Skip to content

Latest commit

 

History

12 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Prior Authorization Copilot

A RAG-based AI assistant that helps clinical and administrative staff draft prior authorization requests — grounded in payer policy, with mandatory citations and a human review gate.

Built as a Solutions Architect portfolio project demonstrating applied AI design for regulated healthcare environments.


The Problem

Prior authorization (PA) is one of the most costly administrative processes in U.S. healthcare. Staff spend 30–90 minutes per request manually comparing clinical notes against dense payer policy documents, then writing justification letters from scratch. Documentation gaps discovered at denial trigger expensive appeals cycles.

The CMS Interoperability and Prior Authorization Final Rule (CMS-0057-F), effective January 2026, adds regulatory urgency — health systems without modernized PA infrastructure face both operational burden and compliance exposure.

What This System Does

  1. Accepts a clinical note as input (MVP: lumbar spine MRI authorization)
  2. Retrieves the relevant medical necessity criteria from a payer policy index
  3. Generates a draft PA justification letter with citations to specific policy clauses
  4. Flags documentation gaps where the note doesn't yet meet required criteria
  5. Presents everything to a human reviewer — nothing is submitted without explicit approval

Why RAG (Not Fine-Tuning)

Payer policies update constantly. A fine-tuned model's knowledge is frozen at training time — every policy update requires a full retraining cycle. RAG lets us update the policy corpus by re-ingesting updated documents, with no model changes. It also provides an auditable retrieval chain: every output is traceable to a specific source chunk, which is a hard requirement for compliance in this domain.

Architecture Decisions

Five Architecture Decision Records (ADRs) document the major design choices:

ADR Decision
ADR-001 RAG over fine-tuning
ADR-002 Hybrid retrieval (BM25 + semantic) over pure vector search
ADR-003 pgvector over dedicated vector databases
ADR-004 Synthetic data only — no real PHI
ADR-005 Human-in-the-loop by design — no autonomous submission

Repository Structure

prior-auth-copilot/

├── architecture/diagrams/ # System and data flow diagrams

├── docs/

│ ├── adr/ # Architecture Decision Records

│ ├── business-case.md # Problem brief and ROI framing

│ └── path-to-production.md # What real deployment would require

├── data/

│ ├── synthetic/ # LLM-generated clinical notes (no PHI)

│ ├── policies/ # Public CMS LCD/NCD policy documents

│ └── README.md # Data sourcing documentation

├── src/

│ ├── ingestion/ # Document chunking and indexing pipeline

│ ├── retrieval/ # Hybrid BM25 + semantic retrieval

│ ├── generation/ # Grounded draft generation with citations

│ └── api/ # FastAPI backend

├── ui/ # React human review interface

└── evals/ # Retrieval and generation evaluation framework

Data and PHI

This project uses zero real patient data. All clinical notes are synthetically generated. Policy documents are public CMS publications (Local Coverage Determinations). See data/README.md for full sourcing documentation.

Build Status

  • Repository structure and architecture artifacts
  • Business case and ADRs
  • Synthetic data generation
  • CMS LCD L34220 policy document (cleaned, structured for RAG)
  • Ingestion pipeline (chunking + embedding + pgvector)
  • Hybrid retrieval layer
  • Generation layer with citations
  • FastAPI backend
  • React UI - the polished MVP
  • Evals + polish

About

RAG-based prior authorization assistant - solutions architecture + MVP for healthcare AI

Resources

Stars

1 star

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages