computing-ecqms

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

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).