Ask Your Data Like You Are Talking to a Colleague

"What's our 30-day readmission rate for diabetic patients?"

21.3% — 94 of 441 diabetic patient discharges readmitted within 30 days. CMS national average: 17.8%. Patient list available for care management follow-up.

Directly relevant to the HRRP (Hospital Readmissions Reduction Program) under ACA §3025. Excess readmissions can trigger CMS payment reductions of up to 3% on Medicare base payments.

"Show A1C trends for patients over 65 in the last 12 months"

Mean A1C across 318 qualifying patients fell from 8.4 (Jan) to 7.6 (Dec). 28% remain above 9.0. Month-by-month trend line shown with volume overlay.

Relevant to HEDIS measure HbA1c Control for Patients with Diabetes (CDC). A1C above 9.0 is the NCQA threshold for poor control.

"Which providers have the highest no-show rates this quarter?"

Dr. Okafor: 34% (89/261). Dr. Bergmann: 29% (71/245). Dr. Chaudhry: 26% (58/223). Practice mean: 19%. National primary care benchmark: 18–23%.

Each percentage point of no-show rate above 20% represents approximately $8,400 in lost revenue per full-time provider annually at average E&M reimbursement.

"What's our MIPS score as of today?"

Estimated composite MIPS score: 67.4 out of 100. Quality: 42.1/45. Promoting Interoperability: 12/25. Improvement Activities: 13.4/15. Cost: not yet calculated. Score as of last data upload Feb 14.

A MIPS score below 75 results in a payment penalty; above 85 qualifies for a positive adjustment. CY 2024 exceptional performance threshold is 89.

"Show denied claims by payer this quarter"

UnitedHealthcare: 14.2% denial rate ($218,400 denied). Aetna: 11.8% ($164,200). BCBS: 9.1% ($142,600). Medicare: 4.3% ($87,100). Medicaid: 16.1% ($93,400).

Medicaid's 16.1% denial rate is significantly above the 5–7% industry benchmark. Top denial codes shown: CO-4 (incomplete modifier), CO-97 (not separately payable).

"Which diagnosis codes have the longest average length of stay?"

DRG 291 (Heart Failure): 6.8 days vs. 4.7-day geometric mean (+2.1). DRG 871 (Septicemia): 8.2 days vs. 6.1-day geometric mean (+2.1). DRG 194 (COPD): 5.4 days vs. 3.8-day geometric mean (+1.6).

Length of stay above geometric mean affects CMI-adjusted reimbursement under MS-DRG. Excess days are not fully compensated, representing direct margin compression.

"How many patients are due for an Annual Wellness Visit this month?"

387 Medicare patients due for AWV (CPT G0438 or G0439) in February. 141 have had no AWV in 24+ months. 246 are due for their subsequent AWV. Estimated billable value: $67,200.

AWVs (G0438 initial, G0439 subsequent) reimburse at approximately $174 and $111 respectively under 2024 Medicare Fee Schedule. No cost-sharing to patient under ACA preventive care provisions.

"What percentage of our hypertensive patients have BP readings above 160 systolic?"

18.4% of hypertensive panel (214 of 1,163 patients) had most recent reading ≥160 systolic. 87 of these had no BP reading recorded in the past 6 months.

HEDIS CBP measure (Controlling High Blood Pressure) uses <140/90 as the target. JNC 8 guidelines recommend BP <150/90 for patients 60+ as the primary threshold for pharmacological intervention.

"Show CPT 99213 and 99214 billing distribution by provider for Q4"

Practice mean: 31% 99213, 54% 99214, 9% 99215. Dr. Williams: 12% 99213, 71% 99214 — statistically high 99214 rate may warrant documentation audit. Dr. Park: 61% 99213 — may be undercoding.

E&M coding distribution outliers (2+ SD from peer mean) can trigger MACs (Medicare Administrative Contractors) to initiate post-payment review. Internal audits at 12-month intervals are standard compliance practice.

"Which patients with COPD had an ED visit in the last 90 days?"

43 patients with ICD-10 J44.x who had an ED encounter in the past 90 days. 18 were subsequently admitted (COPD-related hospitalization rate: 41.9%). 11 had no follow-up visit within 7 days of discharge.

Post-discharge follow-up within 7 days for COPD patients is a HEDIS FUH measure component and a CMS quality reporting metric under the IPFQR program.

"What is our average days to close for patient complaints this year?"

