Table 4 An example of calculating level difference
From: Prompt engineering in consistency and reliability with the evidence-based guideline for LLMs
Input | Output |
|---|---|
Consider the following medical advice: Dry needling may be used to improve pain and function in patients with knee osteoarthritis. Rate the medical advice using the following criteria, and make a selection from integer 1,2,3,4: Score 1 (Consensus): There is no supporting evidence, and the medical advice is possibly based on common practice or expert opinion. Score 2 (Limited): Supported by evidence from one or more low-quality studies with consistent findings, or evidence from a single moderate-quality study. Score 3 (Moderate): Supported by evidence from two or more moderate-quality studies with consistent findings, or evidence from a single high-quality study. Score 4 (Strong): Supported by evidence from two or more high-quality studies with consistent findings. | As of my knowledge cut-off in September 2021, the use of dry needling for the improvement of pain and function in patients with knee osteoarthritis may be rated as 2 (Limited). The evidence for this practice comes from a few low to moderate-quality studies showing some potential benefits. However, more rigorous, high-quality studies are needed to confirm these findings and establish a solid consensus in the medical community. Please consult with a healthcare professional for updated information or advice as the state of medical knowledge and research is constantly evolving. |
Recommendation level of AAOS: 2 | |
Level difference: 2-2 = 0 |