Blind Testing Method to Validate the Efficiency of ICD-10-CM Artificial Intelligence Coding Modules
- PMID: 40776239
- DOI: 10.3233/SHTI251222
Blind Testing Method to Validate the Efficiency of ICD-10-CM Artificial Intelligence Coding Modules
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).
Keywords: Artificial Intelligence; ICD-10-CM/PCS; Natural Language Processing.
Similar articles
-
Developing an ICD-10 Coding Assistant: Pilot Study Using RoBERTa and GPT-4 for Term Extraction and Description-Based Code Selection.JMIR Form Res. 2025 Feb 11;9:e60095. doi: 10.2196/60095. JMIR Form Res. 2025. PMID: 39935026 Free PMC article.
-
Implementation and Evaluation of ICD-10 Artificial Intelligence Coding Assistance System.Stud Health Technol Inform. 2025 Aug 7;329:88-92. doi: 10.3233/SHTI250807. Stud Health Technol Inform. 2025. PMID: 40775825
-
Artificial Intelligence to Improve Clinical Coding Practice in Scandinavia: Crossover Randomized Controlled Trial.J Med Internet Res. 2025 Jul 3;27:e71904. doi: 10.2196/71904. J Med Internet Res. 2025. PMID: 40608484 Free PMC article. Clinical Trial.
-
Impact of artificial intelligence on electronic health record-related burnouts among healthcare professionals: systematic review.Front Public Health. 2025 Jul 3;13:1628831. doi: 10.3389/fpubh.2025.1628831. eCollection 2025. Front Public Health. 2025. PMID: 40678636 Free PMC article.
-
Self-Administered Interventions Based on Natural Language Processing Models for Reducing Depressive and Anxiety Symptoms: Systematic Review and Meta-Analysis.JMIR Ment Health. 2024 Aug 21;11:e59560. doi: 10.2196/59560. JMIR Ment Health. 2024. PMID: 39167795 Free PMC article.
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources