Forecasting Claims and Population Care Patterns

Abstract

Predictive health claims systems currently lack robust prediction-based coding capabilities. As a result, claim coding transitions typically occur only after a set-basis prediction has already been made and treatment administered. This delay in prediction adjustments means that claim transition flows are poorly managed through predictive pathways, resulting in wasted resources and unnecessary costs. Compounding this issue, the shift from a pay-per-claim to a pay-per-capita reimbursement model requires establishing a clear data foundation for population-care management—one that, in turn, depends on understanding claim flow variations across different population segments.

This study models the coordination of health benefits to support both predictive claims systems and population-care management. The proposed Intelligent Health Benefits Coordination (IHBC) framework conceptualizes this coordination as a closed system shaped by environmental and market forces, and fed by data from the broader health-care ecosystem through well-defined channels. The IHBC framework formalizes a High-Level Conceptual Micro Model comprising seven core components, a map of their interconnections and relationships, three standardized types of data input, three key operational processes, and a simplified output structure. This model is grounded in predictions, data generation, and management requirements derived from existing theory and literature. A significant gap identified in the current literature—one directly relevant to the IHBC concept—concerns the implications of health-claims data for managing health-care costs within predictive claims systems.