Knowledge-aware patient representation learning for multiple disease subtypes

Lu, Menglin; Zhang, Yujie; Zhang, Suixia; Shi, Hanrui; Huang, Zhengxing

doi:10.1016/j.jbi.2023.104292

Cited by 3 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is difficult to recommend a best practice, but with iterative testing and refinement, prompts can be significantly improved. Recent studies demonstrate that utilizing structured prompts can elevate LLM performance in medical diagnostics, where precision and interpretability are essential [20][21][22] .…”

Section: Introductionmentioning

confidence: 99%

Comparison of Prompt Engineering and Fine-Tuning Strategies in Large Language Models in the Classification of Clinical Notes

Zhang,

Talukdar,

Vemulapalli

et al. 2024

Preprint

View full text Add to dashboard Cite

The emerging large language models (LLMs) are actively evaluated in various fields including healthcare. Most studies have focused on established benchmarks and standard parameters; however, the variation and impact of prompt engineering and fine-tuning strategies have not been fully explored. This study benchmarks GPT-3.5 Turbo, GPT-4, and Llama-7B against BERT models and medical fellows' annotations in identifying patients with metastatic cancer from discharge summaries. Results revealed that clear, concise prompts incorporating reasoning steps significantly enhanced performance. GPT-4 exhibited superior performance among all models. Notably, one-shot learning and fine-tuning provided no incremental benefit. The model's accuracy sustained even when keywords for metastatic cancer were removed or when half of the input tokens were randomly discarded. These findings underscore GPT-4's potential to substitute specialized models, such as PubMedBERT, through strategic prompt engineering, and suggest opportunities to improve open-source models, which are better suited to use in clinical settings.

show abstract

Section: Introductionmentioning

confidence: 99%