Selection-based prompting with synthesized candidates unlocks high-performance clinical abbreviation disambiguation via open-source LLMs

Journal of Biomedical Informatics · Published 2026-07-26 · DOI 10.1016/j.jbi.2026.105085

Authors (3)

Siwen Wei, Xiaoyu Liu, Yonghong Shi

Abstract

PubPorta does not have an abstract for this article yet.

Read the article at the publisher →

Publication details

Year

2026

Citation

Wei, S., Liu, X., Shi, Y. (2026). Selection-based prompting with synthesized candidates unlocks high-performance clinical abbreviation disambiguation via open-source LLMs. Journal of Biomedical Informatics. https://doi.org/10.1016/j.jbi.2026.105085

Related articles

• Biomedical multimodal large language models: From model-centric development to clinically grounded evaluation and integration · Journal of Biomedical Informatics · 2026 · Same journal
• Multisite evaluation of automated electronic case report form data entry from electronic health records · Journal of Biomedical Informatics · 2026 · Same journal
• Mitigating hallucinations in synthesized clinical texts to improve multimodal deep learning for dermatology · Journal of Biomedical Informatics · 2026 · Same journal
• Towards interpretable AI in personalized medicine through a radiological-biological radiomics dictionary linking semantic Lung-RADS and imaging radiomics features · Journal of Biomedical Informatics · 2026 · Same journal
• Multimodal AI in healthcare: Review of vision–language foundation models for real-world medical applications · Journal of Biomedical Informatics · 2026 · Same journal
• Evaluation of temporal preservation in synthetic longitudinal patient data · Journal of Biomedical Informatics · 2026 · Same journal
• DynaMamba: Multi-scale dynamic interacting Mamba network for irregular clinical time series classification · Journal of Biomedical Informatics · 2026 · Same journal
• A study of large language models for patient information extraction: Model architecture, fine-tuning strategy, and multi-task instruction tuning · Journal of Biomedical Informatics · 2026 · Same journal
• Towards Reliable Clinical Data: A Collaborative Data Governance Architecture with Lifecycle Integration · Journal of Biomedical Informatics · 2026 · Same journal
• Heat and hearts: An exposure-anchored computational phenotyping framework for assessing cardiovascular vulnerability during extreme heat · Journal of Biomedical Informatics · 2026 · Same journal