Related Concept Videos
02:07Improving Translational Accuracy
14.1K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
14.1K
02:07Improving Translational Accuracy
3.6K
3.6K
01:27Language and Cognition
716
Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.
716
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
Sort by
Same author
A dynamic risk prediction framework for Alzheimer's disease and related dementias with interpretability.
NPJ digital medicine·2026
Same author
Clinical document metadata extraction: A scoping review.
Journal of biomedical informatics·2026
Same author
Context matching is not reasoning when performing generalized clinical evaluation of generative language models.
NPJ digital medicine·2025
Related Experiment Video
Updated: Jan 18, 2026
03:14
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
1.0K
Large Language Models Struggle in Token-Level Clinical Named Entity Recognition.
Qiuhao Lu1, Rui Li1, Andrew Wen1
1McWilliams School of Biomedical Informatics, University of Texas Health Science Center, Houston, TX, USA.
Summary
Large Language Models (LLMs) show promise for rare disease Named Entity Recognition (NER). This study explores local and proprietary LLMs for token-level clinical NER, identifying challenges and improvements.
Area of Science:
- Healthcare Informatics
- Artificial Intelligence
- Clinical Natural Language Processing
Background:
- Large Language Models (LLMs) offer potential in healthcare, especially for rare diseases with data challenges.
- Named Entity Recognition (NER) is crucial for extracting clinical information, but current LLM research focuses on document-level NER.
- A gap exists in token-level clinical NER using local open-source LLMs.
Purpose of the Study:
- To investigate the effectiveness of proprietary and local LLMs for token-level clinical NER.
- To address the challenges of data scarcity and complexity in rare disease text analysis.
- To explore different LLM application methods including prompting and fine-tuning.
Main Methods:
- Experiments using zero-shot prompting, few-shot prompting, retrieval-augmented generation (RAG), and instruction-fine-tuning.
- Evaluation of both proprietary and local LLMs on token-level clinical NER tasks.
- Focus on clinical texts, particularly those related to rare diseases.
Main Results:
- LLMs face inherent challenges in token-level NER, especially within the rare disease domain.
- The study identifies specific difficulties LLMs encounter in precise clinical entity extraction.
- Insights into potential improvements for LLM application in healthcare NER were gained.
Conclusions:
- Token-level clinical NER using LLMs, particularly local models, presents significant challenges.
- Further research and model refinement are needed for effective LLM deployment in rare disease informatics.
- This study contributes to advancing LLM applications in specialized healthcare contexts.