Clinical Documentation Improvement Challenges 

Medical professional working on laptop while doing rounds
Clinical documentation improvement challenges continue for ICD-10 related denials as hospitals work with clinicians and coders to improve their systems.

What’s the difference between ICD-10 and ICD-10-CM? Short answer: About 130,000 codes. With the ICD-9 to ICD-10 transition pretty much complete, we thought we’d check in on clinical documentation improvement challenges at hospitals.

Pulmonology Advisor, a publication for “information and resources focused on pulmonary and critical care medicine,” expresses concerns physicians have about the current medical records situation like this: “The ICD-10-CM classification also does not allow clinicians to express “clinical concern” when there is insufficient, incomplete, or inconclusive evidence to support a firm diagnosis. Moreover, because the codes are collected for billing purposes, some argue that their use in research is ‘intrinsically flawed.’”

There has already been some field work conducted to address physician concerns. In an article from 3 years ago asking, “Can Natural Language Processing [NLP] Boost Clinical Documentation?” the editors at EHR Intelligence found the answer might be “yes,” writing about a study that concluded, “This novel dictation-based approach has the potential to reduce the time required for documentation and improve usability while maintaining documentation quality.”

A more recent article in Towards Data Science explains the promise of NLP like this: “NLP techniques have the capability to capture unstructured data, analyze the grammatical structure, determine the meaning of the information and summarize the information. As a result, NLP techniques can reduce cost and extract the information for in-depth big data analytics.”

So, natural language processing continues to look like a boon for your coding teams. But what about other solutions? In an abstract from the article on “Payment Innovations To Improve Diagnostic Accuracy And Reduce Diagnostic Error” from the journal HealthAffairs, authors Robert Berenson and Hardeep Singh list three payment-related approaches to reducing diagnostic error:

  1. “First, coding changes in the Medicare Physician Fee Schedule could facilitate the more effective use of teamwork and information technology in the diagnostic process and better support the cognitive work and time commitment that physicians make in the quest for diagnostic accuracy, especially in difficult or uncertain cases.”
  2. “Second, new APMs [Alternative Payment Models] could be developed to focus on improving diagnostic accuracy in challenging cases and make available support resources for diagnosis, including condition-specific centers of diagnostic expertise or general diagnostic centers of excellence that provide second (or even third) opinions. Performing quality improvement activities that promote safer diagnosis should be a part of the accountability of APM recipients.”
  3. “Third, the accuracy of diagnoses that trigger APM payments and establish payment amounts should be confirmed by APM recipients.”

In a nutshell, Teamwork + Information Technology + APM + Accuracy is the formula recommended in the HealthAffairs article. Its authors believe that, “implementation of these multi-pronged approaches can make current payment models more accountable for addressing diagnostic error and position diagnostic performance as a critical component of quality-based payment.”

We also note that as an article at ICD-10 Monitor has made clear, “one thing that providers must understand is that there is a difference between DRG [Diagnosis Related Groups] validation reviews and clinical validation reviews.” The authors then give some very specific recommendations:

“In general, using coders for DRG validation appeals and clinicians for clinical validation appeals is an established practice, although some appeal arguments may require utilizing both skill sets. Secondly, understand which set of clinical indicators the auditor is using to review certain diagnoses. Realize that not all patients will present with every clinical indicator, as outlined in the auditor’s denial letter, although some payers seem to expect that or else they will deny. Finally, know that many of the diagnoses in question may not have a universally accepted and agreed-upon set of criteria that must be present for a valid diagnosis. The sepsis-2/sepsis-3 definitions are a perfect example. Payors should be tolerant of some variation in physician judgment.”

What KPIs (Key Performance Indicators) does your team use to track ICD-10 performance?  Sometimes CMS can issue long, difficult policy documents, but we found a good, concise “ICD-10 KPIs at a Glance” PDF they produced. We especially like their tip that tracking ICD-10 KPIs “separately for each payer will assist in isolating the root cause of issues.”

Here’s a snapshot of the checklist CMS provides with the caveat that “you don’t have to track all of the KPIs listed below–some might not be practical or relevant for you. But even small steps to identify and resolve issues can get you on the road to higher productivity and more timely claims processing.”

Cloudmed knows that healthcare organizations face increasing regulatory compliance issues. Clinical coding and documentation requirements often overwhelm healthcare systems and lead to significant revenue leakage. That’s why we bring a powerful automated DRG Validation solution — the first of its kind to combine both technology and hands-on auditing. This web-based, fully HIPAA-compliant solution utilizes rules-based algorithms that target potential coding anomalies and/or documentation improvement opportunities at the time of coding completion.