Overview

Accuracy, traceability, and safety via multi‑agent orchestration and evidence‑grounded generation.

Specialist Agents

Diagnostics (differentials + red flags), Pharmacology (DDIs, dosing), and Triage (urgency & disposition).

Reasoning Orchestrator

MCP planner routes tasks, fuses evidence, and enforces self‑consistency with safe refusal and uncertainty flags.

Agentic RAG

Graph & Node RAG over EMR/EHR + PubMed with section‑aware chunking, source allowlists, and citations.

Core Capabilities

Modeling & optimization to drive accurate, inspectable clinical reasoning.

LoRA/QLoRA

Parameter‑efficient adapters let us fine‑tune 7–13B models on modest GPUs while retaining high performance.

Knowledge Distillation

Teacher→Student compression to deliver fast, strong specialists with small runtime footprints.

GRPO Reasoning

Reinforcement learning variant targeting multi‑step, self‑consistent reasoning with lower compute costs.

QAC + Counterfactuals

Paraphrasing, chunking, and “what‑if” synthesis improve robustness across presentation styles.

Safety Rails

Allowlists, section filters, and citation‑required answers reduce hallucinations and protect privacy.

HPC Reproducibility

Deterministic seeds, LR scheduling, and checkpointing ensure auditability and consistent results.

Architecture

Click tabs to switch between layers.

        flowchart LR
          U(["Clinician UI / EMR"]) -->|"symptoms, meds, files"| MCP["MCP Orchestrator
FastAPI routing, planning, safety, tracing"]
          MCP --> DX["Diagnostics Agent"]
          MCP --> RX["Pharmacology Agent"]
          subgraph RAG["Agentic RAG"]
            QR["Query Router"] --> RET["Retriever"]
            RET --> SR["Safety Rails"]
          end
          DX --> RAG
          RX --> RAG
          SR --> KB[("Med KB / PubMed")]
          SR --> EMR[("EMR/EHR summaries")]
          DX --> FUSE["Evidence Fusion + Self-Consistency"]
          RX --> FUSE
          FUSE --> OUT{{"Final Report
summary, plan, citations, cautions"}}
          OUT --> QA["Evaluation & QA
MedMCQA, PubMedQA, similarity audits"]

Data, Training & Reproducibility

From 500k+ cases to specialized, efficient agents.

Datasets & Augmentation

  • 500k+ curated & synthetic clinical cases across specialties
  • QAC paraphrasing & chunking, self‑consistency sampling
  • Counterfactual case generation, back‑translation
Fine‑tuning Collection RAG Collection Ingestion Pipeline

Fine‑Tuning & KD

  • Teacher→Student Knowledge Distillation
  • LoRA/QLoRA adapters, GRPO for reasoning
  • HPC runs: deterministic seeds, LR schedules, checkpoints
KD Procedure Benchmarks Plan

Evaluation & Safety

Benchmarks, semantic audits, and runtime guards.

0
Cases Curated
0
Specialist Agents
0
Benchmarks

Benchmarks

MedMCQA (medical exam QA) and PubMedQA (research abstract QA). Complemented by semantic similarity audits with biomedical embeddings.

Runtime Guards

Uncertainty prompts, refusal policies for out‑of‑scope, citation‑required answers, and HIL oversight to ensure safety.

Team

Swinburne University of Technology COS30018
🎖️
Liam Team Leader
🧪
Henry LLM + RAG
🔗
Hai RAG + APIs
⚙️
Dylan Infra + Fullstack
🔧
Vinh Infra + Backend