AI is entering medical coding — but are the models accurate enough?
This webinar is on-demand and can be viewed at your convenience.
As large language models make their way into medical coding, health systems are facing a tough reality: most models aren't yet reliable. Coding inaccuracies, flawed HCC score capture and downstream financial risks are emerging as common concerns.
In this on-demand session, clinical informatics and AI leaders unpack what's missing in current LLM deployments and share how integrating structured clinical terminology can dramatically improve output quality and ROI.
Whether you're piloting LLMs or refining existing tools, this webinar offers a practical framework for building safer, more scalable solutions.
Insights include:
Common LLM limitations that impact coding accuracy and financial performance
How to use comprehensive clinical terminology to boost reliability
Ways to fine-tune models to support better mapping, risk adjustment and cost savings
Presenters:
Vidhya Sivakumaran, PhD
VP, Clinical Informatics & Terminology, Data Engineering, IMO Health
Jingqi Wang, PhD
SVP, Data Science & Chief AI Architect, IMO Health
