Payers, including major player Humana, are challenging the Medicare Advantage Risk Adjustment Data Validation (RADV) final rule, with more expected to follow suit. Humana’s lawsuit questions CMS’s removal of the fee-for-service (FFS) adjuster and its impact on payment errors. The legal battle may continue for years. To comply with RADV rules, payers are urged to focus on comprehensive documentation and employ artificial intelligence for compliance. Additionally, advancements in AI and machine learning can help identify coding errors and lack of documentation, while clinical validation processes may further assist Medicare Advantage plans.
The Medicare Advantage Risk Adjustment Data Validation (RADV) final rule has not been well-received by payers, with Humana leading the charge by initiating a lawsuit against CMS in an attempt to overturn the regulation.
This legal action by Humana is expected to set a precedent, with more payers likely to follow suit. In the interim, Medicare Advantage organizations are advised to concentrate on maintaining thorough documentation and harnessing the power of artificial intelligence to ensure compliance, as suggested by Michael Stearns, MD, specialized consulting director of medical informatics and health language at Wolters Kluwer, in a discussion with HealthPayerIntelligence.
Humana’s lawsuit centers on CMS’s decision to eliminate the fee-for-service (FFS) adjuster from the RADV audit process. Humana contends that this move violates the Administrative Procedure Act and lacks reasonable justification from CMS.
The FFS adjuster previously established an acceptable threshold for payment errors related to unsupported diagnosis codes and limited RADV audit recoveries to errors exceeding that threshold. CMS argues that the adjuster had no impact on risk scores or Medicare Advantage payments.
Nevertheless, Humana insists that the removal of the FFS adjuster will affect payments significantly. Dr. Stearns noted, “It would be a significant hit on revenue and it would make even a single error here and there start to count against the payer, which is pretty tough. Even the RADV process has a margin of error so that part does seem rather strict to me.”
As of now, CMS has not responded to Humana’s lawsuit, but Dr. Stearns anticipates that more payers will pursue legal action against the final rule. He stated, “I would be surprised if none of the other major payers joined in; given the amount of money, it’s worth putting in the effort and the costs associated with filing the litigation for larger payers. Humana has given them a bit of a roadmap, so they can emphasize Humana’s points or agree with them as they go forward. Humana has opened the door. The [payers] on the fence are probably strongly considering joining in.”
The outcome of these lawsuits will depend on CMS’s response, which could involve legal arguments or data and analyses to support its stance. The litigation process is expected to be protracted, contingent on the number of payers involved and the arguments presented.
While Dr. Stearns acknowledged that the removal of the FFS adjuster may not seem ideal, he stressed the necessity for change. He noted, “Some sort of calibration related to how differently doctors document in the fee-for-service model versus the risk adjustment model is needed.”
Amid ongoing litigation and the anticipation of further lawsuits, payers must find ways to comply with the RADV final rule to avoid repayments. CMS will employ extrapolation to estimate error rates based on diagnoses from 2018, placing pressure on payers to rectify claims lacking supporting documentation.
However, advancements in machine learning, artificial intelligence, and natural language processing offer solutions to identify these issues efficiently. Dr. Stearns explained, “Rather than having an auditor look at something like five records an hour, a machine can look at 500 records an hour and, based on the calibration of the tools, can point out things you want to focus on.”
The Office of Inspector General (OIG) has identified nine high-risk diagnosis groups with elevated error rates over the past two years, including acute stroke, acute heart attack, embolism, vascular claudication, major depressive disorder, lung cancer, breast cancer, colon cancer, and prostate cancer.
Some errors, such as incorrectly coding a follow-up visit as a stroke, can be addressed effectively using software tools to prevent inaccurate coding.
In addition to coding errors, a lack of supporting documentation can lead to rejections, suggesting that clinical validation may be beneficial. Dr. Stearns emphasized the importance of clinical validation, which involves determining whether a condition can be reported based on documented clinical information meeting specific criteria.
While Medicare Advantage audits may not currently involve clinical validation, Dr. Stearns suggested that it could help manage diagnoses effectively. Medicare Advantage plans can leverage automation tools and software to focus on the diagnoses typically targeted by the OIG in its audits. These tools can identify inaccurate documentation by focusing on codes or medications that should or should not be included in a patient’s chart, given their diagnosis.
Dr. Stearns concluded by noting that payers can use software tools to review records effectively, identify areas requiring correction, and pinpoint where provider education, additional guidance, and policy changes are needed.
