Evaluating the Efficacy of Large Language Models in CPT Coding for Craniofacial Surgery: A Comparative Analysis

Emily L Isch; Advith Sarikonda; Abhijeet Sambangi; Angeleah Carreras; Adrija Sircar; D Mitchell Self; Theodore E Habarth-Morales; E J Caterson; Mario Aycart

doi:10.1097/SCS.0000000000010575

Evaluating the Efficacy of Large Language Models in CPT Coding for Craniofacial Surgery: A Comparative Analysis

J Craniofac Surg. 2024 Sep 2. doi: 10.1097/SCS.0000000000010575. Online ahead of print.

Authors

Emily L Isch¹, Advith Sarikonda², Abhijeet Sambangi², Angeleah Carreras², Adrija Sircar², D Mitchell Self³, Theodore E Habarth-Morales², E J Caterson⁴, Mario Aycart⁴

Affiliations

¹ Department of General Surgery, Thomas Jefferson University.
² Sidney Kimmel Medical College at Thomas Jefferson University.
³ Department of Neurosurgery, Thomas Jefferson University and Jefferson Hospital for Neuroscience, Philadelphia, PA.
⁴ Department of Surgery, Division of Plastic Surgery, Nemours Children's Hospital Wilmington, DE.

PMID: 39221924
DOI: 10.1097/SCS.0000000000010575

Abstract

Background: The advent of Large Language Models (LLMs) like ChatGPT has introduced significant advancements in various surgical disciplines. These developments have led to an increased interest in the utilization of LLMs for Current Procedural Terminology (CPT) coding in surgery. With CPT coding being a complex and time-consuming process, often exacerbated by the scarcity of professional coders, there is a pressing need for innovative solutions to enhance coding efficiency and accuracy.

Methods: This observational study evaluated the effectiveness of 5 publicly available large language models-Perplexity.AI, Bard, BingAI, ChatGPT 3.5, and ChatGPT 4.0-in accurately identifying CPT codes for craniofacial procedures. A consistent query format was employed to test each model, ensuring the inclusion of detailed procedure components where necessary. The responses were classified as correct, partially correct, or incorrect based on their alignment with established CPT coding for the specified procedures.

Results: The results indicate that while there is no overall significant association between the type of AI model and the correctness of CPT code identification, there are notable differences in performance for simple and complex CPT codes among the models. Specifically, ChatGPT 4.0 showed higher accuracy for complex codes, whereas Perplexity.AI and Bard were more consistent with simple codes.

Discussion: The use of AI chatbots for CPT coding in craniofacial surgery presents a promising avenue for reducing the administrative burden and associated costs of manual coding. Despite the lower accuracy rates compared with specialized, trained algorithms, the accessibility and minimal training requirements of the AI chatbots make them attractive alternatives. The study also suggests that priming AI models with operative notes may enhance their accuracy, offering a resource-efficient strategy for improving CPT coding in clinical practice.

Conclusions: This study highlights the feasibility and potential benefits of integrating LLMs into the CPT coding process for craniofacial surgery. The findings advocate for further refinement and training of AI models to improve their accuracy and practicality, suggesting a future where AI-assisted coding could become a standard component of surgical workflows, aligning with the ongoing digital transformation in health care.