Medical Large Language Model-Assisted Diagnosis and Treatment in Primary Care Chronic Disease Management
2026年7月27日 更新者：Jiangsu Taizhou People's Hospital
Verification and Application Study of Medical Large Language Model-Assisted Diagnosis and Treatment in Primary Care Chronic Disease Management: A Randomized Controlled Study
This study aims to explore the feasibility of using medical large language models to assist in chronic disease management.
By setting up experimental and control group interventions and having experts blindly evaluate anonymized cases, it compares different management approaches in chronic disease care, verifying the scientific basis, effectiveness, and potential for broader use of medical large language models in supporting chronic disease management.
研究概览
研究类型
介入性
注册 (估计的)
20
阶段
- 不适用
联系人和位置
本节提供了进行研究的人员的详细联系信息，以及有关进行该研究的地点的信息。
学习联系方式
- 姓名：Guoyu Wang, MD
- 电话号码：+8615951154720
- 邮箱：wangguoyutzheart@163.com
学习地点
-
-
Jiangsu
-
Taizhou、Jiangsu、中国、225300
- The Affiliated Taizhou People's Hospital of Nanjing Medical University
-
接触：
- Guoyu Wang, MD
- 电话号码：+8615951154720
- 邮箱：wangguoyutzheart@163.com
-
-
参与标准
研究人员寻找符合特定描述的人，称为资格标准。这些标准的一些例子是一个人的一般健康状况或先前的治疗。
资格标准
适合学习的年龄
- 成人
- 年长者
接受健康志愿者
不
描述
Inclusion Criteria:
- Work experience of 3 years or more;
- Able to complete the case assessment tasks required by the study;
- Have a practicing doctor qualification;
- Work at a township health center or community health service center;
- Voluntarily participate in the study and sign the informed consent form.
Exclusion Criteria:
N/A
学习计划
本节提供研究计划的详细信息，包括研究的设计方式和研究的衡量标准。
研究是如何设计的？
设计细节
- 主要用途：其他
- 分配：随机化
- 介入模型：并行分配
- 屏蔽：单身的
武器和干预
参与者组/臂 |
干预/治疗 |
|---|---|
|
有源比较器：LLM-Assisted Intervention Group
Primary care doctors creating management plans for chronic diseases (coronary heart disease, atrial fibrillation, heart failure, stroke) with the help of large medical language models
|
The primary care physicians in the intervention group completed the management decisions for chronic disease cases, including disease assessment, examination suggestions, treatment plans, selection of management methods, and health education, with the assistance of the medical LLM.
|
|
无干预：Usual Care Control Group
Primary care doctors creating management plans for chronic diseases (coronary heart disease, atrial fibrillation, heart failure, stroke) without the help of a large medical language model
|
研究衡量的是什么？
主要结果指标
结果测量 |
措施说明 |
大体时间 |
|---|---|---|
|
expert overall scores
大体时间：through study completion, an average of 3 months.
|
A total of 200 cases (50 each of coronary heart disease, atrial fibrillation, heart failure, and stroke) were grouped by disease type and independently evaluated in a blinded manner by three subspecialty experts.
For each case, the two management plans were anonymized in the same way and then randomly labeled by a computer as Plan A and Plan B. Experts could only view the anonymized case information and the two corresponding anonymized management plans.
They rated them using a Likert scale on several aspects: accuracy of condition assessment, reasonableness of test recommendations, reasonableness of treatment plans, appropriateness of management choices, scientific nature of patient education content, feasibility at the primary care level, overall clinical quality.
Experts were instructed to rank the seven dimensions from lowest to highest quality.
These ordinal rankings were then converted into standardized scores of 1 to 5. Higher scores mean better.
|
through study completion, an average of 3 months.
|
次要结果测量
结果测量 |
措施说明 |
大体时间 |
|---|---|---|
|
accuracy of condition assessment
大体时间：through study completion, an average of 3 months.
|
A total of 200 cases (50 each of coronary heart disease, atrial fibrillation, heart failure, and stroke) were grouped by disease type and independently evaluated in a blinded manner by three subspecialty experts.
