{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/98f3cff7b01b4b7eb4bd4ddcc0f77644\" frameborder=\"0\" width=\"1152\" height=\"864\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":864,"width":1152,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":864,"thumbnail_width":1152,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/98f3cff7b01b4b7eb4bd4ddcc0f77644-a64e1a20e4f514a3.gif","duration":300.1,"title":"AI Gene Analysis for Tetralogy of Fallot","description":"This Loom explains Connor Hsu’s Statera health profile AI that analyzes uploaded DNA for genetic and health insights. He starts with his lifelong cardiology focus from being born with Tetralogy of Fallot and his research using Python and R to link gene networks to non-syndromic cases. In the demo, he uploads an Ancestry DNA file locally, then the model highlights gene regions tied to traits like lactose intolerance and type 2 diabetes, and especially region 9p21 for cardiac health and embryogenesis. He notes the AI runs locally using an LLM architecture trained off models from Ollama and that he recently won an AMD AI Pro 9700 Sapphire GPU to enable more powerful models."}