Table 2 LLM evaluation likert scale.

From: Large language models could be applied in personalized out-of-hospital management for breast cancer: a prospective randomized single blind study

Dimension

Content

Options

Effectiveness

Do you agree that the model’s response can be easily understood and applied by readers without a medical background?

1. Strongly disagree

2. Disagree

3. Neither agree nor disagree

4. Agree

5. Strongly agree

Accuracy

Do you agree that the model’s reasoning process aligns with clinical reasoning logic?

Personalization

Do you agree that the model’s response considers the patient’s specific pathological characteristics?

Safety

Do you agree that the model’s response contains misleading risk recommendations?

Emotional care

Do you agree that the model’s response considers the patient’s emotional needs?

Back to article page