For each case, the two management plans were anonymized in the same way and then randomly labeled by a computer as Plan A and Plan B. Experts could only view the anonymized case information and the two corresponding anonymized management plans.
They rated them using a Likert scale on accuracy of condition assessment from lowest to highest quality.
These ordinal rankings were then converted into standardized scores of 1 to 5. Higher scores mean better.
|
through study completion, an average of 3 months.
|
|
reasonableness of test recommendations
大体时间：through study completion, an average of 3 months.
|
A total of 200 cases (50 each of coronary heart disease, atrial fibrillation, heart failure, and stroke) were grouped by disease type and independently evaluated in a blinded manner by three subspecialty experts.
For each case, the two management plans were anonymized in the same way and then randomly labeled by a computer as Plan A and Plan B. Experts could only view the anonymized case information and the two corresponding anonymized management plans.
They rated them using a Likert scale regarding the reasonableness of test recommendations.
Experts were instructed to rank the dimension from lowest to highest quality.
These ordinal rankings were then converted into standardized scores of 1 to 5. Higher scores mean better.
|
through study completion, an average of 3 months.
|
|
reasonableness of treatment plans
大体时间：through study completion, an average of 3 months.
|
A total of 200 cases (50 each of coronary heart disease, atrial fibrillation, heart failure, and stroke) were grouped by disease type and independently evaluated in a blinded manner by three subspecialty experts.
For each case, the two management plans were anonymized in the same way and then randomly labeled by a computer as Plan A and Plan B. Experts could only view the anonymized case information and the two corresponding anonymized management plans.
They rated them using a Likert scale regarding the reasonableness of treatment plans.
Experts were instructed to rank the dimension from lowest to highest quality.
These ordinal rankings were then converted into standardized scores of 1 to 5. Higher scores mean better.
|
through study completion, an average of 3 months.
|
|
appropriateness of management choices
大体时间：through study completion, an average of 3 months.
|
A total of 200 cases (50 each of coronary heart disease, atrial fibrillation, heart failure, and stroke) were grouped by disease type and independently evaluated in a blinded manner by three subspecialty experts.
For each case, the two management plans were anonymized in the same way and then randomly labeled by a computer as Plan A and Plan B. Experts could only view the anonymized case information and the two corresponding anonymized management plans.
They rated them using a Likert scale regarding the ppropriateness of management choices.
Experts were instructed to rank the dimension from lowest to highest quality.
These ordinal rankings were then converted into standardized scores of 1 to 5. Higher scores mean better.
|
through study completion, an average of 3 months.
|
|
scientific nature of patient education content
大体时间：through study completion, an average of 3 months.
|
A total of 200 cases (50 each of coronary heart disease, atrial fibrillation, heart failure, and stroke) were grouped by disease type and independently evaluated in a blinded manner by three subspecialty experts.
For each case, the two management plans were anonymized in the same way and then randomly labeled by a computer as Plan A and Plan B. Experts could only view the anonymized case information and the two corresponding anonymized management plans.
They rated them using a Likert scale regarding the scientific nature of patient education content.
Experts were instructed to rank the dimension from lowest to highest quality.
These ordinal rankings were then converted into standardized scores of 1 to 5. Higher scores mean better.
|
through study completion, an average of 3 months.
|
|
feasibility at the primary care level
大体时间：through study completion, an average of 3 months.
|
A total of 200 cases (50 each of coronary heart disease, atrial fibrillation, heart failure, and stroke) were grouped by disease type and independently evaluated in a blinded manner by three subspecialty experts.
For each case, the two management plans were anonymized in the same way and then randomly labeled by a computer as Plan A and Plan B. Experts could only view the anonymized case information and the two corresponding anonymized management plans.
