Search
loader loading subjects...
cover
Blind Testing Method to Validate the Efficiency of ICD-10-CM Artificial Intelligence Coding Modules
Authors
Chih-Yen Sun, Zheng-Hao Li, Ming-Ju Tsai, Chung-Cheng Tsai, Hong-Jie Dai
Pages
1802 - 1803
DOI
10.3233/SHTI251222
Category
Research Article
Series
Studies in Health Technology and Informatics
Ebook
Volume 329: MEDINFO 2025 — Healthcare Smart × Medicine Deep
Abstract

This study compares coding time between Natural Language Processing (NLP) and Certified Coding Specialists (CCS) using three AI models (HAN, GPT-2, and BioMistral). Analyzing discharged patients from October to November 2024, the results indicate that GPT-2 reduced the average coding time per record by approximately 75 seconds compared to manual coding (P < 0.05).

Download PDF
Creative Commons License