Accelerating the adoption of bundled payment reimbursement systems: A data-driven approach utilizing claims data

Abstract

ABSTRACTBundled payments as a reimbursement mechanism have the potential to reduce health care expenditures and improve the quality of care by aligning the incentives of payers, providers and, most importantly, patients. The Centers for Medicare and Medicaid Services (CMS) launched the Bundled Payments for Care Improvement (BPCI) program in April 2013 and has set ambitious goals for adopting alternative payment models on a large scale. One of the crucial components for successful implementation of a bundled payment system is the identification of procedural homogeneous groups within an episode of care (a set of services needed to treat a medical condition), to which a flat reimbursement rate can be applied. In this study, we propose a data-driven clustering approach to automatically detect and explicitly represent homogeneous sub-groups of services for a given condition. Manual detection is slow and relies on consensus decisions, but automatic detection can serve as an important foundational input for bundle building. We explore the results from analyzing two conditions, one with a low and the other with a high degree of treatment complexity. Resulting clusters characterize episodes of care by specifying included services. The automatically extracted clusters of services have different cost patterns and highlight the payer's expenditure and provider's financial risk under bundled payments. Such a data-driven approach could be used by payers (e.g., CMS) to facilitate the adoption of bundled payments by different providers. To demonstrate, we use the clusters identified to model a payment scheme that minimizes providers’ financial risk.