Skip to content
Skills Library
Medicine & health · Analysis

computing-ecqms

/computing-ecqms

Compute electronic clinical quality measures (eCQMs) over structured data using CQL/QDM logic, lifting note-derived numerator and exclusion facts from OpenMed to improve measure capture. Use when the user wants to compute an eCQM, evaluate a CMS/ECQI quality measure, improve numerator capture from clinical notes, build CQL/QDM measure logic, or close documentation gaps that structured codes miss. Covers eCQM structure (IPP/denominator/numerator/exclusions), CQL v1.5 and QDM v5.6, MADiE authoring, and mapping OpenMed entities to QDM data elements. Consumes OpenMed analyze_text facts (coded via

Repository
openmed ↗
Licence
Apache-2.0
Last repository change
27.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
5
Deprecation

No signals detected. Repository changed on 27.10.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What it does and when to use it

Compute electronic clinical quality measures (eCQMs) over structured data using CQL/QDM logic, lifting note-derived numerator and exclusion facts from OpenMed to improve measure capture. Use when the user wants to compute an eCQM, evaluate a CMS/ECQI quality measure, improve numerator capture from clinical notes, build CQL/QDM measure logic, or close documentation gaps that structured codes miss. Covers eCQM structure (IPP/denominator/numerator/exclusions), CQL v1.5 and QDM v5.6, MADiE authoring, and mapping OpenMed entities to QDM data elements. Consumes OpenMed analyze_text facts (coded via

Original author description

Compute electronic clinical quality measures (eCQMs) over structured data using CQL/QDM logic, lifting note-derived numerator and exclusion facts from OpenMed to improve measure capture. Use when the user wants to compute an eCQM, evaluate a CMS/ECQI quality measure, improve numerator capture from clinical notes, build CQL/QDM measure logic, or close documentation gaps that structured codes miss. Covers eCQM structure (IPP/denominator/numerator/exclusions), CQL v1.5 and QDM v5.6, MADiE authoring, and mapping OpenMed entities to QDM data elements. Consumes OpenMed analyze_text facts (coded via

How it works

  1. When to use this skill
  2. eCQM anatomy (what you're populating)
  3. Quick start
  4. Workflow
  5. Hand-off to / from OpenMed
  6. Edge cases & gotchas
  7. Standards & references
Original SKILL.md headings · 116 lines, 752 words
SKILL.md preview
---
name: computing-ecqms
description: "Compute electronic clinical quality measures (eCQMs) over structured data using CQL/QDM logic, lifting note-derived numerator and exclusion facts from OpenMed to improve measure capture. Use when the user wants to compute an eCQM, evaluate a CMS/ECQI quality measure, improve numerator capture from clinical notes, build CQL/QDM measure logic, or close documentation gaps that structured codes miss. Covers eCQM structure (IPP/denominator/numerator/exclusions), CQL v1.5 and QDM v5.6, MADiE authoring, and mapping OpenMed entities to QDM data elements. Consumes OpenMed analyze_text facts (coded via the linking skills) to supplement structured EHR data; does not replace certified measure engines."
license: Apache-2.0
metadata:
  project: OpenMed
  category: analytics-reporting
  pairs: after
  version: "1.0"
---

# Computing eCQMs

Electronic Clinical Quality Measures (eCQMs) are computed over structured data
using **CQL** (Clinical Quality Language) logic against the **QDM** (Quality
Data Model). Much of what a measure needs — a counseling note, a reason a
service wasn't done, a symptom — lives only in **free text**. This skill uses
OpenMed to lift those facts out of notes (on-device) and feed them into measure
computation so numerators and valid exclusions aren't undercounted.

## When to use this skill

When structured codes under-capture a measure population and the evidence is in
notes: documented exclusions ("patient declined screening"), numerator-relevant
findings, or symptoms gating a measure. Use it *alongside* a certified measure
engine — OpenMed supplements capture; it does not compute or certify the
measure.

## eCQM anatomy (what you're populating)

| Population | Meaning | Where OpenMed helps |
| --- | --- | --- |
| IPP (Initial Population) | everyone the measure could apply to | usually structured (encounters, age) |
| Denominator | IPP meeting base criteria | mostly structured |
| Denominator Exclusion / Exception | valid reasons to remove from denom | **notes**: "declined", "medical reason", "not indicated" |
| Numerator | met the quality action | **notes**: counseling delivered, advice given, status documented |

## Quick start

```python
import openmed

note = (
    "Tobacco use screened today; patient is a current every-day smoker. "
    "Cessation counseling provided and cessation medication offered."
)

result = openmed.analyze_text(note, output_format="dict")
# entities -> {text, label, confidence, start, end}

# Lift two measure-relevant facts (illustrative, for a tobacco-screening eCQM):
facts = {
    "tobacco_status_documented": any(e["label"] in {"smoking_status", "tobacco_use"}
                                     for e in result["entities"]),
    "cessation_intervention_documented": "counseling" in note.lower(),
}
# These become QDM data elements your CQL references (see workflow).
```

Pick the model whose labels match the measure concept (`choosing-openmed-models`)
and code spans to value-set vocabularies via the linking skills before they
enter QDM.

