With the Centers for Medicare and Medicaid Services (CMS) leading the way, government and commercial payers alike leverage hierarchical condition categories (HCCs) to drive quality ratings, shared savings, risk scores and payment adjustments for a broad range of value-based contracts and activities.
As the popularity of risk-adjusted programs such as Medicare Advantage grows, so does the scrutiny. CMS estimates it made in excess of $70 billion in overpayments to MA plans. As a result, the Department of Justice is now pursing multiple lawsuits against multiple insurers.
In addition to regulatory risk, incorrect coding limits plan growth, provides cracks for members to slip through and depresses margins on otherwise-profitable lines of business.
Increasingly, health plans turn to proven analytic technologies to help determine the appropriate level of member condition complexity and severity, accurately predict future costs of care, reduce regulatory risk exposure and maximize risk-adjusted payments. The best of these technologies:
- Combine clinical (EHR), claims, lab, pharmacy and social determinants of health (SDoH) data to bring together necessary, but previously isolated, information.
- Leverage machine-learning algorithms to continuously improve coding accuracy and optimization across unique and differentiated network contracts.
- Utilize natural language processing to turn invaluable, but buried, clinical notes into usable data.
- Detect and automatically populate missing HCCs as appropriate
- Identify and prioritize members based on risk-adjustment improvement potential
- Deliver clinical integration to ease physician burden by revealing potential coding gaps within the EHR.
Health plans must take every advantage to optimize HCC accuracy, stay competitive, gain market share and ensure accurate and full reimbursement, and to do so in ways that minimize the burden on network physicians.
To learn more, I encourage you to download our white paper today.