Practical Design and Benchmarking of Generative AI Applications for Surgical Billing and Coding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929668632870912 |
|---|---|
| author | Rollman, John C. Rogers, Bruce Zaribafzadeh, Hamed Buckland, Daniel Rogers, Ursula Gagnon, Jennifer Meireles, Ozanan Jennings, Lindsay Bennett, Jim Nicholson, Jennifer Lad, Nandan Cendales, Linda Seas, Andreas Martinino, Alessandro Hwang, E. Shelley Kirk, Allan D. |
| author_facet | Rollman, John C. Rogers, Bruce Zaribafzadeh, Hamed Buckland, Daniel Rogers, Ursula Gagnon, Jennifer Meireles, Ozanan Jennings, Lindsay Bennett, Jim Nicholson, Jennifer Lad, Nandan Cendales, Linda Seas, Andreas Martinino, Alessandro Hwang, E. Shelley Kirk, Allan D. |
| contents | Background: Healthcare has many manual processes that can benefit from automation and augmentation with Generative Artificial Intelligence (AI), the medical billing and coding process. However, current foundational Large Language Models (LLMs) perform poorly when tasked with generating accurate International Classification of Diseases, 10th edition, Clinical Modification (ICD-10-CM) and Current Procedural Terminology (CPT) codes. Additionally, there are many security and financial challenges in the application of generative AI to healthcare. We present a strategy for developing generative AI tools in healthcare, specifically for medical billing and coding, that balances accuracy, accessibility, and patient privacy.
Methods: We fine tune the PHI-3 Mini and PHI-3 Medium LLMs using institutional data and compare the results against the PHI-3 base model, a PHI-3 RAG application, and GPT-4o. We use the post operative surgical report as input and the patients billing claim the associated ICD-10, CPT, and Modifier codes as the target result. Performance is measured by accuracy of code generation, proportion of invalid codes, and the fidelity of the billing claim format.
Results: Both fine-tuned models performed better or as well as GPT-4o. The Phi-3 Medium fine-tuned model showed the best performance (ICD-10 Recall and Precision: 72%, 72%; CPT Recall and Precision: 77%, 79%; Modifier Recall and Precision: 63%, 64%). The Phi-3 Medium fine-tuned model only fabricated 1% of ICD-10 codes and 0.6% of CPT codes generated.
Conclusions: Our study shows that a small model that is fine-tuned on domain-specific data for specific tasks using a simple set of open-source tools and minimal technological and monetary requirements performs as well as the larger contemporary consumer models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_05479 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Practical Design and Benchmarking of Generative AI Applications for Surgical Billing and Coding Rollman, John C. Rogers, Bruce Zaribafzadeh, Hamed Buckland, Daniel Rogers, Ursula Gagnon, Jennifer Meireles, Ozanan Jennings, Lindsay Bennett, Jim Nicholson, Jennifer Lad, Nandan Cendales, Linda Seas, Andreas Martinino, Alessandro Hwang, E. Shelley Kirk, Allan D. Computation and Language Machine Learning I.2.7; I.2.1; J.3 Background: Healthcare has many manual processes that can benefit from automation and augmentation with Generative Artificial Intelligence (AI), the medical billing and coding process. However, current foundational Large Language Models (LLMs) perform poorly when tasked with generating accurate International Classification of Diseases, 10th edition, Clinical Modification (ICD-10-CM) and Current Procedural Terminology (CPT) codes. Additionally, there are many security and financial challenges in the application of generative AI to healthcare. We present a strategy for developing generative AI tools in healthcare, specifically for medical billing and coding, that balances accuracy, accessibility, and patient privacy. Methods: We fine tune the PHI-3 Mini and PHI-3 Medium LLMs using institutional data and compare the results against the PHI-3 base model, a PHI-3 RAG application, and GPT-4o. We use the post operative surgical report as input and the patients billing claim the associated ICD-10, CPT, and Modifier codes as the target result. Performance is measured by accuracy of code generation, proportion of invalid codes, and the fidelity of the billing claim format. Results: Both fine-tuned models performed better or as well as GPT-4o. The Phi-3 Medium fine-tuned model showed the best performance (ICD-10 Recall and Precision: 72%, 72%; CPT Recall and Precision: 77%, 79%; Modifier Recall and Precision: 63%, 64%). The Phi-3 Medium fine-tuned model only fabricated 1% of ICD-10 codes and 0.6% of CPT codes generated. Conclusions: Our study shows that a small model that is fine-tuned on domain-specific data for specific tasks using a simple set of open-source tools and minimal technological and monetary requirements performs as well as the larger contemporary consumer models. |
| title | Practical Design and Benchmarking of Generative AI Applications for Surgical Billing and Coding |
| topic | Computation and Language Machine Learning I.2.7; I.2.1; J.3 |
| url | https://arxiv.org/abs/2501.05479 |