Default banner
Health Plans

Ease chart audit pain and improve coding accuracy

July 31, 2018
Automated coding support and machine-learning algorithms ease chart audit pain and improve provider relations.
President and CEO

The last decade of bringing technology and healthcare together shows successful health plan leaders gut-check every piece of innovation against its practicality at the physician level. Nowhere is this truer than the expensive and high-pain domain of chart audits.

Chart audits have long been accepted as a necessary evil – health plans enlist nurses and medical examiners to visit network provider offices to review patient/member charts, and providers allow them to come and comb through their records.

The auditors identify high-value opportunities where improvements in coding accuracy, specifically hierarchical condition categories (HCCs), leads to better outcomes across reimbursement, quality scores, risk adjustment factors and member care. Improving HCC accuracy to fully document the severity, complexity and interactions of member conditions helps payers – and providers – maximize reimbursement and close care gaps associated with HEDIS® measures, Medicare Star ratings and contracted targets. Despite the mutual benefit, chart audits are frequently a source of friction.

Thankfully, we can use advanced analytics with clinical integration to implement a more effective and less intrusive way.

Automated coding support is the way forward.

Health plans must prepare for, and move toward, clinically-integrated technology that delivers decision support and enables providers to easily improve coding practices at the point of care, driving acceptance, provider engagement and in-office improvement.

Infographic automated coding.

It’s no secret that accurately capturing and documenting codes is time-consuming and frustrating for providers and their staff. There are thousands of diagnostic codes rolling up into relatively few HCCs and the work doesn’t naturally fit into the clinical workflow. Until now.

A single, shared analytics platform can automatically inspect clinical records to accurately substantiate data and dramatically reduce the number of manual in-office chart audits. It delivers clear visibility into potential coding gaps, allowing care teams to easily address and close them at the point of care from within their EHR workflow.

A shared analytics platform enables health plans and their provider networks to see the same information across coding and quality measures, thereby eliminating error-prone hand-offs, reducing reporting burden, and helping create an environment of transparency, trust and collaboration.

Machine-learning algorithms and clinical integration.

Best-in-class analytics platforms deliver immediate coding improvement and ongoing refinement through machine-learning algorithms to:

  • Detect missing HCCs
  • Populate missing HCCs automatically, when appropriate
  • Prioritize members based on risk adjustment factor (RAF) improvement potential
  • Predict future cost, utilization, performance and risk
  • Identify and prioritize suspect conditions and co-morbidities for clinical intervention
  • Reveal potential coding gaps within the provider workflow

These technologies discover codes that existed in the previous reporting year but not the current one. When valid supporting data exists, these missing codes are automatically and appropriately populated for the current year. When supporting data does not exist, the suspected missing codes (gaps) are prioritized for internal chart auditing and clinical intervention.

A clinically-integrated platform will automatically push notifications into the clinical workflow where office staff can easily map them to upcoming appointments and providers can view and address potential gaps throughout the office visit and from within their EHR.

Infographic providers.

This type of technology-driven decision support has the direct effect of easing provider reporting burden and dramatically improving results by delivering coding visibility and the ability to take direct action at the point of care and within the clinical workflow.

Over time, as machine-learning algorithms adapt to the unique needs and nuances of the organization, the better the results and the more the platform can do to passively and organically improve HCC accuracy and risk score optimization without active intervention.

Without a doubt, balancing physician needs with the importance of coding accuracy isn’t easy. For quality leaders focused on collaboration and improving provider relationships, it’s time to gut-check your current approach to chart audits.

To learn more about improving coding accuracy and strengthening provider relationships, I encourage you to download our whitepaper, Improve Reimbursement, Quality Scores and Risk Adjustment through Better HCC Practices

Image calling the reader to download the whitepaper.