Risk Adjustment Data Marts

Note that Zus Risk Adjustment features are currently in public preview and are subject to change.

Risk adjustment analytics are exposed via flattened, query-friendly tables derived from the underlying FHIR MeasureReport resources.

Risk Gap Views

risk_gap

A denormalized view of one row per risk gap (MeasureReport).

Common fieldNotes
idRisk gap identifier.
patient_id, upidPatient identifiers.
code_hcc, hcc_versionHCC code and model version.
gap_typeRecapture, suspect, or net-new.
gap_statusCurrent/latest status.
confidence_level1–5 (5 = highest confidence).
period_startStart date for the calendar-year period.
created_at, last_updated_atCreation and last update timestamps.
Typical use caseDescription
Population listingList all current-year gaps for a population.
SegmentationSegment by gap type/status.
TrendsTrend monitoring by period.

risk_gap_status_update

One row per status update event per risk gap (full history).

Common fieldNotes
risk_gap_idLink to risk_gap.id.
created_at, created_byWhen and by whom the status was created.
statusStatus code for this update.
note (optional)Free-text note.
substatus_one, substatus_two, substatus_three (optional)Additional categorization fields.
Typical use caseDescription
Audit trailAudit trail of review workflows.
Operational metricsMeasuring time-to-close or time-to-review.
Status evolutionUnderstanding how gaps evolve (e.g., open → expected-to-close → closed).

risk_gap_hierarchy

Represents superseding relationships between gaps based on HCC hierarchy.

Common fieldNotes
risk_gap_idThe superseded gap.
superseded_by_risk_gap_idThe superseding gap.
Typical use caseDescription
Top-level filteringFilter to top-level gaps only.
Accurate countsAvoid double-counting related HCCs in reporting.

risk_gap_source

Identifies which upstream sources contributed to each risk gap.

Common fieldNotes
risk_gap_idLink to risk_gap.id.
sourceContributing source (e.g., rules-based, AI, payer, user).
last_updatedWhen the risk gap was last updated.
Typical use caseDescription
Attribution"Which systems are producing gaps?"
QAQA and monitoring by source.

risk_gap_diagnosis_code

Normalized mapping of ICD-10 codes to risk gaps (one row per ICD-10 per gap).

Common fieldNotes
risk_gap_idLink to risk_gap.id.
code_icd_10ICD-10 diagnosis code.
Typical use caseDescription
DrilldownDrilldown from HCC gap → supporting ICD-10s.
ComparisonsCompare coding patterns across providers.

risk_gap_evidence

Normalized mapping from risk gaps to evidence resources.

Common fieldNotes
risk_gap_idLink to risk_gap.id.
resource_type, resource_idThe referenced FHIR resource.
typeevaluated or related.
last_updatedWhen the risk gap was last updated.
last_encounter_diagnosis_recorded_date (when applicable)Most recent encounter diagnosis timestamp for the evaluated resource.
Typical use caseDescription
Reviewer experiencesBuild reviewer experiences (evidence panels).
AnalyticsAnalytics on evidence completeness/recency.

Linking back to FHIR

You can often construct a direct FHIR reference using:

.../fhir/{resource_type}/{resource_id}

(Your exact base URL will depend on your deployment/environment.)


RAF Score Views

raf_score_v28 and raf_score_v24

One row per patient, builder, and calendar year with aggregated RAF metrics based on v28 and v24 CMS HCC models. These are estimates and not always the same scores that are in our raf_score table, which contains RAF Score MeasureReports data.

Common fieldNotes
upidUniversal patient identifier.
patient_idPatient identifier.
potential_rafRAF score if all non-dismissed gaps were paid.
potential_hcc_countCount of HCCs contributing to potential score.
current_rafRAF score for closed gaps only.
current_hcc_countCount of HCCs contributing to the current socore
raf_gapDifference: potential_raf − actual_raf.
hcc_gapDifference: potential_hcc_count − actual_hcc_count.
Typical use caseDescription
Population overviewAggregate RAF opportunity across a patient panel.
Gap prioritizationIdentify patients with largest raf_gap.
Trend trackingMonitor score changes over time.

raf_score

Table for analyzing RAF Score MeasureReport FHIR resources.

Common fieldNotes
idID of the RAF Score MeasureReport Resource.
upidUniversal patient identifier.
patient_idPatient identifier.
period_startStart date for the calendar-year period.
actual_raf_scoreCurrent RAF score of closed gaps.
expected_raf_scoreRAF score for expected-to-close and closed gaps.
potential_raf_scoreRAF score if all non-dismissed gaps were paid.
measureThe MeasureReport.measure value.
last_updatedWhen the MeasureReport resource was last updated.
created_atWhen the MeasureReport resource was created.
raf_score_modelThe model applied to RAF scoring.
Typical use caseDescription
Risk Gap Measure Report attributionLink RAF scores to specific data in the risk_gap data.
Trend ChangesIdentify how risk gap RAF score changed over time.

Payer Risk Gap Views

payer_risk_gap

Table for analyzing Payer Risk Gap MeasureReport FHIR resources.

Common fieldNotes
idID of the Risk Gap MeasureReport Resource.
upidUniversal patient identifier.
patient_idPatient identifier.
period_startStart date for the calendar-year period.
code_hcc_versionHCC CMS version (e.g. 'V28').
code_hccHCC code of the Risk Gap.
code_icd_10ICD-10-CM code of the Risk Gap.
last_claim_dateThe last date reported by the Payer Risk Gap file.
last_updatedWhen the MeasureReport resource was last updated.
created_atWhen the MeasureReport resource was created.
measureThe MeasureReport.measure value. (e.g. http://zusapi.com/quality/measure/risk/CMSv28 )
gap_sourceWhere the MeasureReport was created (e.g. payer-risk-gap-csv-file).
payer_reported_recapture_flagThe recapture / not recaptured status according to the payer.
payer_reported_statusThe status (open / closed) according to the payer file.
reasonThe reason the payer gave for the current reported status and recapture status.
Typical use caseDescription
Risk Gap Source TrackingIdentify payer gap data provided to create certain risk_gap entries.
Import trackingSuccessfully imported Payer Risk Gap CSVs create Payer Risk Gaps which ultimately reach the payer_risk_gap data mart. This allows you to check if a CSV completed successfully.