## Workflow

1. **Read the measure.** Get the human-readable spec + CQL + value sets from
   ECQI / MADiE. Identify which populations depend on documentation that
   structured data misses.
2. **De-identify.** Run `openmed.deidentify` on notes before any logging or
   storage; keep the measure keyed by internal patient ids.
3. **Extract facts.** `openmed.analyze_text` for the concepts the measure needs
   (status, intervention, reason-not-done). Use `resolving-clinical-context` to
   drop negated/hypothetical/family-history mentions — a *negated* exclusion is
   not an exclusion.
4. **Code to value sets.** Map entities to the codes the measure's value sets
   expect (SNOMED/LOINC/RxNorm via the linking skills). QDM data elements are
   defined by code membership, not raw strings.
5. **Materialize QDM data elements.** Turn coded, dated facts into QDM elements
   (e.g. `Assessment, Performed`, `Intervention, Performed`,
   `Diagnosis`) with the right author/relevant dates
   (`building-patient-timelines`).
6. **Compute with CQL.** Feed the structured + note-derived QDM into a
   **certified** CQL engine (e.g. the open-source `cqframework` engine). OpenMed
   does not execute CQL.
7. **Reconcile & audit.** Track which population members were added by
   note-derived facts and at what confidence, so QA can review.

## Hand-off to / from OpenMed

- **From OpenMed:** `analyze_text` entities + `clinical` temporality + the
  linking skills (to land facts in the measure's value sets) + `deidentify`
  upstream.
- **To measure tooling:** materialized QDM data elements feed a CQL engine and
  MADiE test decks. Note-derived QDM can also originate from `etl-to-omop-cdm`
  rows if you compute measures on an OMOP store instead.

## Edge cases & gotchas

- **OpenMed supplements, it does not certify.** Measure scoring must run in a
  validated CQL engine. Treat note-derived facts as additional evidence subject
  to review, not as authoritative measure results.
- **Negation flips meaning.** "Screening declined" is an *exclusion*; "screening
  not declined" / "no contraindication" is the opposite. Always run the
  temporality/negation pass before counting.
- **Dates drive measurement periods.** A fact only counts if its relevant date
  falls in the measurement period. Resolve dates first; undated facts can't be
  placed.
- **Value-set membership, not keywords.** A QDM data element is defined by codes
  in the measure's value set. Map entities to those codes — don't match on the
  surface word.
- **No restricted terminology bundling.** SNOMED/LOINC/RxNorm content stays
  out-of-process under your own license; OpenMed provides spans/labels only.
- **No raw PHI in logs or audit.** Record measure provenance by offset, label,
  confidence, and internal id.

## Standards & references

- ECQI Resource Center (eCQM specs, CMS measures): https://ecqi.healthit.gov/
- CQL (Clinical Quality Language) v1.5 spec: https://cql.hl7.org/
- QDM (Quality Data Model) v5.6: https://ecqi.healthit.gov/qdm
- MADiE (Measure Authoring Development Integrated Environment):
  https://madie.cms.gov/
- Open-source CQL engine (HL7 cqframework): https://github.com/cqframework/clinical_quality_language
- OpenMed source: `openmed/processing/` (`analyze_text`), `openmed.clinical`
  (temporality).

Versions

The database has no other skills named computing-ecqms.

Database snapshot: 13.11.2026 · package version cd8394c9abb4 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100quality-measures
    Pipeline skill for computing HEDIS quality measures from claims and clinical data. Use when the user asks to calculate HEDIS measure rates, check continuous enrollment, build denominator/numerator logic, detect care gaps, compute utilization rates, identify high-cost claimants,…
  • 90hedis-measure-specification
    Interpret Healthcare Effectiveness Data and Information Set (HEDIS) quality measure logic: denominator, numerator, exclusions, continuous enrollment, audit readiness, and Star Rating care gap prioritization. Use when asked to 'interpret a HEDIS measure', 'evaluate continuous…
  • 100health-informatics-specialist
    Use when a task needs the judgment of a Health Informatics Specialist — diagnosing why a clinical quality measure (eCQM/HEDIS) rate looks off, checking whether required data is captured as structured/coded fields versus free text, redesigning a clinical decision support (CDS)…
  • 100extracting-clinical-entities
    Run clinical and biomedical named-entity recognition on medical text with OpenMed's analyze_text. Use when the user wants to extract diseases, drugs, anatomy, genes, or other biomedical entities from notes; needs NER output as dict/json/html/csv; wants to filter by confidence,…
  • 100ask-openmed
    Choose the first OpenMed workflow skill for an intake, privacy, extraction, exchange, or verification request using deterministic local routing. Use when a goal is broad, spans several clinical-data stages, or leaves the data-sensitivity status unclear; the privacy gate is…
  • 100hedis-measure-specification
    Reasoning skill for HEDIS measure specification, enrollment logic, exclusion evaluation, NCQA audit requirements, and care gap prioritization. Use when the user asks about HEDIS measure definitions, denominator/numerator/exclusion logic, continuous enrollment rules, Star Rating…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.