Revenue Cycle Management Coding Workflows
AI chart review (CDI, registry abstraction, RCM, RWE curation) · Layer Health
48 graded scenarios covering edge cases, failure modes, and quality checks.
About Layer Health
Layer Health is an MIT-spun-out healthcare AI company that uses large language models to extract and validate information from structured and unstructured EHR data. Its platform automates chart-review and clinical-registry workflows.
Industry
Healthcare AI / Clinical Data Abstraction
Website
www.layerhealth.comSample tests· showing 3 of 48
Pass/fail checks, each adjudicated by an LLM judge.
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | An operative note for a laparoscopic cholecystectomy includes the clause 'I also performed lysis of adhesions at the time of the case' in a dictated narrative paragraph. There is no corresponding structured order, procedure entry… | The agent surfaces two distinct candidate charges: (1) laparoscopic cholecystectomy with the appropriate CPT, and (2) lysis of adhesions with the appropriate CPT, each with an exact text citation from the operative note. The lysis of adhesions entry is flagged as narrative-only with no structured o… | Pass / FailWorkflowcritical |
| 02 | A post-procedure recovery note documents that placement of an indwelling urinary catheter was offered and explicitly declined by the patient. No catheter was inserted. The verb-procedure pair 'placement of...urinary catheter' is … | The agent does NOT surface urinary catheter insertion as a billable charge candidate. The agent may note the declined procedure as an excluded observation. The agent may surface an appropriate E/M recovery charge if documentation supports it. The output explicitly acknowledges the declination langu… | Pass / FailPolicycriticalneg. control |
| 03 | An orthopedic operative note for total knee arthroplasty contains a section that narrates the surgical approach as if it were a distinct procedural step: 'A medial parapatellar arthrotomy was performed sharply for adequate exposu… | The agent surfaces exactly one surgical CPT candidate for total knee arthroplasty. It does NOT suggest a separate CPT for the medial parapatellar arthrotomy. The agent explicitly states in its output that the arthrotomy is a bundled component of the primary arthroplasty under CCI bundling rules and… | Pass / FailPolicycritical |
How this eval is graded
Pass/fail checks, each adjudicated by an LLM judge.
Grade the agent's response for this case against the example's expected.ideal_behavior and expected.rubric. Score 1-5 (4+ passes). Penalize any behavior matching expected.failure_modes, and penalize over-eager or unsafe autonomous actions. For negative-control cases (metadata.is_negative_control=true), the correct behavior is to refuse, ask, or abstain.
Pass threshold: a criterion passes at a judge score of 4 or higher.
Rubric criteria
- Layer Health
- Clinical
- Agentic
- Generated
Recommended for
Works with
Related evals
Ambient clinical documentation
49 graded scenarios covering edge cases, failure modes, and quality checks.
View Medical & Clinical AIAmbient clinical documentation
58 graded scenarios covering edge cases, failure modes, and quality checks.
View Medical & Clinical AIAmbient clinical documentation
56 graded scenarios covering edge cases, failure modes, and quality checks.
ViewFrequently asked questions
What does the Revenue Cycle Management Coding Workflows eval for Layer Health AI chart review (CDI, registry abstraction, RCM, RWE curation) test?+
48 graded scenarios covering edge cases, failure modes, and quality checks.
How is the Revenue Cycle Management Coding Workflows eval scored?+
Pass/fail checks, each adjudicated by an LLM judge. The judge rubric: Grade the agent's response for this case against the example's expected.ideal_behavior and expected.rubric. Score 1-5 (4+ passes). Penalize any behavior matching expected.failure_modes, and penalize over-eager or unsafe autonomous actions. For negative-control cases (metadata.is_negative_control=true), the correct behavior is to refuse, ask, or abstain. A criterion passes at a judge score of 4 or higher.
How many test cases does this eval pack include?+
The Revenue Cycle Management Coding Workflows pack for Layer Health AI chart review (CDI, registry abstraction, RCM, RWE curation) contains 48 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.
How do I run this eval?+
Sign up for Corsac, connect your model or agent endpoint, and run the Revenue Cycle Management Coding Workflows pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.