How Payers Can Use NLP to Improve Risk Adjustment Coding

Publish Date
Read Time
August 30, 2018

When payers think about using NLP services, they often think about how they can embed an NLP-enabled process into the first pass coding process. The process of bringing a new technology into the risk adjustment process can be daunting, and payers should be cautious to engage with the right technology partner. But to take advantage of NLP, and experience the value it can add to risk adjustment, there are other ways for payers to obtain the benefits more quickly — without having to implement a full, first-pass coding NLP solution, and even when already working with a coding vendor.

Payers Can Do Better than 95% Coding Accuracy

Payers run the traditional coding accuracy reviews, also known as second-level review or over-reads. During this review, a coder or auditor takes a second pass at the chart. While this level of review can help capture missing HCCs, it can also result in additional human errors and introduces new problems as previously captured codes end up unmatched.

Using NLP, the charts are run through the engine before the second manual validation. The NLP results can be matched against the first pass results to find the variances. This step enables Payers to only run manual coding validation on the new codes from the NLP run and the codes the NLP didn’t find. This results in these benefits:

  • High Accuracy: Including a coder review of the unmatched codes increases your accuracy and decreases compliance risk.
  • More Efficiency: NLP radically increases efficiency, as the manual coding review is being done on fewer codes.
  • Faster Coding: The review of NLP codes is much faster than a traditional review, as it is usually coupled with an indexed and highlighted chart.

Payers benefit from higher coding accuracy rates at a lower cost than a traditional second level review.

Risk Adjustment Factor (RAF) Accuracy Review

This level of review is done at the member level. This review includes reviewing additional data sources like charts from other programs, RAPS data, claims, or other data. When running this level of review, Payers can see close to 100 percent accuracy, with the following benefits:

  • Most codes found are validated from multiple sources
  • Member conditions are effectively matched to financial reimbursements
  • Cost can be very low per chart

NLP can enhance your coding operations and provide benefits to your organization, even if it is used as a standalone process, and when the coding season is already underway.

Learn more about implementing an NLP-enabled Second Level Review.

Contact Health Plan

Complete Data Solution for Health Plans Access Clinical Data with Datavant (formerly known as Ciox)

Contact us

Achieve your boldest ambitions

Explore how Datavant can be your health data logistics partner.

Contact us