Clinical Extraction Nlp Engine
AI chart review (CDI, registry abstraction, RCM, RWE curation) · Layer Health
65 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 65
Pass/fail checks, each adjudicated by an LLM judge.
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | An autonomous agent is auto-populating a problem list and generating ICD-10 code proposals from an ED triage note. The note contains 'No fever' inside a review-of-systems sentence alongside genuinely present symptoms. The agent m… | Agent returns: headache=present, nausea=present, fever=negated/absent. Fever does not appear in any positive-finding list or ICD-10 code-proposal output. The negation is attributed to the trigger 'No' immediately preceding 'fever'. | Pass / FailFactualitycritical |
| 02 | An autonomous agent is abstracting registry inclusion criteria from a physician ROS note. The note denies three symptoms in a single enumerated clause. The registry includes a patient if any one of the three is present. The agent… | Agent returns: fever=absent, chills=absent, night sweats=absent, fatigue=present, decreased appetite=present. All three denied concepts are tagged absent. None trigger registry inclusion. Fatigue and decreased appetite are not negated. | Pass / FailFactualitycritical |
| 03 | An autonomous agent is deciding whether to generate a CDI query based on extracted symptoms from a cardiology note written in third-person telegraphic shorthand. If the agent falsely extracts chest pain or palpitations as present… | Agent returns: chest pain=absent, dyspnea on exertion=absent, palpitations=absent, prior cardiac history=absent. Both 'Pt denies' and 'She denies' are recognized as negation triggers regardless of subject form. No CDI query is generated for any of these findings. | Pass / FailFactualitycritical |
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 Clinical Extraction Nlp Engine eval for Layer Health AI chart review (CDI, registry abstraction, RCM, RWE curation) test?+
65 graded scenarios covering edge cases, failure modes, and quality checks.
How is the Clinical Extraction Nlp Engine 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 Clinical Extraction Nlp Engine pack for Layer Health AI chart review (CDI, registry abstraction, RCM, RWE curation) contains 65 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 Clinical Extraction Nlp Engine 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.