Primary Care Performance Analytics

Primary Care Chain Performance Analysis Case Study

FastHSR used Medicare claims and Medicare Advantage encounter data to evaluate the performance of a large primary care group in value-based care.

Home / Medicare & Medicaid Claims Data Analytics / Primary Care Chain Performance Analysis Case Study

Client question

A client wanted to understand the performance of a large primary care group in a target market. The question was whether the group was operating at the level expected of a well-managed value-based care organization and where improvement opportunities were concentrated.

FastHSR combined Traditional Medicare claims, Medicare Advantage encounter data, ACO comparison data, peer benchmarks, and statistical modeling to evaluate the group's cost, utilization, quality, risk, and care coordination patterns.

Executive summary approach

FastHSR structured the analysis to separate overall performance from the specific drivers behind that performance. The executive summary synthesized longitudinal trends, peer comparisons, service-line decomposition, Traditional Medicare claims findings, and Medicare Advantage encounter data findings.

Rather than relying on a single total-cost metric, the approach identified where performance variation came from: acute-care use, emergency use, physician services, Part B drugs, post-acute care, preventive-care completion, risk capture, and other high-cost service categories.

Longitudinal performance analysis

FastHSR evaluated the group's longitudinal performance from 2020 through 2024. The analysis tracked spending, utilization, risk, and care-management indicators over time to determine whether performance was improving, deteriorating, or diverging from peer patterns.

  • Per capita spending trends.
  • Utilization trends across hospital, emergency, physician-service, and post-acute categories.
  • Annual Wellness Visit completion trends.
  • Risk score and risk capture patterns.
  • Service-line categories driving cost changes.

Comparison with other ACOs in the state

FastHSR compared the group with 29 other ACOs with at least 1% market share in the state. The analysis used linear mixed-effects models for outcomes such as per capita spending and utilization across 2020-2024.

The model accounted for differences across ACOs and over time to evaluate whether the group's spending or utilization patterns changed differently from other major ACOs in the state.

Comparison with peer ACOs in the market

FastHSR also compared the group with two local peer ACOs in the market. This helped separate broad statewide dynamics from market-specific peer performance and gave the client a more relevant benchmark for operational improvement.

Traditional Medicare claims analysis

Traditional Medicare claims supported detailed service-line and utilization analyses. FastHSR examined where patients received hospital care, how hospitalization and emergency visit rates varied by risk score, and which Part B physician-service categories contributed to total cost variation.

  • Hospitalization and emergency visit rates by risk score.
  • Hospital destinations for the group's patients.
  • Part B physician-service cost drivers.
  • Elective surgery use and other procedure categories.
  • High-cost Part B service categories, including drug and skin-substitute spending where relevant.
  • Low Annual Wellness Visit completion rates and implications for care coordination.
  • Comparison with local ACO REACH peers.

Medicare Advantage encounter data analysis

FastHSR used Medicare Advantage encounter data to extend the evaluation beyond Traditional Medicare. The MA analysis compared the group with another peer in Medicare Advantage, examined SNP composition in the group's MA population, and compared the group's MA population with statewide and local MA populations.

  • Comparison of the group and a peer in Medicare Advantage.
  • SNP composition of the group's MA population.
  • Comparison with statewide MA populations.
  • Comparison with local MA populations.

Performance improvement framework

The claims and encounter data analysis was designed to translate findings into a practical improvement framework. Depending on the observed pattern, priorities could include reducing avoidable hospital use, improving risk capture accuracy, increasing Annual Wellness Visit completion, strengthening care coordination, and monitoring high-cost service categories.

  • Reduce avoidable hospital use through better care management and earlier intervention.
  • Improve risk capture accuracy so patient severity is measured appropriately.
  • Raise Annual Wellness Visit completion rates to support care planning and documentation.
  • Strengthen care coordination for high-risk patients and post-discharge transitions.
  • Monitor high-cost Part B services, procedures, drugs, and post-acute care categories.

Deliverables

  • Executive summary of primary care group performance and improvement priorities.
  • Longitudinal performance analysis from 2020-2024.
  • Statewide ACO comparison using mixed-effects models.
  • Local peer ACO comparison.
  • Traditional Medicare claims analysis of hospitalizations, emergency visits, Part B services, AWVs, and high-cost procedures.
  • Medicare Advantage encounter data analysis of MA population and peer performance.

Frequently asked questions

How can Medicare claims evaluate primary care chain performance?

Medicare claims can measure longitudinal spending, hospitalizations, emergency visits, Part B physician services, Part B drug spending, Annual Wellness Visits, procedure use, post-acute care, and comparisons with ACO peers.

Why include Medicare Advantage encounter data?

Medicare Advantage encounter data expands the analysis beyond Traditional Medicare and helps compare MA populations, SNP composition, utilization patterns, and performance against local or statewide MA benchmarks.

What can this performance analysis identify?

The analysis can identify which service categories, utilization patterns, risk-capture issues, quality gaps, and care-management opportunities are contributing to performance variation.

What improvement priorities can claims analytics identify?

Claims analytics can identify priorities such as reducing avoidable hospital use, improving risk capture accuracy, increasing Annual Wellness Visit completion, strengthening care coordination, and monitoring high-cost service categories.

For primary care performance analysis, Medicare claims ACO benchmarking, Medicare Advantage encounter analysis, or value-based care performance evaluation, please email us.

See more case studies