Few-Shot Learning of Medical Coding Systems: A Case Study on Death Certificates with BERT and Mistral
Studies in Health Technology and Informatics · 2025
DOI: 10.3233/shti250476 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Mihai Horia Popescu und 2 weiteren Autor:innen. Beteiligte Einrichtung: University of Udine, Department of Mathematics, Computer Science and Physics. Hauptthemen laut MEDLINE: Death Certificates, International Classification of Diseases, Clinical Coding, Natural Language Processing. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Identifying the Underlying Cause of Death accurately is crucial for effective healthcare policy and planning. The World Health Organization recommends using the ICD-10 system to standardize death certificate coding, a task often supported by semi-automated systems. This paper assesses the effectiveness of BERT and Mistral language models in automating this process, focusing particularly on their handling of varied instance densities per ICD code, ranging from 1 (simulating the introduction of a new code) to 100 (representing well-established codes). Through extensive comparative experiments, we find that the finetuned Mistral model substantially outperforms BERT, especially in scenarios with limited data. Mistral’s higher effectiveness, even with limited data from less commonly used codes, highlight its potential to significantly enhance automated coding systems.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- University of Udine, Department of Mathematics, Computer Science and Physics.
Zitieren
APA
Popescu, M. H., Della Mea, V., & Roitero, K. (2025). Few-Shot Learning of Medical Coding Systems: A Case Study on Death Certificates with BERT and Mistral. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti250476
Vancouver
Popescu MH, Della Mea V, Roitero K. Few-Shot Learning of Medical Coding Systems: A Case Study on Death Certificates with BERT and Mistral. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti250476
BibTeX
@article{Popescu2025,
author = {Popescu, Mihai Horia and Della Mea, Vincenzo and Roitero, Kevin},
title = {Few-Shot Learning of Medical Coding Systems: A Case Study on Death Certificates with BERT and Mistral},
journal = {Studies in Health Technology and Informatics},
year = {2025},
doi = {10.3233/shti250476}
}
EUVIMED