About the scores
Every number on Atlas is derived from publicly available government data. No surveys, no self-reporting, no recruiter claims. Here's exactly how we calculate what you see.
Medicare Part B Provider Data, Centers for Medicare & Medicaid Services (CMS). This dataset captures physician-practice affiliations across annual snapshots. Atlas scores are calculated from 2019 onwards, using the complete longitudinal record of every physician who has appeared on a practice's Medicare roster. No proprietary, self-reported, or third-party data is used. Practices cannot edit, remove, or influence what appears in this data.
Atlas is not affiliated with, endorsed by, or sponsored by the Centers for Medicare & Medicaid Services or any other federal agency.
Every physician who joins a practice either stays or leaves. Staying is an endorsement. The longer they stay, the stronger it is. Leaving is a withdrawal of that endorsement, and the weight of that withdrawal depends on how long they stayed before deciding to go.
A physician who leaves in under two years saw something immediately disqualifying. A physician who leaves after five years likely hit a structural ceiling: partnership that never materialized, growth that stalled. Both matter. The Retention Score captures both, weighted by how invested each physician was when they left.
Each score is scaled 0–100. Higher reflects stronger physician retention.
Measures the weighted departure load of physicians who have left the practice. Unlike a simple short-exit count, every departure is weighted by how long the physician stayed, with shorter departures carrying significantly more penalty.
| Tenure at departure | Penalty | Signal |
|---|---|---|
| 0 – 2 years | Highest | Immediate red flag. Something disqualifying found quickly |
| 2 – 4 years | High | Classic churn. Dysfunction discovered within partnership track |
| 4 – 6 years | Moderate | Partnership or growth failure. A structural ceiling hit |
| 6 – 10 years | Low | Baseline signal. Ambiguous, many possible explanations |
| 10+ years | Minimal | Near-retirement territory. Lower signal weight |
Measures how long physicians currently at the practice have stayed. Calculated from the active roster only. Physicians who have already left no longer contribute to this metric.
Two pattern-level signals that apply a downward modifier when triggered.
Fires when a meaningful concentration of departures occurs within a defined rolling window. Signals a systemic event such as leadership change, acquisition, or cultural disruption. Applies a downward score adjustment.
Fires when multiple physicians departed after a similar amount of time. Signals a structural failure at a specific career stage. Applies a downward score adjustment.
Measures the collective seniority of the current roster. Derived from median years since medical school graduation. Displayed as context alongside the Retention Score but not included in the composite.
A weighted composite of Attrition Resistance and Tenure Strength, adjusted by cluster signals.
[(Attrition Resistance × primary weight)
+ (Tenure Strength × secondary weight)]
× Cluster Modifier (if applicable)
Specific component weights are proprietary.
Every metric is compared against a 2019 baseline. Delta scores show whether a practice has improved, deteriorated, or remained stable over time.
The Retention Score is not a measure of clinical quality, patient outcomes, compensation, or workplace culture. It answers one question: based on how physicians have historically moved through this practice, how well does it retain the people who join it?
Use Atlas as one input in your due diligence, alongside site visits, peer conversations, and contract review with an attorney.
Atlas scores are derived from CMS Medicare Part B data, which may occasionally contain inaccuracies. If you believe a score reflects a data error, contact us to flag the issue.
Email admin@matchmed.app with subject line Data Inquiry – [Practice Name].
All scores are derived from CMS Medicare Part B public datasets. MatchMed makes no representations regarding the completeness, accuracy, or timeliness of underlying CMS data.
Scores are statistical estimates, not factual declarations. They do not establish causation or assign blame for physician departures.
MatchMed, LLC is not liable for any employment, contracting, or other decisions made in reliance on Atlas scores. Use is subject to our Terms of Service and Privacy Policy.