{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/14e85cc12fed4ae4b001382ee37fdb90\" frameborder=\"0\" width=\"1728\" height=\"1296\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1296,"width":1728,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1296,"thumbnail_width":1728,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/14e85cc12fed4ae4b001382ee37fdb90-83612d231865c8cf.gif","duration":280.024,"title":"Clinical Codes Finder, Plain English to ICD-10 and More 📌","description":"In this demo, I show a Clinical Codes Finder that removes the invisible bottleneck of scattered medical knowledge across ICD-10-CM, LOINC, and RxNorm. You describe what you need in plain English, and the AI decides which coding systems are relevant, searches in parallel, filters noise, and returns ranked codes ready to use. It even iterates when results are weak, like refining a tuberculosis treatment query after no initial RxNorm hits. Faster, more accurate coding means fewer rejected claims and better data quality. You can test the full project, architecture, and live demo in the links down below."}