明天分享一篇科研文献：Wang Q, Chen Z, Zhang H, et al. Large language models could be applied in personalized out-of-hospital management for breast cancer: a prospective randomized single blind study. Sci Rep. 2025;15(1):33589.
IF 3.9, Q1
文献解读
大言语模型运用于乳腺癌的个性化院外管理：一项前瞻性随机单盲研讨
Large language models could be applied in personalized out-of-hospital management for breast cancer: a prospective randomized single blind study
（1）首先，在数据搜集阶段，建立了一个数据清洗和分类流程，用于从公开的乳腺癌相关对话数据集（Huatuo-26M）中提取成绩数据集。该数据集涵盖了三种典型的院外管理运用场景：疾病咨询、康复指点和心思管理。此外，从浙江大学附属邵逸夫医院乳腺癌数据库中选取了已去除身份信息的真实患者数据（10 例，表1），构建了一个电子病历（electronic health record，EHR）数据集。
第三，归入了 4 位参与 LLM 反应评价的医生，个体间的异质性也能够影响结果。但是，研讨采用了 Cohen's Kappa 检验来降低潜在的偏倚。在数据集 A 中，DS-R1 得分的 Cohen's Kappa 检验结果为 0.52（ P <0.01），GPT-o3得分的Cohen's Kappa检验结果为0.68（ P <0.01）。在数据集B中，DS-R1评分的结果为0.80（ P <0.01），GPT-o3评分的结果为0.54（ P <0.01）。
Please determine whether the following content is related to postoperative rehabilitation for breast cancer. Note: It must explicitly mention breast cancer, and the dialogue must occur in a postoperative scenario. The judgment should be as strict as possible to filter out as many false positives as possible. Only output True or False.
1.2. Appendix A2. Classification and summarization prompts
QA Dataset:
{qa 1}, {qa 2}, {qa 3}, …
Please summarize the questions related to the three domains of disease consultation, rehabilitation guidance, and psychological management from the following question-and-answer content.
Definitions:
Disease consultation: These involve patients' queries about their disease status, including but not limited to surgery outcomes, pathology reports, recurrence risks, metastasis possibilities, and subsequent treatment plans (e.g., radiation therapy, chemotherapy, endocrine therapy, targeted therapy). They typically focus on the nature, extent, progression, and prognosis of the disease.
Rehabilitation Guidance: These involve practical issues patients encounter during postoperative recovery, including but not limited to wound care, pain management, dietary nutrition, exercise, lymphedema prevention, and adjustments to daily life. They generally focus on improving physical function, enhancing quality of life, and reducing complications.
Psychological management: These involve psychological distress experienced by patients during illness and treatment, including but not limited to anxiety, depression, fear, insomnia, emotional fluctuations, interpersonal relationship issues, and sexual health problems. They typically address how to manage negative emotions, reduce psychological stress, and rebuild a positive mindset.
Notes:
The summarized questions should not include any personal patient information.
The questions should be concise.
No more than 10 questions should be listed for each domain. If there are more than 10, only retain the most frequently occurring questions.
According to the 'patient information', please select one problem from the ' disease consultation ', ' rehabilitation guidance 'and ' psychological management 'of the question dataset that is most consistent with the patient's situation and most likely to occur at the same time and form a set of patient problem sets. Ten different sets of patient questions were selected 10 times and output with json.
Now that you're an out-of-hospital breast cancer patient, your EHR information and core needs have been clearly defined in the above section. Here you are in a group chat asking for help from a health care provider.
Now that you're an out-of-hospital breast cancer patient, your EHR information and core needs have been clearly defined in the above section. Here you are in a group chat asking for help from a health care provider. Please follow the way patients communicate in the ' Example group chat' and express your needs.
Attention: You only need to speak one request at a time, not necessarily in order. Pay attention to the context and your personal information during the conversation and try to give some feedback to what I am saying. End the conversation politely when the core appeal is met. I'm going to be talking to you as the doctor, and you're just going to be the patient.
{dialogue history}
1.5. Appendix A5. Virtual doctor prompt
System Prompt:
Now that you're a breast cancer doctor, your patient is contacting you for help after surgery.
EHR of the patient is shown below: {EHR}
Please provide as professional, effective and understandable feedback as possible in conjunction with the patient's information.
User Prompt:
{dialogue history}
1.6. Appendix A6. Conversation monitoring prompt
System Prompt:
You are the conversation monitor, and your function is to determine if the conversation is complete. All you must do is output True or False.
Please determine whether the patient in the following conversation has obtained all the necessary information based on the core needs. If yes, output True; otherwise, output False. No additional content is required.
Conversation: {dialogue history}
1.7. Appendix A7. Translation prompt
System Prompt:
Please act as a translation software to translate the input text into Chinese.
User Prompt:
{content}
2. Appendix B. Prompt Design
In Appendix B, we will present examples of DeepSeek-V3 translating English text generated by GPT-o3 into Chinese text to demonstrate the fairness of translation in this study. Since the main text content of GPT-o3 is in Chinese, with only the reasoning part in English, the examples will only display the English content of the reasoning section that requires translation.
Example 1:
Original Text (English):
**Providing post-surgery guidance**\nI’m tasked with giving post-surgery advice to a 63-year-old breast cancer patient. The details provided include specific characteristics such as the diagnosis method, tumor location, and measurement.\n**Understanding patient needs**\nTaking a closer look at the patient's age, menstrual status, diagnostic method, and tumor specifics to tailor post-surgery advice effectively.
I'm gathering info on managing a post-surgery breast cancer patient, focusing on ensuring accurate reporting and considering potential complications and follow-up care. Progress is steady, but there's more to explore.\n**Crafting a comprehensive reply**\nI'm assembling a thorough list of potential post-surgery complications for a 63-year-old breast cancer patient, including pain, bleeding, and infection, and detailing accurate diagnostic methods.
**Assessing post-surgery**\nI'm piecing together the patient's medical history, including their age, lack of stillness, diagnosis method, tumor location, and physical measurements. This helps me evaluate their progress and tailor ongoing care.\n**Gathering relevant details**\nI'm noting the patient's age, menstrual status, diagnosis method, tumor location, and physical measurements, aiming to understand their needs and manage post-surgery care effectively.