|
审核状态: Project audit state: |
通过审核 Successful |
|
注册号: Registration number: |
ChiCTR2400089353 |
|
最近更新日期: Date of Last Refreshed on: |
2024-09-06 10:37:52 |
|
注册时间: Date of Registration: |
2024-09-06 00:00:00 |
|
注册号状态: |
补注册 |
|
Registration Status: |
Retrospective registration |
|
注册题目: |
基于RNN-LSTM人工智能算法构建2型糖尿病胰岛素泵短期强化治疗剂量预测模型 |
|
Public title: |
Construction of insulin dose prediction model based on RNN-LSTM in patients with type 2 diabetes using short-term intensive insulin pump treatment. |
|
注册题目简写: |
|
|
English Acronym: |
|
|
研究课题的正式科学名称: |
基于RNN-LSTM人工智能算法构建2型糖尿病胰岛素泵短期强化治疗剂量预测模型 |
|
Scientific title: |
Construction of insulin dose prediction model based on RNN-LSTM in patients with type 2 diabetes using short-term intensive insulin pump treatment. |
|
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: |
张希恬 |
研究负责人: |
黄知敏 |
|
Applicant: |
Zhang Xitian |
Study leader: |
Huang Zhimin |
|
申请注册联系人电话: Applicant telephone: |
+86 178 1956 8635 |
研究负责人电话: Study leader's telephone: |
+86 139 2505 7613 |
|
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: |
zhangxt87@mail2.sysu.edu.cn |
研究负责人电子邮件: Study leader's E-mail: |
hzhim@mail.sysu.edu.cn |
|
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: |
广东省广州市越秀区中山二路58号 |
研究负责人通讯地址: |
广东省广州市越秀区中山二路58号 |
|
Applicant address: |
58 Zhongshan Er Road, Yuexiu District, Guangzhou, Guangdong, China |
Study leader's address: |
58 Zhongshan Er Road, Yuexiu District, Guangzhou, Guangdong, China |
|
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: |
中山大学附属第一医院 |
||
|
Applicant's institution: |
The First Affiliated Hospital of Sun Yat-sen University |
||
|
研究负责人所在单位: |
中山大学附属第一医院 |
||
|
Affiliation of the Leader: |
The First Affiliated Hospital of Sun Yat-sen University |
||
|
是否获伦理委员会批准: |
是/Yes |
||
|
Approved by ethic committee: |
Yes |
||
|
伦理委员会批件文号: Approved No. of ethic committee: |
伦审临[2023]220 号 |
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: |
中山大学附属第一医院临床科研和实验动物伦理委员会 |
||
|
Name of the ethic committee: |
IEC for Clinical Research and Animal Trials of the First Affiliated Hospital of Sun Yat-sen University |
||
|
伦理委员会批准日期: Date of approved by ethic committee: |
2023-04-26 00:00:00 |
||
|
伦理委员会联系人: |
颜楚荣 |
||
|
Contact Name of the ethic committee: |
Yan Churong |
||
|
伦理委员会联系地址: |
广东省广州市越秀区中山二路58号 |
||
|
Contact Address of the ethic committee: |
58 Zhongshan Er Road, Yuexiu District, Guangzhou, Guangdong, China |
||
|
伦理委员会联系人电话: Contact phone of the ethic committee: |
+86 20 8733 4871 |
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: |
中山大学附属第一医院 |
||||||||||||||||||||||
|
Primary sponsor: |
The First Affiliated Hospital of Sun Yat-sen University |
||||||||||||||||||||||
|
研究实施负责(组长)单位地址: |
广东省广州市越秀区中山二路58号 |
||||||||||||||||||||||
|
Primary sponsor's address: |
58 Zhongshan Er Road, Yuexiu District, Guangzhou, Guangdong, China |
||||||||||||||||||||||
|
试验主办单位(项目批准或申办者): Secondary sponsor: |
|
||||||||||||||||||||||
|
经费或物资来源: |
NSFC (82070918) |
||||||||||||||||||||||
|
Source(s) of funding: |
NSFC (82070918) |
||||||||||||||||||||||
|
Target disease: |
Type 2 Dibetes |
||||||||||||||||||||||
|
Target disease code: |
|
||||||||||||||||||||||
|
研究类型: |
观察性研究 |
||||||||||||||||||||||
|
Study type: |
Observational study |
||||||||||||||||||||||
|
研究所处阶段: |
其它 | ||||||||||||||||||||||
|
Study phase: |
N/A |
||||||||||||||||||||||
|
研究设计: |
连续入组 |
||||||||||||||||||||||
|
Study design: |
Sequential |
||||||||||||||||||||||
|
研究目的: |
本课题拟利用我科近20年接受胰岛素泵短期强化治疗的所有2型糖尿病患者数据库,通过循环神经网络-长短期记忆(RNN-LSTM)人工智能算法,对强化治疗期间患者的毛细血管血糖(CBG)与胰岛素剂量数据进行学习和建立预测模型,通过不断迭代训练、验证、测试以优化模型,将胰岛素泵短期强化治疗中医生的主观经验转化为客观、标准化、易操作的计算机软件和手机应用程序(App)。 |
||||||||||||||||||||||
|
Objectives of Study: |
