An Analytics-Driven Risk Adjustment Solution to Mitigate Revenue Leakage
An AI-based and analytics-driven single risk adjustment solution for the US health plans market especially for Government administered programs like Medicare.
Health Plans that administer government programs such as Medicare and Medicaid typically face huge challenges around Revenue Leakage. One of the key triggers for revenue leakage is the area of Risk Adjustment. Some of the typical challenges faced by these health plans are:
Accuracy – Lack of a solution to Accurately calculate risk scores and risk adjusted payments
Gap Analytics – Difficulty to produce target interventions, care gap closure activities, and coordination with quality programs
Forecasting – Accurate reflection of member risk and utilization to derive revenue projections
Optimization – No single system to manage and track Risk adjustment gaps.
Build and position a product/solution for the Health Plan market (specifically Government program administering plans) that would be a single solution across Risk Adjustment markets with the below targeted outcomes.
While the focus of Ejyle’s solution was to resolve the issue of revenue leakage through risk adjustments and missed health conditions, the product was built such that apart from the core problem, areas such as population health and utilization optimization could also be targeted. The solution encompassed the below key elements.
Key benefits of our solution include:
- Improved Accuracy – Ability to accurately calculate the risk scores
- Enhanced Revenues – Reliable chase list that highlights the potential missed conditions within suspect members (complemented by potential revenue gaps) along with recommendations of providers and claims that can be involved in triage and chart reviews
- Better Forecasts – Conservative to aggressive forecasts of revenues for future year along with chase lists to achieve the forecasts
- Optimized Utilization – Ability to slice and dice utilization to identify potential optimization opportunities around utilization (Eg: Members for whom wellness can be focused upon to reduce emergency usage)
- Real gaps v/s Potential Gaps – Reconciliation of chart review data for re-calculation of revenues and RAF scores
- Predictive Models – Predictive models to identify
- Uncovered health conditions that could potentially occur in members
- Disease and Condition Correlations and Co-morbidities