From Adoption to Interoperability: How Policy Shape Medicaid Providers’ Progress in Modified Stage 2 Meaningful Use

• In Event: AI in Health Systems and Healthcare Innovation

Abstract

Introduction/Background:The Health Information Technology for Economic and Clinical Health (HITECH) Act accelerated nationwide adoption of electronic health records (EHRs) through the Centers for Medicare & Medicaid Services (CMS) Medicaid Promoting Interoperability Program. As policy priorities shifted toward interoperability and coordinated, data-driven care, Modified Stage 2 Meaningful Use (MS2 MU) was introduced to reduce reporting burden and support providers’ transition to advanced digital capabilities. Concurrently, external technical assistance structures, such as Regional Extension Centers, were phased out, reshaping the support environment for providers. Despite these policy changes, variation in progression persists, suggesting that the timing of engagement may be critical.

Purpose/Research Question:This study examines how provider characteristics and external resource environments influence Medicaid providers’ progression to Modified Stage 2 Meaningful Use, with a focus on the role of early program participation.

Data:We use longitudinal, quantitative data from the Medicaid EHR Incentive Program for providers in North Carolina and Florida from 2011 to 2021, including participation history, payment timing, and practice characteristics.Research Design and Methods:This retrospective cohort study evaluates achievement of MS2 MU between 2015 and 2018. We employ an XGBoost classification model optimized for F1 score, with SHapley Additive exPlanations (SHAP) to assess feature importance. Logistic regression is used as a benchmark model.

Results/Findings:The study includes 6,177 providers in North Carolina and 8,747 in Florida. MS2 MU achievement was higher in North Carolina (41.2%) than Florida (26.5%). Pediatricians had the highest success rates, while dentists had the lowest. Geographic patterns varied by state, and progression to Stage 3 Meaningful Use remained limited.Across models, participation in 2014 emerges as a pivotal inflection point in the policy trajectory. Providers who received Meaningful Use incentives in 2014 were substantially more likely to achieve MS2 MU, even after controlling for provider and practice characteristics. This pattern suggests that 2014 functioned as a de facto threshold year, where early and continuous engagement positioned providers to successfully transition into more complex program requirements, while those not engaged by this point faced compounding barriers to advancement. Additional predictors included program entry timing, provider specialty, and state context. The XGBoost model achieved 75% accuracy (AUC = 0.81), with consistent findings across logistic regression.

Conclusion/Implications:These findings suggest that policy timing—not just policy design—plays a decisive role in shaping outcomes. The concentration of effects around 2014 indicates that early participation created a path-dependent advantage, reinforcing providers’ capacity to progress as requirements evolved. Conversely, delayed entry may have limited providers’ ability to build the technical and organizational capabilities needed for interoperability.For policymakers, this underscores the importance of front-loaded support and sustained engagement during early implementation phases, particularly around key policy transitions. Strengthening Medicaid digital health initiatives will require targeted strategies for late adopters, continued technical assistance, and alignment with federal interoperability efforts. Without such interventions, early participation gaps may translate into persistent disparities in digital health adoption and outcomes.

Author

• Judith Monestime, Florida Atlantic University
  Presenting Author