ChiCTR2600122017 版本V1.0 版本创建时间2026/04/08 10:07:52 中国临床试验注册中心

审核状态:

Project audit state:

通过审核

Successful

注册号:

Registration number:

ChiCTR2600122017 

最近更新日期:

Date of Last Refreshed on:

2026-04-08 10:07:36 

注册时间:

Date of Registration:

2026-04-08 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

大规模人工智能模型在麻醉前评估中的应用:探讨三大AI模型ChatGPT、Deepseek和Gemini在手术患者术前ASA分级准确性中的表现

Public title:

The Application of Large-scale Artificial Intelligence Models in Pre-anesthetic Assessment: Discussing the Performance of Three Major AI Models, Chatgpt, Deepseek, and Gemini, in the Accuracy of Preoperative ASA Grading for Surgical Patients.

注册题目简写:

English Acronym:

研究课题的正式科学名称:

大规模人工智能模型在麻醉前评估中的应用:探讨三大AI模型ChatGPT、Deepseek和Gemini在手术患者术前ASA分级准确性中的表现

Scientific title:

The Application of Large-scale Artificial Intelligence Models in Pre-anesthetic Assessment: Discussing the Performance of Three Major AI Models, Chatgpt, Deepseek, and Gemini, in the Accuracy of Preoperative ASA Grading for Surgical Patients.

研究课题代号(代码):

Study subject ID:

在二级注册机构或其它机构的注册号:

The registration number of the Partner Registry or other register:

申请注册联系人:

周敏 

研究负责人:

周敏 

Applicant:

Min Zhou 

Study leader:

Min Zhou 

申请注册联系人电话:

Applicant telephone:

+86 182 9746 2557

研究负责人电话:

Study leader's
telephone:

+86 182 9746 2557

申请注册联系人传真 :

Applicant Fax:

研究负责人传真:

Study leader's fax:

申请注册联系人电子邮件:

Applicant E-mail:

bawanglong0318@163.com

研究负责人电子邮件:

Study leader's E-mail:

bawanglong0318@163.com

申请单位网址(自愿提供):

Applicant website(voluntary supply):

研究负责人网址(自愿提供):

Study leader's website(voluntary supply):

申请注册联系人通讯地址:

六安市裕安区磨子潭路73号

研究负责人通讯地址:

六安市裕安区磨子潭路73号

Applicant address:

73, Mozi Tan Road, Yu'an District, Lu'an

Study leader's address:

73, Mozi Tan Road, Yu'an District, Lu'an

申请注册联系人邮政编码:

Applicant postcode:

研究负责人邮政编码:

Study leader's postcode:

申请人所在单位:

皖西卫生职业学院附属医院

Applicant's institution:

The Affiliated Hospital of West Anhui Health Vocational College

研究负责人所在单位:

皖西卫生职业学院附属医院

Affiliation of the Leader:

The Affiliated Hospital of West Anhui Health Vocational College

是否获伦理委员会批准:

Approved by ethic committee:

Yes

伦理委员会批件文号:

Approved No. of ethic committee:

院伦审LAEY-2026-001

伦理委员会批件附件:

Approved file of Ethical Committee:

查看附件View

批准本研究的伦理委员会名称:

皖西卫生职业学院附属医院医学伦理委员会

Name of the ethic committee:

The Medical Ethics Committee of The Affiliated Hospital of West Anhui Health Vocational College

伦理委员会批准日期:

Date of approved by ethic committee:

2026-03-16 00:00:00

伦理委员会联系人:

邵文丽

Contact Name of the ethic committee:

Wenli Shao

伦理委员会联系地址:

六安市裕安区磨子潭路73号

Contact Address of the ethic committee:

73, Mozi Tan Road, Yu'an District, Lu'an

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 137 3301 3022

伦理委员会联系人邮箱:

Contact email of the ethic committee:

研究实施负责(组长)单位:

皖西卫生职业学院附属医院

Primary sponsor:

The Affiliated Hospital of West Anhui Health Vocational College

研究实施负责(组长)单位地址:

六安市裕安区磨子潭路73号

Primary sponsor's address:

73, Mozi Tan Road, Yu'an District, Lu'an

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

安徽

市(区县):

