Appeals & Denial Triage

Revenue Cycle

Denial classification with DOPS priority scoring and appealability ratings.

DenialsCARC/RARCDOPSAppeals

About

Triages claim denials at scale. Each denial's CARC/RARC codes are mapped to one of 12 denial categories, classified by an LLM with a plain-language explanation, scored with the formula-based DOPS priority score (factoring billed amount, appealability, and timeliness), and rated for appealability from high to none.

A batch endpoint classifies up to 100 denials per call and returns portfolio rollups — counts by category, by appealability, and the average DOPS score — for building denial-queue dashboards.

How it works

  1. 1CARC/RARC mapping to the 12-category taxonomy
  2. 2LLM classification + explanation
  3. 3DOPS priority scoring (deterministic formula, not LLM)
  4. 4Appealability rating + governance checks

Intended use

  • •Denial triage queues sorted by DOPS score
  • •Appeal-worthiness routing (work high-appealability denials first, write off "none")
  • •Denial-pattern analytics by payer and category via the batch endpoint

Key outputs

  • ▸triage_result — category, category_name, appealability (high|medium|low|none), dops_score, explanation
  • ▸batch summary — totals by_category, by_appealability, avg_dops_score
  • ▸/categories — the full 12-category taxonomy with typical CARC codes

Endpoints

Try each endpoint with your signed-in session — usage counts toward your monthly budget.

Use synthetic data only. Do not submit real patient records or PHI when testing endpoints.

Limitations & caveats

  • –Classification quality depends on input completeness — provide CARC/RARC, amounts, payer, and dates where available
  • –Batch requests cap at 100 denials per call
  • –Triage output prioritizes work; it does not draft the appeal letter itself