1672,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/52c90fd5fb3a45d19b424927d50e60b1-5f07750a1075c7f0.gif","duration":64.5599,"title":"Building a Clinical Rules Engine with GPT-5 and Codex","description":"In this video, I share our development of a clinical rules engine designed to deliver the right clinical rules at the right time using GPT-5 and Codex. We structured the rules into an intermediate format and encoded them into Python modules for deployment. Additionally, we built a CDS services compliant API to ensure timely delivery of these rules at the point of prescribing. I encourage you to explore how this integration can enhance our clinical decision-making processes. Your feedback and insights on this initiative would be greatly appreciated."}