Country:

China

Province:

An Hui

City:

单位(医院):

皖西卫生职业学院附属医院

具体地址:

六安市裕安区磨子潭路73号

Institution
hospital:

The Affiliated Hospital of West Anhui Health Vocational College

Address:

73, Mozi Tan Road, Yu'an District, Lu'an

经费或物资来源:

2025年度六安市科技计划备案项目

Source(s) of funding:

2025 Lu'an City Science and Technology Plan Registered Projects

研究疾病:

需要接受择期手术治疗的各类疾病  

Target disease:

Various diseases/conditions requiring elective surgery

研究疾病代码:

Target disease code:

研究类型:

诊断试验

Study type:

Diagnostic test

研究所处阶段:

回顾性研究 

Study phase:

Retrospective study

研究设计:

诊断试验诊断准确性 

Study design:

Diagnostic test for accuracy 

研究目的:

评估三种AI模型(ChatGPT-4、Deepseek、Gemini)预测ASA分级的准确性  

Objectives of Study:

Evaluation of the Accuracy of Three AI Models (ChatGPT-4, Deepseek, Gemini) in Predicting the ASA Physical Status Classification.

药物成份或治疗方案详述:

将纳入的患者由具有资格的麻醉医生进行常规术前访视评估,将患者住院就诊信息及麻醉医生通过术前访视后所得到的综合信息进行汇总,并进行人工ASA分级,将结果进行记录。同时将所获得的患者信息也通过 Chatgpt 、Deepseek 和 Gemini 大型语言模型对手术患者 ASA 评级, Chatgpt 、Deepseek 和 Gemini 是一种通用人工智能,具备创建特定GPT 模型的能力。当它们在接收到包括患者年龄、性别、身高、体重、吸烟史、循环系统、呼吸系统、肝功能、肾功能、内分泌系统、神经系统状态以及任何异常的实验室和影像学结果,计划手术的详细信息及患 者咨询记录等数据后,提供从1到6的ASA 评分预测,当ASA 评分为V/VI 时,因为AI 无法 观测到病人实际复杂情况,我们排除这种结果。本研究不涉及研究分组,仅需人机结果对比。 

Description for medicine or protocol of treatment in detail:

In this study, all enrolled patients will undergo routine preoperative assessment by qualified anesthesiologists. The patients' hospitalization information and the comprehensive data obtained by anesthesiologists during preoperative evaluations will be compiled, followed by manual ASA classification, with the results recorded accordingly. Simultaneously, the same patient information will be submitted to the large language models—ChatGPT, Deepseek, and Gemini—for ASA classification of surgical patients. ChatGPT, Deepseek, and Gemini are general-purpose artificial intelligence systems capable of creating specific GPT models. Upon receiving data including the patient's age, gender, height, weight, smoking history, circulatory system status, respiratory system status, liver function, kidney function, endocrine system status, neurological system status, any abnormal laboratory and imaging findings, detailed information of the planned surgery, and patient consultation records, these models will provide an ASA score prediction ranging from 1 to 6. Predictions of ASA class V or VI will be excluded, since the AI cannot observe the patient's actual complex condition. This study does not involve research grouping; it solely requires a comparison between human and AI-generated results. 

纳入标准:

需麻醉的ASA 评分为 I 至 IV 级的择期手术患者

Inclusion criteria

Patients scheduled for elective surgery with an ASA score of I to IV requiring anesthesia

排除标准:

1. ASA V 和 VI 级的危症患者; 2. 急诊手术患者; 3. 信息不足的患者。

Exclusion criteria:

1. Critically ill patients with ASA V and VI classifications; 2. Patients requiring emergency surgery; 3. Patients with insufficient information.

研究实施时间:

Study execute time:

From 2026-03-31 00:00:00 To 2026-05-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-04-10 00:00:00 To 2026-05-31 00:00:00

诊断试验:

Diagnostic Tests:

金标准或参考标准(即可准确诊断某疾病的单项方法或多项联合方法,在本研究中用于诊断是否有该病的临床参考标准):

纳入的患者由具有资格的麻醉医生进行常规术前访视评估,将患者住院就诊信息及麻醉医生通过术前访视后所得到的综合信息进行汇总,并进行人工ASA分级,将结果进行记录。

Gold Standard or Reference Standard (The clinical reference standards required to establish the presence or absence of the target condition in the tested population in present study):

In this study, all enrolled patients will undergo routine preoperative assessment by qualified anesthesiologists. The patients' hospitalization information and the comprehensive data obtained by anesthesiologists during preoperative evaluations will be compiled, followed by manual ASA classification, with the results recorded accordingly.

