In this session, we'll explore the use of generative AI models like ChatGPT in auditing E&M documentation. We'll start with an overview of how ChatGPT operates, followed by live examples of the AI being used to audit sample medical record notes. Using these as case studies, we'll discuss what AI can do well and where it can miss the mark, showcasing both successful and erroneous audit outcomes. The session will cover how generative AI models can be a helpful tool for quickly cutting through medical terminology and clinical contexts to make better judgments about medical decision-making and medical necessity but also highlight the risk of generating factual errors and what can cause them. We'll wrap up with a summary of the do's and don’ts when using AI in E&M auditing to help ensure a balanced and informed approach.
THREE (3) LEARNING OBJECTIVES
- Understand the basics of generative AI models like ChatGPT and see their application in auditing E&M documentation through live demonstrations.
- Identify the advantages and limitations of using AI models in E&M auditing by analyzing examples of both correct and incorrect audit outcomes, enabling a balanced approach to leveraging AI.
- Learn how AI models can speed up an auditor’s information processing while being aware of the potential for factual inaccuracies, and why AI output should never replace a human auditor’s experience, intuition, and judgement.