Interest in using artificial intelligence (AI), like large language models (LLMs), to automate medical coding continues to grow. However, a recent study by Mount Sinai revealed that LLMs are actually poor medical coders.i
This guide explains why and how enhancements with reliable clinical terminology can help. Read now and discover how to optimize your LLM for improved mapping accuracy, HCC score integration, and cost efficiency.
Key Learnings:
Shortcomings of out-of-the-box LLMs
The impact of clinical ontologies and informatics
How domain-specific IMO Clinical AI improves mapping accuracy
i 1Soroush, Ali., et al. Large Language Models Are Poor Medical Coders — Benchmarking of Medical Code Querying. NEJM AI. 19 April 2024. Accessed via: https://ai.nejm.org/doi/full/10.1056/AIdbp2300040
Featured speaker(s)
i 1Soroush, A., Glicksberg, B. S., Zimlichman, E., Barash, Y., Freeman, R., Charney, A. W., … & Klang, E. (2024). Large Language Models Are Poor Medical Coders—Benchmarking of Medical Code Querying. NEJM AI, AIdbp2300040.
Marketing Director
IMO
Thomas Magnum
Marketing Manager
IMO
B.A. Baracus
Data Analyst
IMO
B.A. Baracus
Data Analyst
IMO
i 1Soroush, A., Glicksberg, B. S., Zimlichman, E., Barash, Y., Freeman, R., Charney, A. W., … & Klang, E. (2024). Large Language Models Are Poor Medical Coders—Benchmarking of Medical Code Querying. NEJM AI, AIdbp2300040.
