Historically, Natural Language Processing (NLP) platforms have produced spurious results. Their data extraction outputs have produced too many invalid codes, which in turn meant that coders spent too much time rejecting invalid codes. Additionally, the platforms missed so many codes that coders had to recode the chart from scratch to get to a high-quality coded chart. Many people who tested NLP platforms early-on found it to be more expensive than traditional manual coding.
NLP has turned a corner in recent years thanks to significant investments in NLP platforms. The clinical rule sets have become much more refined, and machine learning (ML) and artificial intelligence (AI) components have had millions of charts run through them to tune the engines and refine the extractions. NLP vendors have worked to develop business rules specific to chart coding use cases. These platforms are now operationally viable and can drive insights into your coding business and lower coding costs per chart.
When we think about using NLP services, we are often thinking about how we can embed an NLP-enabled process into our first-pass coding process. There is nothing wrong with this approach, but there are other ways to access the benefits of NLP quickly and without having to embed it into the first-pass coding process.
Pre-coding business intelligence
Today, when you code a chart you know very little—if anything—about it before it is coded. Running NLP on charts prior to coding can offer deep insights and benefits.
No HCC charts
Typically, you must code a chart to know if there is a Hierarchical Condition Category (HCC) mapped Dx Code in it. However, NLP can now tell you before a coder has spent time in that chart. You may find that you don’t need to code those charts after NLP has run, or you may decide to code a sample of the charts to feel comfortable with the results of the NLP run.
Chart segmentation
With actionable data from an NLP run, you can think less about the traditional shotgun approach to coding and can take more of a sharpshooter approach. For example, if you have coders who specialize in cancer coding, charts that have suspected cancer codes can be funneled to those coders. Charts with more “vanilla” codes can be sent to your new or less-specialized coders.
Chart value
Running NLP prior to coding also provides better information about the possible financial value of each chart, which allows you to decide if you want to treat charts differently based on financial factors. High-value charts can be run through multiple passes to mitigate the increased regulatory risk associated with those charts. This information can also be used to sync the coding of your high- and low-value charts with submission deadlines.
These are just a few ways in which you can drive value with NLP without buying an instream solution.
Coding accuracy review
In a traditional accuracy review—otherwise known as a second-level review or an over-read—you have another coder or auditor take a fresh, second pass at the chart. While this process can increase your overall chart accuracy, it also introduces a second opportunity for human error and leaves you with the problem of what to do with the unmatched codes from the various passes.
In an NLP-enabled accuracy review, NLP is run on the charts before the second manual validation. These NLP results can be matched against the first-pass results to find the variances. Now, you only need to run manual coding validation on the new codes from the NLP run and the codes the NLP didn’t find. This has several benefits:
- Including a coder review of the unmatched codes increases your accuracy and decreases compliance risk.
- The manual coding review is being done on fewer codes, making it more efficient.
- The review of NLP codes is much faster than a traditional review, as it is usually coupled with an indexed and highlighted chart.
The net effect results in higher coding accuracy rates at a lower cost than a traditional over-read.
Risk adjustment factor accuracy review
A coding accuracy review is at the chart level, and a risk adjustment factor (RAF) accuracy review is at the member level. This is done by adding additional data sources like charts from other programs, risk adjustment processing system (RAPS), claims or other data. This kind of review drives close to 100%accuracy at the member level and has deep benefits:
- Most codes found are validated from multiple sources
- Member conditions are effectively matched to financial reimbursement
- Can be executed at a very low cost per chart
NLP can enhance your coding operations and provide benefits to your organization, even if it is used as a standalone process. Identifying HCC charts before coding, routing charts to the right coders based on specialties and level of difficulty, understanding the financial value of charts, conducting more accurate, efficient coding accuracy reviews, and benefiting from highly effective RAF accuracy reviews are just a few ways in which you can realize the benefits of NLP without purchasing a full, first-pass coding NLP solution.
