KEMAL KOÇ@microbiology

MediAgent is an AI-powered clinical decision support system built for physicians. Doctors face hundreds of diagnostic decisions every day under pressure, with incomplete information, and often without support. Existing tools either send patient data to third-party cloud servers, require million-dollar enterprise implementations, or offer no transparency into how their conclusions were reached. MediAgent was built to solve all three problems at once. The system analyzes patient symptoms, vital signs, laboratory results, and radiology notes to produce a prioritized differential diagnosis list. Each diagnosis comes with an ICD-10 code, a confidence score, a clinical rationale, and a full six-step reasoning chain showing exactly how the AI reached its conclusion. Physicians see not just the answer they see the thinking behind it. Everything runs locally. Patient data never leaves the infrastructure not by policy, but by architecture. This makes MediAgent viable for small clinics, rural hospitals, and healthcare systems in emerging markets where data sovereignty is non-negotiable. The system also includes full patient profile management, analysis history, urgency triage, recommended tests, and PDF report generation. The global clinical decision support market stands at $2.43 billion today, growing at 9.6% annually. On-premise deployment already accounts for 41.9% of the market — and 80% of hospitals worldwide still have no production AI in place. MediAgent targets exactly this gap. Under the hood: MedGemma 27B running on AMD MI300X GPU via vLLM and ROCm, FastAPI backend, React frontend, SQLite — all in a single Docker container. Open source, MIT licensed. Built by Axiom Core. Your Clinical Copilot.

To participate in the hackathon, simply click Sign up with AMD. If you are not already a member of the AMD AI Developer Program (ADP), you will need to create an account. ADP members can access AI tutorials, experts, and community support. In addition, new members can claim a free month of DeepLearning.ai pro, $100 in AMD GPU cloud credits, and $50 in Fireworks AI API credits. All hackathon participants will receive on hackathon launch additional compute and API credits for their projects. Ready to build what's next on AMD? Sign up with AMD below to secure your spot.