此页面是自动翻译的，不保证翻译的准确性。请参阅英文版对于源文本。

Development of an AI-Agent for Urological Disease Diagnosis and Treatment

2026年7月18日更新者：Xu Kewei、Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University

Development of an AI-Agent for Diagnosis and Treatment of Urological Diseases

Urological diseases such as urinary stones, prostate cancer, and bladder cancer are very common and often require highly specialized diagnosis and treatment. Today, the quality of care can vary between doctors, and there are not enough urology specialists to meet patient demand. Artificial intelligence (AI) may help doctors make faster and more consistent decisions.

This study aims to develop and test an AI-powered assistant called "UroAgent" that supports doctors in diagnosing and treating urological diseases. UroAgent is built on a large language model trained specifically for urology and is connected to tools that help it retrieve medical knowledge and analyze images. To build and test UroAgent, the research team will use 1,500 past patient records from 2010-2025 and collect 500 new patient cases for validation, for a total of 2,000 cases. This is an observational study: no patient's medical treatment will be changed because of it. The goal is to create a reliable AI tool that helps improve urological care for patients.

研究概览

地位

招聘中

条件

详细说明

This study protocol describes an observational study aiming to develop and validate UroAgent, an artificial-intelligence agent for the diagnosis and treatment of urological diseases. A total of 2,000 urological disease cases will be collected, comprising 1,500 retrospective cases recorded at the center between 2010 and 2025 for model development and 500 prospectively enrolled cases for independent performance validation. The primary evaluation is the concordance between UroAgent's diagnostic and treatment recommendations and the reference standards established by senior urologists, assessed through diagnostic accuracy, recommendation appropriateness, completeness, and safety; secondary evaluations include the agent's performance across disease subtypes (urinary stones, prostate cancer, bladder cancer) and its image-interpretation capability. All records will undergo de-identification, and the study will adhere to rigorous ethical standards and a pre-specified statistical analysis plan to provide robust evidence for the clinical application of this urology-specific AI agent.

研究类型

观察性的

注册 (估计的)

2000

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：Mingzhou Dai
电话号码：+86 19924684262
邮箱：daimzh3@mail2.sysu.edu.cn

学习地点

中国
- Guangdong
  - Guangzhou、Guangdong、中国、510000
    - 招聘中
    - Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University
    - 接触：
      
      Mingzhou Dai
      
      电话号码：+86 19924684262
      
      邮箱：daimzh3@mail2.sysu.edu.cn
  - Shantou、Guangdong、中国、516600
    - 招聘中
    - Shenshan Medical Center, Sun Yat-sen Memorial Hospital, Sun Yat-sen University
    - 接触：
      
      Zhuang Tang
      
      电话号码：+86 13666144867
      
      邮箱：tangzh23@mail.sysu.edu.cn
- Jiangxi
  - Ganzhou、Jiangxi、中国、341000
    - 招聘中
    - Ganzhou People's Hospital
    - 接触：
      
      Cong Lai
      
      电话号码：+86 19872753573
      
      邮箱：laic@mail2.sysu.edu.cn

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

孩子
成人
年长者

接受健康志愿者

不

取样方法

非概率样本

研究人群

The study population comprises patients diagnosed with urological diseases at Sun Yat-sen Memorial Hospital, including urinary stones, prostate cancer, bladder cancer, and other urological conditions. A total of 2,000 participants (cases) will be included: 1,500 retrospective cases with records from 2010 to 2025, and 500 prospective, consecutively enrolled cases. Both sexes are eligible, and the population is predominantly adult (the protocol does not specify an age cutoff; an age criterion of ≥18 years is recommended for registry entry, per the note in section 16). All included participants have complete clinical information, imaging data, and surgical video available for model development and validation. Records are de-identified prior to use. The population reflects the real-world case mix of a tertiary urology center.

描述

Inclusion Criteria:

Diagnosed with a urological disease (e.g., urinary stones, prostate cancer, bladder cancer, and other urological conditions).
Availability of complete clinical information, imaging data, and surgical video required for model development and validation.

Exclusion Criteria:

1. Missing clinical information, imaging data, or surgical video.

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

团体/队列数

队列和干预

团体/队列
Urological Disease Cohort The cohort consists of patients diagnosed with urological diseases-including urinary stones, prostate cancer, and bladder cancer-at Sun Yat-sen Memorial Hospital. A total of 2,000 cases are included: 1,500 retrospective cases recorded between 2010 and 2025 (used for model development) and 500 prospectively and consecutively enrolled cases (used for independent validation); all records are de-identified. The intervention (technology) of interest is "UroAgent," an artificial-intelligence diagnostic-and-treatment agent built on a urology-specialized large language model with integrated tool modules (knowledge retrieval, image interpretation). For each case, UroAgent's diagnostic and treatment recommendations are generated and compared with the analyses provided by human urology specialists, to evaluate the agent's performance-diagnostic accuracy, recommendation appropriateness, completeness, and safety-against expert judgment.

