EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access · CC BY-NC 4.0

Blind Testing Method to Validate the Efficiency of ICD-10-CM Artificial Intelligence Coding Modules

Chih-Yen Sun, Zheng-Hao Li, Ming-Ju Tsai, Chung-Cheng Tsai, Hong-Jie Dai

Studies in Health Technology and Informatics · 2025

DOI: 10.3233/shti251222 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Chih-Yen Sun und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Technology, Kaohsiung Medical University Chung-Ho Memorial Hospital, Taiwan. Hauptthemen laut MEDLINE: International Classification of Diseases, Artificial Intelligence, Natural Language Processing, Clinical Coding. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

International Classification of DiseasesArtificial IntelligenceNatural Language ProcessingClinical CodingElectronic Health RecordsHumans

Stichwörter der Autor:innen

Artificial IntelligenceICD-10-CM/PCSNatural Language Processing

Autor:innen und Institutionen

  • Department of Information Technology, Kaohsiung Medical University Chung-Ho Memorial Hospital, Taiwan.
  • Department of Electrical Engineering National Kaohsiung University of Science and Technology Kaohsiung, Taiwan.
  • Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine Kaohsiung Medical University Hospital Kaohsiung, Taiwan.

Zitieren

APA

Sun, C. Y., Li, Z. H., Tsai, M. J., Tsai, C. C., & Dai, H. J. (2025). Blind Testing Method to Validate the Efficiency of ICD-10-CM Artificial Intelligence Coding Modules. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti251222

Vancouver

Sun CY, Li ZH, Tsai MJ, Tsai CC, Dai HJ. Blind Testing Method to Validate the Efficiency of ICD-10-CM Artificial Intelligence Coding Modules. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti251222

BibTeX
@article{Sun2025,
  author = {Sun, Chih-Yen and Li, Zheng-Hao and Tsai, Ming-Ju and Tsai, Chung-Cheng and Dai, Hong-Jie},
  title = {Blind Testing Method to Validate the Efficiency of ICD-10-CM Artificial Intelligence Coding Modules},
  journal = {Studies in Health Technology and Informatics},
  year = {2025},
  doi = {10.3233/shti251222}
}
Kostenlos starten →