How Artificial Intelligence Can Improve Coding Audits

Print Friendly, PDF & Email

Medical coding audits are complex, time-consuming, and costly processes that historically have required significant investment of manual resources to complete, but, more recently, advances in artificial intelligence have made audits more efficient, accurate, and cost-effective. 

Due to the volume and complexity of clinical documentation that providers must manage each day in support of coding, the Medical Group Management Association (MGMA) recommends that medical practices perform coding audits on a regular basis. Coding audits are an important tool to ensure that a practice’s processes are functioning appropriately and are imperative for effective risk mitigation and revenue cycle optimization, according to MGMA. 

Coding audits ensure accuracy and enable practice leadership to understand the level of complexity in the coding and billing within the practice.  They can also identify educational opportunities for coders – whether outside vendors or in-house staff – to protect the practice and maintain compliance.

No one likes audits and there are logistical challenges associated with performing coding audits that make the process ripe for improvement through technologies like artificial intelligence and automation. 

Coding auditing challenges
The reality of coding audits today is that they are time-consuming and high-intensity efforts necessary to support in-house and vendor coders, with minimal visibility of performance or benchmarking. Indeed, the process for managing coding audits often involves a jumble of spreadsheets along with payer policies and procedures.

Large healthcare organizations may have multiple vendors, as well as internal teams, dedicated to coding. That means these organizations may also have five or six different methodologies for auditing, all of which are manual.  Then all the audit results must be combined. The process is time-consuming and prone to errors.

This approach results in a lack of visibility into coding errors, such as individual charge level or diagnosis codes, and coder or vendor audit dispositions. The approach also creates an inability to accurately quantify coder accuracy, limiting the opportunities to quickly and easily identify educational opportunities to improve coder performance.

In turn the process may become unmanageable and data integrity can become severely compromised. 

An intelligent approach to coding audit management
To reduce the burdens associated with coding audits, many healthcare organizations have turned to technology like artificial-intelligence-derived algorithms to drive a more automated and intelligent approach to auditing. By enabling auditors to work in a centralized workflow system, this AI-driven approach drives better coding accuracy, identifies missed coding opportunities, and creates educational opportunities for coders in real-time.

Following are several ways that AI improves coding audit management:

Provides centralized visibility across in-house and vendor coding performance: With a centralized repository for all coding audit performance data, organizations can better gauge the overall health of their coding teams. This enables users to see systemic failures to adjust workload volume and how charts get assigned, as well as identify trends in error rates to determine whether they are temporary or part of a broader trend.

Determines whether to expand or contract business with a vendor or coder: Modern coding audit management platforms can identify weak- and strong-performing team members by comparing revenue-impact metrics across error rates.

Targets the right accounts to audit: AI-driven systems enable users to target accounts to prioritize for coding audits, based on factors such as impact on revenue, performance history of vendor or coder, historical disposition of similar accounts, and attributes that may create high risk for coding errors. 

Coding audits are painful at times, but they are essential to protecting the integrity of an organization’s revenue, data, and patient documentation. With a more advanced approach than the traditional methods of performing coding audits, AI-enhanced coding audit solutions accurately assess performance, identify opportunities for improvement, and enhance coder education.

About the Author

Jacob Wilkinson, Director, Product Management at VisiQuate, provider of advanced revenue cycle analytics, intelligent workflow and AI-powered automation.

Sign up for the free insideBIGDATA newsletter.

Join us on Twitter: https://twitter.com/InsideBigData1

Join us on LinkedIn: https://www.linkedin.com/company/insidebigdata/

Join us on Facebook: https://www.facebook.com/insideBIGDATANOW


Speak Your Mind

*