Mean time to complaint resolution: 12.4 days YTD. Longest category: billing disputes (18.7 days). Shortest: scheduling (4.2 days). 7% of complaints exceeded 30 days — CMS QAPI standard requires 30-day closure.

CMS Conditions of Participation (42 CFR §482.13) require hospitals to have a grievance process. QAPI programs under §482.21 track complaint resolution time as a performance improvement indicator.

"Show revenue cycle KPIs: AR days, clean claim rate, and denial rate"

AR Days: 34.2 (target <35). Clean Claim Rate: 91.4% (industry benchmark 95%+). First-pass Denial Rate: 10.8% (target <5%). Net Collection Rate: 94.2%. Days in Accounts Receivable over 90 days: 18.3%.

A clean claim rate below 95% and denial rate above 5% are widely cited industry underperformance thresholds. Each additional AR day represents approximately $28,000 in working capital tied up for a 100-physician group practice.

HEDIS measure denominators

When you ask "what is our HEDIS CDC performance," Vizier applies NCQA-published denominator logic — patients 18–75 with two outpatient encounters or one inpatient stay carrying a diabetes diagnosis during the measurement year or year prior, continuous enrollment, applicable exclusions. The denominator is not the same as "rows with E11.x in the diagnosis column" — and getting it wrong inflates or deflates your rate against the national benchmark.

MIPS measure exclusions

MIPS Quality #001 (HbA1c Poor Control >9%) excludes patients in hospice, deceased during the measurement period, gestational diabetes (O24.4x), and steroid-induced diabetes (E09.x). MIPS #122 (Adult Kidney Disease) excludes patients on chronic dialysis. Vizier applies the CMS-published exclusion logic for each quality ID alongside the inclusion criteria — exclusions are not optional to compute, but they are commonly missed in homegrown SQL.

LACE+ readmission scoring

LACE+ combines Length of stay, Acuity (admission through the ED, yes/no), Charlson Comorbidity Index from prior diagnoses, and ED visits in the past 6 months. Vizier computes the score per discharge from existing claims and encounter data — no external scoring API, no chart abstraction. Any readmission-prevention query can surface patients above your LACE+ threshold (most programs use 60 or higher as the high-risk cohort).

ICD-10-CM hierarchy

Vizier expands code ranges (J44.x → J44.0, J44.1, J44.9 for COPD subcategories), rolls up to chapter level on request (Chapter J = all respiratory diseases, J00–J99), distinguishes acute from chronic (I21 acute MI vs. I25 chronic ischemic heart disease), and respects the laterality and severity suffix structure introduced with ICD-10. "Diabetic complications" expands to E08–E13 with .2x–.9x suffix patterns.

RxNorm drug normalization

A query for "metformin" matches RxNorm ingredient code 6809 — covering all dosages (500mg, 850mg, 1000mg, 750mg ER), brand names (Glucophage, Glumetza, Fortamet, Riomet), and combination products that contain metformin (Janumet, Glucovance, Metaglip, Synjardy). The reverse is also true: a query against a specific brand resolves to its RxNorm components so that medication-adherence and polypharmacy analyses are not fragmented by spelling and product variants.

LOINC laboratory codes

A1C results map to LOINC 4548-4 (Hemoglobin A1c/Hemoglobin.total in Blood) and LOINC 17856-6 (IFCC method). LDL cholesterol resolves to 13457-7 (calculated) or 18262-6 (direct measurement). Vizier reconciles encoded lab results across these representations and also matches the loosely-coded labs that some EHRs send as description text without a LOINC code attached — common when results arrive via interface engines from outside reference labs.

SNOMED CT clinical concepts

A query for "diabetic patients" against FHIR or international EHR data matches SNOMED 73211009 (Diabetes mellitus) and all descendant concepts via the SNOMED IS-A hierarchy — 44054006 (Type 2), 46635009 (Type 1), 11530004 (Brittle diabetes). Important for non-US deployments and Epic / Cerner FHIR exports that use SNOMED problem-list coding rather than ICD-10. Vizier maintains the SNOMED-to-ICD-10 crosswalk so queries written either way return identical cohorts.

CPT modifiers

CPT modifiers change billing meaning. Modifier 25 (significant separately identifiable E&M on the same day as a procedure) means a 99214-25 should not be counted as a routine 99214. Modifier 59 (distinct procedural service) affects bundling and NCCI edits. Modifier 91 (repeat clinical diagnostic lab) and 76 (repeat procedure by same physician) drive duplicate-claim denial patterns. Vizier separates billings by modifier when computing provider distributions or denial analyses.