指标试验(即本研究的待评估诊断试验,无论为方法、生物标志物或设备,均请列出名称):

三种AI模型(ChatGPT-4、Deepseek、Gemini)预测ASA分级

Index test:

Three AI Models (ChatGPT-4, Deepseek, Gemini) in Predicting the ASA Physical Status Classification.

目标人群(可以是某种疾病患者或正常人群,详细描述其疾病特征,注意应纳入符合分布特点的全序列病例,具有良好的代表性)

需麻醉的ASA 评分为 I 至 IV 级的择期手术患者

例数:

Sample size:

212

Target condition (The target condition is a particular disease or disease stage that the index test will be intended to identify. Please specify the characteristics in detail; the population should has a complete spectrum and good representative):

Patients scheduled for elective surgery with an ASA score of I to IV requiring anesthesia

容易混淆的疾病人群(即与目标疾病不易区分的一种或多种不同疾病,应避免采用正常人群对照的病例-对照设计):

例数:

Sample size:

0

Population with condition difficult to distinguish from the target condition, the normal population in a case-control study design should be avoid:

None

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

安徽省 

市(区县):

 

Country:

China

Province:

Anhui Province

City:

单位(医院):

皖西卫生职业学院附属医院 

单位级别:

三甲 

Institution
hospital:

The Affiliated Hospital of West Anhui Health Vocational College

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

ChatGPT-4、Deepseek、Gemin三个大语言模型对患者的ASA分级准确率

指标类型:

主要指标

Outcome:

The accuracy rates of ASA classification for patients by three large language models: ChatGPT-4, Deepseek, and Gemin

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

最优模型组合在危重症识别任务中的准确率

指标类型:

次要指标

Outcome:

Accuracy of Optimal Model Portfolio in Critical Condition Identification Task

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

GPT模型将ASA II级病例过度归类为III级的错误率

指标类型:

次要指标

Outcome:

The GPT model exhibited an error rate of overclassifying ASA II cases as ASA III cases.

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

灵敏度

指标类型:

次要指标

Outcome:

Sensitivity

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

特异度

指标类型:

次要指标

Outcome:

Specificity

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

采集人体标本:

Collecting sample(s)
from participants:

标本中文名:

组织:

Sample Name:

None

Tissue:

人体标本去向

使用后销毁  

说明

Fate of sample:

Destruction after use  

Note:

征募研究对象情况:

Recruiting status:

尚未开始

Not yet recruiting

年龄范围:

Participant age:

最小 Min age years
最大 Max age years

性别:

男女均可

Gender:

Both

随机方法(请说明由何人用什么方法产生随机序列):

Randomization Procedure (please state who generates the random number sequence and by what method):

None

是否公开试验完成后的统计结果:

Calculated Results after the Study Completed public access:

公开/Public

盲法:

Blinding:

试验完成后的统计结果(上传文件):

Calculated Results after
the Study Completed(upload file):

是否共享原始数据:

IPD sharing

否No

共享原始数据的方式(说明:请填入公开原始数据日期和方式,如采用网络平台,需填该网络平台名称和网址):

The way of sharing IPD”(include metadata and protocol, If use web-based public database, please provide the url):

none

数据采集和管理(说明:数据采集和管理由两部分组成,一为病例记录表(Case Record Form, CRF),二为电子采集和管理系统(Electronic Data Capture, EDC),如ResMan即为一种基于互联网的EDC:

本研究所有患者信息将以病例记录表进行汇总

Data collection and Management (A standard data collection and management system include a CRF and an electronic data capture:

All patient information in this study will be compiled using a case report form (CRF).

数据与安全监察委员会:

Data and Safety Monitoring Committee:

暂未确定/Not yet

注册人:

Name of Registration:

 2026-04-08 10:07:36