Coding in the Age of AI: Friend or Foe?
Article Reference Code: NAMAS.05.22.2026
Written by: Stephanie Allard, CPC, CEMA, RHIT
Artificial intelligence (AI) is rapidly transforming medical coding through auto coding tools, natural language processing, and AI driven scribes. These technologies offer efficiency, but they also introduce new compliance risks that require monitoring and oversight. The issue is no longer whether AI is being used, but how it is being monitored to ensure accuracy, documentation integrity, and regulatory compliance.
AI can improve productivity by accelerating code selection and assisting with documentation. However, when these tools are not routinely audited, they can increase errors across a large volume of claims. Without validation, incorrect coding logic or outdated rules can be applied repeatedly, creating patterns that are easily identified by payer analytics. This increases the risk of denials, audits, and recoupments. The concern is the widespread impact of automated inaccuracies.
AI systems must be continuously evaluated to ensure alignment with current coding guidelines and payer policies. Without this oversight, organizations lose visibility into whether codes are supported by documentation and medical necessity. Variances may go undetected until flagged by a payer if an organization is not paying close attention. Remember that when these tools are created they sold and implemented as is. The company that is developing the tool does not also include oversight and monitoring of their products.
AI scribes are another area where additional documentation risks are already being seen. While they can improve efficiency, they may generate generalized or templated language that does not accurately reflect the clinical encounter. In some cases, AI may infer details that were not performed or documented by the provider. This creates a disconnect between the medical record and the actual service, which can lead to audit findings. When we pair that with the provider reliance on AI documentation the risk increases. When notes are not thoroughly reviewed and validated, inaccuracies may remain in the record. Despite the use of AI, the provider is ultimately responsible for the content of the documentation a macro statement saying that AI was used and may contain errors is not a legal defense in the event of adverse findings in external investigations.
To manage these risks, practices must implement structured monitoring processes. Routine pre-billing and post-billing audits should focus on encounters influenced by AI to confirm that documentation supports the codes assigned. Oversight of AI tools is essential, including regular updates and validation of coding logic. Providers must review and authenticate all AI generated documentation to ensure accuracy. Coders should remain actively involved in final code selection, applying their expertise rather than relying solely on automated outputs.
AI can be a valuable tool, but only when used with strong oversight. We must keep a human in the loop to maintain compliance. Practices that prioritize auditing and accountability will be better positioned to benefit from AI while maintaining compliance.
Contact Stephanie on LinkedIn by Clicking her Name Below:
Stephanie Allard, CPC, CEMA, EHIT
Stephanie Allard is an expert in Medical Coding, Billing, Reimbursement, and Compliance. She is a multispecialty auditor with proficiency in more than 40 specialties including, but not limited, to behavioral health, rheumatology, orthopedics, lab services, dental, neurology, general surgery, OB/GYN, PM&R, and PT/OT. In addition to performing external audit reviews, Stephanie conducts revenue cycle reviews to help organizations maximize their workflow and repair the disconnects throughout the administrative side of their business. She uses her training and education experience to help clients implement practices and strategies that will reduce risk in the future. She also performs forensic auditing as an expert that includes focused reviews to be used in court cases and payer investigations.
NAMAS BLOG Disclaimer:
The NAMAS Blog features content written by both NAMAS staff and guest contributors. Guest contributors may present opinions or perspectives that differ from those officially instructed or encouraged by NAMAS. We believe in providing space for a range of informed viewpoints to foster dialogue, reflection, and deeper understanding within the auditing and compliance community.
Some contributors may use artificial intelligence (AI) tools in the development of their content. The decision to incorporate AI is left to the discretion of the author and does not reflect an endorsement or directive from NAMAS.
If you have questions, comments, or concerns about a specific blog post, we encourage you to contact the individual author directly. Their name and contact information are provided at the end of each post.
