Is your risk adjustment model accurate to identify and address those unrecorded clinical codes?

Organizations view Medicare risk adjustment as a necessity but don’t you look at it as a strategic approach too.

With the correct organizational alignment, risk adjustment can be considered a competitive advantage. Accurate risk adjustment not only improves the medical coder’s workflow accuracy but also provides a snapshot of population health that can be used to direct care delivery efforts and improve quality ratings.

What is Risk Adjustment in healthcare?

Risk adjustment is a process that considers the health and spending of patients when examining their healthcare costs.

Of the many types of risk adjustment models below are some popular ones:

  • Centers for Medicare and Medicaid Services (CMS)
  • US News Rankings (3M-APR-DRGs)
  • Health plan prescription rates (RxHCC)
  • Medicare Advantage contract rates (CMS- Hierarchical Condition Category (HCC))
  • Affordable Care Act Health Plan Premiums (HHS-HCC).

It can be a lot of work, hassle, and expense to manage medical coding review via multiple vendors, handling every step of the retrospective risk adjustment coding process. At times, after care has been delivered and claims have been submitted to the payer.  Such reviews often uncover HCC risk adjustment codes supported by the medical record that was not reported, as well as ICD-10 diagnosis codes that should not have been submitted because they did not meet documentation guidelines.

One of the most common challenges in health care resource allocation is how to measure population health needs. An individual’s need for health care should not be restricted to curing disease; it should be interpreted in terms of the ability to benefit from health care, implied by reducing the risks of health status or enhancing the chances of improvements to health status.

Why RAAPID?

Improving efficiency, completeness, and accuracy, RAAPID automates the barriers to clinical coding, applies AI to review medical charts, and determines the appropriate adoption of ICD-10 and HCC coding for accurate and complete medical record review.

How does RAAPID.AI work?

When charts reach the coding stage, RAAPID’s AI-Enabled Analytics uses a three-step chart review workflow to facilitate efficient chart routing. Considering the National Clinical Coding Standards, the modern AI risk adjustment solution medical coder’s workflow to be more precise when capturing suspected but unreported diagnosis codes:

  1. Smart chart routing– Analyzes unreported conditions which are then routed to reviewers based on coder expertise.
  2. AI-Enabled Coding can assist certified coders with tools to:
  • Specific diagnosis code suspects – AI identifies suspected unreported diagnosis codes to the coder, allowing them to focus only on those suspected conditions from within the medical records.
  • Full-chart targeted-condition reviews – Allows AI-Identified Suspects to the coder so they can review the entire chart.
  1. Completeness– Detects if a member’s health history may still indicate possible unreported diagnosis codes. AI can also direct the medical record for additional review if needed.
  2. Time-saving operational efficiencies – AI can be configured to automatically exclude charts that do not support unreported diagnosis codes before they are retrieved.
  3. Increase retrieval rates – Analytics informs chart retrieval by identifying retrieval modalities that can be aligned with provider preferences.
  4. Reduce the need for provider action – Direct electronic health record (EHR) retrieval can remove provider action from workflow entirely.

Wrapping up

RAPPID.AI understands the impact of inaccurate coding on the patient, and its AI solution predicts and prioritizes suspected disease conditions for accurate clinical coding review. In addition, adopting a comprehensive retrospective risk adjustment solution will enhance the quality of your coding process.

Share:

Lastest Post

Subscribe To Our Newsletter

Disclaimer: All the information, views, and opinions expressed in this blog are those of the authors and their respective web sources and in no way reflect the principles, views, or objectives of RAAPID.