Skip to content

Health plans, provider organizations and healthcare analytics teams

DeepGarden for healthcare

Ask market questions across maintained CMS data — and connect your membership, network and financial data when you are ready.

The data is published. That is not the same as usable.

CMS releases enrollment, penetration, Star Ratings, the annual plan landscape, the crosswalk between years and the benefit package files.

Columns move between releases. Counties are SSA-coded in one file and FIPS in another. Enrollment below eleven members is suppressed rather than zero, so naive sums are quietly wrong. Plans are renumbered between years, so growth is meaningless until the crosswalk is applied. Organizations appear under a marketing name, a contract name and a parent that may differ from both.

Where the answer is currently spread

  • CMS monthly enrollment by contract, plan and county
  • CMS Medicare eligibility and MA penetration
  • CMS Star Ratings, with cut points
  • CMS annual plan landscape and crosswalk
  • CMS plan benefit package files
  • Your membership, provider, network and financial systems

Who is involved

Market intelligence and strategy
Where enrollment is moving, who is taking it, and which counties are worth defending.
Product and benefits
What competitors filed for next year, and where the plan is an outlier.
Stars and quality
Which measures sit closest to a cut point, and what a half-star move is worth.
Finance and actuarial
Revenue exposure by contract, and whether a membership change is real or a renumbering artifact.

Questions this makes routine

These all cross a system boundary, which is why they currently get asked once a quarter rather than once a week.

  • Which Michigan counties moved most on MA enrollment last quarter, and who gained?
  • Where is Aetna taking MA share fastest in Ohio, and from whom?
  • Which Texas counties have the most eligibles but below-average penetration?
  • Which contracts are within half a star of losing 4.0?
  • Where are our Cook County premiums outliers for 2026?
  • Is growth in H1234-002 organic, or a renumbering artifact?

What an answer looks like here

A question, the clarification it needed, the answer, and the query behind every figure.

Health plan · market intelligence

AskWhere is Aetna gaining or losing MA market share fastest in Ohio, and to whom?

Clarifying question

Two readings are available. Which did you mean?

  • Share of Medicare Advantage enrolled, by countyselected
  • Share of all Medicare eligibles, by county

Across Ohio counties, Aetna's MA share moved most in Cuyahoga, where it fell over the six months to June 2026, from to .

Calculation

Share shift is the difference between the two period endpoints, computed on MA enrolled rather than on eligibles.

share_shift = (aetna_enrolled_end / ma_enrolled_end) − (aetna_enrolled_start / ma_enrolled_start)
  • Endpoints are June 2026 and December 2025 enrollment
  • Plans are crosswalked to 2026 contracts, so consolidations are not read as growth
  • Counties where CMS suppressed enrollment are excluded from the county total and flagged below

The share went predominantly to Anthem, which gained over the same period in Cuyahoga.

What this cannot tell you

Two Ohio counties — Vinton and Noble — are excluded: CMS suppressed Aetna enrollment there at or below ten members in at least one endpoint, so a share shift cannot be computed. They are listed in the evidence rather than counted as zero.

Query evidence

Dataset
CMS MA enrollment by contract, plan and county
Rows
10
Duration
412 ms
Executed
2026-07-14 09:22:07
Status
succeeded
Mode
read-only

View assembled from the result (pp)

  • Cuyahoga−2.4
  • Franklin−1.1
  • Hamilton−0.7
  • Summit−0.5
  • Montgomery+0.3
  • Lucas+0.5
  • Stark+0.8
Representative interface. The block structure, verified-value chips and evidence records mirror the product; the figures shown are illustrative rather than customer data.

What DeepGarden does about it

What changes, specifically, and what lands in front of the person who asked.

The public record, maintained

Collected, parsed, normalized to consistent identifiers, crosswalked across years and refreshed on CMS's own cadence. Suppression is preserved rather than coerced to zero, so a total is either right or explicitly incomplete.

Entities resolved before you join anything

Contract to plan to segment, plan to county across both SSA and FIPS, contract to organization to parent — so a question about a competitor returns everything they own, not everything under one marketing name.

Your data alongside it

Connect membership, provider, network or financial data through Roots and the same question crosses the boundary: your enrollment against market enrollment, your benefit design against the filed field.

An answer with the arithmetic shown

Market share arrives with its numerator, denominator and counties. A share shift arrives with both endpoints. The number is going into a filing, a board pack or a bid.

Why the output holds up

The parts of the governed path that matter most in this particular setting.

  • Every figure opens onto the executed query, the CMS file, the row count and the timestamp.
  • Suppressed cells stay suppressed, never zero, and any total affected says so.
  • Year-over-year comparisons are crosswalk-aware, so a consolidation is not reported as growth.
  • Access is scoped per person before the question is planned, which is what makes member-level and public data safe in one workspace.
  • DeepGarden reads and only reads.

How implementation would work

CMS data on day one; your own sources typically six to ten weeks

Bring a market question you cannot answer this week.

We will run it live against the maintained CMS data on the call. If the answer is wrong you will be able to see exactly where, because the query is right there.