Intelligent Medical Coding Using Transformer-Based Language Models

Notification

Announcement!

ISJEM Invites papers for various areas like engineering, Management, Science & other multi discplinary subjects. Please submit your paper for review.

ISJEM assigns a digital object identifier (DOI) to each published paper, making it easier for the paper to be cited in various major databases like Google Scholar, ResearchGate, Academia.edu, etc…

ISJEM takes 24–48 hours to publish a research paper. Within 24 hours, the submitted paper will be reviewed and notified of its status, and it will be published once the processing fee is successfully received.

Intelligent Medical Coding Using Transformer-Based Language Models

Version
Download 3
File Size 522.12 KB
Download

Intelligent Medical Coding Using Transformer-Based Language Models

Veerendra Nath Jasthi

veerendranathjasthi@gmail.com

Abstract— Medical coding is a critical process in the medical practice as it translates clinical records to a standard coding where they are referred to as, ICD-10 or CPT so as to utilize billing, statistical and research information. It is time-consuming, imprecise and manual coding requires highly qualified people. Because of the application of deep learning and natural language processing (NLP), transformer-based language models like BERT, RoBERTa, and BioBERT have been promising to automate this task. As pointed out by the present article, a smart medical coding system, which involves transformer-based models to locate unstructured clinical notes to the appropriate medical terms, is generated and tested. The proposed system code is very accurate, thus, it makes information processing simple and can be flexible to those peculiarities unique to medical terminologies.

Keywords— Medical Coding, Transformers, BERT, Clinical NLP, ICD-10, Deep Learning, Automation, Healthcare Informatics.