Few-shot Generation of Medical Incident Causal Factors and Preventive Measures Using Category-based Example Selection
Transactions of the Japanese Society for Artificial Intelligence · 01.07.2026 · 41 (4) · AN40-E_1-12
DOI: 10.1527/tjsai.41-4_an40-e ↗Kurz gefasst
Fachartikel in der Zeitschrift Transactions of the Japanese Society for Artificial Intelligence, erschienen am 01.07.2026. Verfasst von Yuna Haseyama und 3 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben.
Abstract (Originalsprache)
In high-stakes domains such as healthcare, the reliability of Large Language Models (LLMs) is critical, particularlywhen generating clinical insights from incident reports. This study proposes a category-based few-shot exampleselection method for prompting LLMs to generate background/causal factors and preventive measures from detailsof the medical incidents. For our experiments, we use the Japanese Medical Incident Dataset (JMID), a structureddataset of 3,884 real-world medical accident and near-miss reports. These reports are variably annotated with a widerange of tags―some include descriptive information (e.g.,“ medications, ”“ blood transfusion therapy ”). We alsomake this dataset publicly available to support future research. We compare a zero-shot baseline and three few-shotexample selection strategies―random sampling, cosine similarity-based selection, and our proposed category-basedmethod―using GPT-4o and Llama 3.3. Results show that the category-based approach achieves the highest precisionand most stable generation behavior, while similarity-based selection often leads to unintended outputs and safety filteractivation. These findings suggest that selecting examples based on human-interpretable dataset tags can improvegeneration precision and stability in clinical LLM applications.
Zitieren
APA
Haseyama, Y., Ito, T., Sakaji, H., & Noda, I. (2026). Few-shot Generation of Medical Incident Causal Factors and Preventive Measures Using Category-based Example Selection. Transactions of the Japanese Society for Artificial Intelligence, 41(4), AN40-E_1-12. https://doi.org/10.1527/tjsai.41-4_an40-e
Vancouver
Haseyama Y, Ito T, Sakaji H, Noda I. Few-shot Generation of Medical Incident Causal Factors and Preventive Measures Using Category-based Example Selection. Transactions of the Japanese Society for Artificial Intelligence. 2026;41(4):AN40-E_1-12. doi:10.1527/tjsai.41-4_an40-e
BibTeX
@article{Haseyama2026,
author = {Haseyama, Yuna and Ito, Tomoki and Sakaji, Hiroki and Noda, Itsuki},
title = {Few-shot Generation of Medical Incident Causal Factors and Preventive Measures Using Category-based Example Selection},
journal = {Transactions of the Japanese Society for Artificial Intelligence},
year = {2026},
volume = {41},
number = {4},
pages = {AN40--E_1--12},
doi = {10.1527/tjsai.41-4_an40-e}
}
EUVIMED