They rated them using a Likert scale regarding the feasibility at the primary care level.
Experts were instructed to rank the dimension from lowest to highest quality.
These ordinal rankings were then converted into standardized scores of 1 to 5. Higher scores mean better.
|
through study completion, an average of 3 months.
|
|
the overall clinical quality
大体时间：through study completion, an average of 3 months.
|
A total of 200 cases (50 each of coronary heart disease, atrial fibrillation, heart failure, and stroke) were grouped by disease type and independently evaluated in a blinded manner by three subspecialty experts.
For each case, the two management plans were anonymized in the same way and then randomly labeled by a computer as Plan A and Plan B. Experts could only view the anonymized case information and the two corresponding anonymized management plans.
They rated them using a Likert scale regarding the overall clinical quality.
Experts were instructed to rank the dimension from lowest to highest quality.
These ordinal rankings were then converted into standardized scores of 1 to 5. Higher scores mean better.
|
through study completion, an average of 3 months.
|
|
risk advice
大体时间：through study completion, an average of 3 months.
|
A total of 200 cases (50 each of coronary heart disease, atrial fibrillation, heart failure, and stroke) were grouped by disease type and independently evaluated in a blinded manner by three subspecialty experts.
For each case, the two management plans were anonymized in the same way and then randomly labeled by a computer as Plan A and Plan B. Experts could only view the anonymized case information and the two corresponding anonymized management plans.
If there is no risk advice, the expert selects 'No'; otherwise, the expert selects 'Yes' and specifically lists the content of the risk advice.
|
through study completion, an average of 3 months.
|
|
Any diagnostic or treatment information missing
大体时间：through study completion, an average of 3 months.
|
A total of 200 cases (50 each of coronary heart disease, atrial fibrillation, heart failure, and stroke) were grouped by disease type and independently evaluated in a blinded manner by three subspecialty experts.
For each case, the two management plans were anonymized in the same way and then randomly labeled by a computer as Plan A and Plan B. Experts could only view the anonymized case information and the two corresponding anonymized management plans.
If there is no omission of diagnostic and treatment information, the expert selects "No"; otherwise, the expert selects "Yes" and specifically lists the omitted diagnostic and treatment content.
|
through study completion, an average of 3 months.
|
|
feedback regarding the use of medical LLM by primary care physicians
大体时间：through study completion, an average of 3 months.
|
After primary care physicians complete a case assessment assisted by medical LLM , they will fill out an evaluation of the medical LLM usage, including whether the medical LLM helped in disease assessment, assisted in formulating examination plans, aided in developing treatment plans, improved chronic disease management capabilities, supported chronic disease education, assisted in management approach selection, enhanced confidence, saved time, whether there were hallucinations or omissions, whether it provided risky suggestions, and any additional comments on the use of the medical LLM.
|
through study completion, an average of 3 months.
|
合作者和调查者
在这里您可以找到参与这项研究的人员和组织。
研究记录日期
这些日期跟踪向 ClinicalTrials.gov 提交研究记录和摘要结果的进度。研究记录和报告的结果由国家医学图书馆 (NLM) 审查，以确保它们在发布到公共网站之前符合特定的质量控制标准。
研究主要日期
学习开始 (估计的)
2026年8月17日
初级完成 (估计的)
2026年9月30日
研究完成 (估计的)
2026年11月30日
研究注册日期
首次提交
2026年7月20日
首先提交符合 QC 标准的
2026年7月27日
首次发布 (实际的)
2026年7月31日
研究记录更新
最后更新发布 (实际的)
2026年7月31日
上次提交的符合 QC 标准的更新
2026年7月27日
最后验证
2026年7月1日
更多信息
此信息直接从 clinicaltrials.gov 网站检索，没有任何更改。如果您有任何更改、删除或更新研究详细信息的请求，请联系 register@clinicaltrials.gov. clinicaltrials.gov 上实施更改，我们的网站上也会自动更新.