团体/队列

Urological Disease Cohort

The cohort consists of patients diagnosed with urological diseases-including urinary stones, prostate cancer, and bladder cancer-at Sun Yat-sen Memorial Hospital. A total of 2,000 cases are included: 1,500 retrospective cases recorded between 2010 and 2025 (used for model development) and 500 prospectively and consecutively enrolled cases (used for independent validation); all records are de-identified. The intervention (technology) of interest is "UroAgent," an artificial-intelligence diagnostic-and-treatment agent built on a urology-specialized large language model with integrated tool modules (knowledge retrieval, image interpretation). For each case, UroAgent's diagnostic and treatment recommendations are generated and compared with the analyses provided by human urology specialists, to evaluate the agent's performance-diagnostic accuracy, recommendation appropriateness, completeness, and safety-against expert judgment.

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
Diagnostic Accuracy of UroAgent 大体时间：Retrospective cases - at data extraction (single time point); Prospective cases - at enrollment (single time point); no longitudinal follow-up.	The primary outcome is UroAgent's diagnostic accuracy, measured as the F1 score of its leading diagnosis against the reference-standard final diagnosis. The reference standard is established by senior urologists from pathology, imaging, and clinical course. F1 = 2 × Precision × Recall / (Precision + Recall), computed per case and aggregated as macro-F1 across the 2,000-case cohort (1,500 retrospective + 500 prospective). Unit of measure: F1 score (range 0-1).	Retrospective cases - at data extraction (single time point); Prospective cases - at enrollment (single time point); no longitudinal follow-up.

次要结果测量

结果测量	措施说明	大体时间
Expert Subjective Accuracy Rating 大体时间：Retrospective cases - at data extraction (single time point); Prospective cases - at enrollment (single time point); no longitudinal follow-up.	Independent urologists rate the accuracy of UroAgent's diagnosis on a 5-point Likert scale (1 = completely inaccurate, 5 = completely accurate), blinded to model identity. Reported as the mean rating and the percentage of cases rated ≥ 4; disagreements resolved by a third urologist. Unit of measure: mean rating (1-5) and percentage of cases rated accurate (%).	Retrospective cases - at data extraction (single time point); Prospective cases - at enrollment (single time point); no longitudinal follow-up.
Treatment Recommendation Appropriateness of UroAgent 大体时间：Retrospective cases - at data extraction (single time point); Prospective cases - at enrollment (single time point); no longitudinal follow-up.	The proportion of cases in which UroAgent's management recommendation is rated appropriate. Two independent urologists rate each recommendation on a 5-point Likert appropriateness scale (1 = completely inappropriate, 5 = completely appropriate), blinded; "appropriate" defined as Likert ≥ 4; disagreement resolved by a third urologist. Unit of measure: percentage of cases (%) rated appropriate.	Retrospective cases - at data extraction (single time point); Prospective cases - at enrollment (single time point); no longitudinal follow-up.
Clinical Safety of UroAgent Recommendations 大体时间：Retrospective cases - at data extraction (single time point); Prospective cases - at enrollment (single time point); no longitudinal follow-up.	The rate of clinically unsafe recommendations. Each case is reviewed by senior urologists using a safety rubric and flagged (binary per case) for any contraindicated, erroneous, or potentially harmful recommendation. Unit of measure: percentage of cases (%) with ≥ 1 unsafe recommendation.	Retrospective cases - at data extraction (single time point); Prospective cases - at enrollment (single time point); no longitudinal follow-up.
Concordance and Non-Inferiority of UroAgent versus Clinician Diagnoses 大体时间：Retrospective cases - at data extraction (single time point); Prospective cases - at enrollment (single time point); no longitudinal follow-up.	On the same cases, UroAgent's diagnoses are compared with those of practicing urologists. Reported as the agreement rate (%) between UroAgent and clinician diagnoses, plus the diagnostic-accuracy difference in percentage points (pp); Cohen's κ reported as a supplementary statistic. Both are assessed against the reference-standard final diagnosis. Unit of measure: agreement rate (%) and accuracy difference (pp).	Retrospective cases - at data extraction (single time point); Prospective cases - at enrollment (single time point); no longitudinal follow-up.

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。

赞助

Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University

合作者

Shenshan Medical Center, Memorial Hospital of Sun Yat-sen University

Ganzhou City People's Hospital

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 (实际的)

2025年4月1日

初级完成 (估计的)

2026年12月31日

研究完成 (估计的)

2027年6月30日

研究注册日期

首次提交

2026年7月12日

首先提交符合 QC 标准的

2026年7月18日

首次发布 (实际的)

2026年7月23日

研究记录更新

最后更新发布 (实际的)