Advancing Medical Coding with AI and NLP Driven solutions

The Hard fact!

Physicians are often Over burdened with their Patient care routine, and thus often slip off writing medical history of writing medical history and notes or sometimes lack the proper guidance on its Criticality.  This can lead to discrepancies between Payers and Coders. In the cycle of documentation to Records to Claim submission – Medical Coders play a vital role. They derive the ICD10 and HCC codes, and based on their reviews, Payers submit the claims and Risk adjustment Data to CMS. Any single missed point or mistake can lead to an error in RAF score which further increases the risks of liability Penalties. 

Challenges for Payers, Coders, Providers, and Auditors

While we transition to a value-based digital healthcare ecosystem, accurate coding and auditing capabilities are critical. Besides adequate resources, healthcare payers, coders, and providers need to understand how to overcome challenges and achieve their goals. The challenge for Coders may be a huge Chart review task, an inadequate number of manpower who are not the latest technology versed, or might be in need of the “Correct Technology partner”. Additionally, with the ever-evolving coding guidelines, the risk of incorrect or outdated medical codes are also increasing. Those errors can be risky, and at a high Audit penalty risk. 

CMS’ overall objective an audit is to

  • Review quality of care provided to patients
  • Educate providers on documentation guidelines
  • Determine if organizational policies are current and effective
  • Optimize revenue cycle management
  • Ensure appropriate revenue is captured
  • Defend against federal and payer audits, malpractice litigation, and health plan denials

They select less than 5% records (submitted by a health plan) for audit. Mostly they do manual review. But if the quantity is more, they may also prefer to use AI solutions like ours.

What does CMS determine while calculating risk scores?

The CMS calculates RAF scores based on the enrollee’s diagnosis received from healthcare providers, including physicians and hospitals. An MA organization, healthcare insurance companies will then collect diagnosis codes that the physicians document and submit to the CMS. The CMS will then map certain diagnosis codes based on similar clinical characteristics, severity, and cost implications, into Hierarchical Condition Categories (HCCs).

Now, each HCC has a factor (numerical value) assigned to it for use in each enrollee’s risk score. The CMS then consolidates certain HCCs into related-disease groups as a part of the risk adjustment program. Within each of these groups, CMS assigns an HCC for only the most severe ones in a related-disease group.

Therefore, if MA organizations submit diagnosis codes for an enrollee that map to more than one of the HCCs in a related-disease group, only the most severe HCC will be considered for determining the enrollee’s RAF scores.

For example: If an MA organization submits diagnosis codes for an enrollee that map to the HCCs for lung cancer and immune disorders, the CMS assigns a separate factor for this disease interaction. By doing so, CMS increases the enrollee’s risk score for each of the two HCC factors and by an additional factor for the disease interaction.

The CMS uses the diagnosis codes of an enrollee for the service year to determine HCCs and calculate risk scores for the following calendar year, which is also known as the payment year. Therefore, an enrollee’s risk score will not change for the year in which a diagnosis is made, instead, the risk score updates for the year after the diagnosis has been made. 

Introducing RAAPID’s HCC COMPASS

HCC COMPASS is World’s first personalized AI Powered Risk Adjustment Coding & Audit Platform. Now leverage natural language processing (NLP) and deep learning (DL) and look at clinical charts and claims both ways (ADDs and DELETEs) to capture a complete, defensible picture of member/patient risk.

HCC COMPASS can help you perform better and offer a comprehensive chart review and audit to auto suggest ICD-10 CM and HCC along with MEAT evidence/gaps. It also compares the claims with the charts to identify “Adds”(unclaimed codes) and “Deletes” (overclaimed, unsubstantiated codes). This helps coders quickly identify, add or delete based on the suggestions with proper supporting evidences.

Key benefits

  • Comprehensive clinical data review and QA
  • Adhere to the Medical coding guidelines
  • Optimize RAF scoring opportunities
  • Ensure optimized RAF score is captured 
  • Automate and streamline risk adjustment coding workflow.

Ending note

Considering this, AI is surely acting as a thrust for healthcare payers and medical coders to now only improve efficiency but also contribute to enhancing patient health status and value-based care as a whole.

Share:

Lastest Posts

Subscribe To Our Newsletter

This field is for validation purposes and should be left unchanged.

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.