The purpose of this project is to retrieve the database of all the patients with type 2 diabetes mellitus who have received short-term intensive treatment with insulin pump in the past 20 years in our department. Capillary blood glucose and insulin dose adjustment prescription data on each day during short-term intensive insulin pump treatment for every patient are to be collected, and assign to machine learning. Recurrent neural network-long short term memory (RNN-LSTM) algorithm is to be employed to construct the learning model. Feature automatic extraction system and valid memory will be formed by the model. By numerous iteration training, repeated validation and testing, the model will be optimized to predict insulin dosage (including basal rate and premeal boluses) at any given blood glucose level. |
||||||||||||||||||||||
|
药物成份或治疗方案详述: |
为利于模型建立的准确性及模型优化,研究将尽可能纳入更多同质的病例 |
||||||||||||||||||||||
|
Description for medicine or protocol of treatment in detail: |
To improve the accuracy and optimization of the model, the study will include as more homogeneous cases as possible |
||||||||||||||||||||||
|
纳入标准: |
2001年~2020年所有在中山大学附属第一医院内分泌科住院2型糖尿病患者病历, 住院期间接受胰岛素泵短期强化治疗治疗,包括初诊断患者及非初诊断患者。 |
||||||||||||||||||||||
|
Inclusion criteria |
Case records of all the patients with type 2 diabetes mellitus hospitalized between year 2001 and 2020 in the Department of Endocrinology, First Affiliated Hospital of Sun Yat-sen University were retrieved. Patients who received short-term intensive insulin pump treatment were included in the study, including those with newly diagnosed type 2 diabetic patients and non-newly diagnosed type 2 diabetic patients. |
||||||||||||||||||||||
|
排除标准: |
1. 血糖或医嘱数据缺失严重; 2. 非带泵强化治疗患者; 3. 严重并发或及合并症伴器官功能衰竭者,研究者认为不适宜纳入研究。 |
||||||||||||||||||||||
|
Exclusion criteria: |
1. Missing data on CBG or prescription that compromises analysis. 2. Type 2 diabetic patients received treatment other than short-term intensive insulin pump treatment during hospital stay. 3. Severe complications or comorbidities with severe organ failure that the investigator dictates not suitable for the study. |
||||||||||||||||||||||
|
研究实施时间: Study execute time: |
从 From 2023-04-27 00:00:00至 To 2025-12-31 00:00:00 |
征募观察对象时间: Recruiting time: |
从From 2023-04-27 00:00:00 至 To 2024-08-31 00:00:00 |
|
干预措施: Interventions: |
|
|
研究实施地点: Countries of recruitment and research settings: |
|
||||||||||||||||||||||||||||
|
测量指标: Outcomes: |
|
|
采集人体标本:
Collecting sample(s)
|
|
|
征募研究对象情况: Recruiting status: |
结束 /Completed |
年龄范围: Participant age: |
|
||||||
|
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): |
无 |
||||||||
|
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: |
无 |
|
Blinding: |
None |
|
试验完成后的统计结果(上传文件): |
|
|
Calculated Results after
|
|
|
是否共享原始数据: IPD sharing |
Yes |
|
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): |
ResMan, http://www.medresman.org.cn/ |
|
The way of sharing IPD”(include metadata and protocol, If use web-based public database, please provide the url): |
ResMan, http://www.medresman.org.cn/ |
|
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: |
中山大学附属第一医院自 2013 年开始实现全面电子病历管理,因此 2013年以前的病历数据需要通过缩微病历系统获得,通过人工录入方式,将所需数据录入在线电子病历数据系统中。2013 年以后电子病历系统数据可通过我院信息科直接导出,进行数据分类汇总后再导入电子病历数据系统中。 |
|
Data collection and Management (A standard data collection and management system include a CRF and an electronic data capture: |
Electronic medical records has been implemented in our hospital since year 2013. Therefore, the medical records before 2013 need to be obtained from the scanned version of the medical records and input manually via the online electronic medical records data system that we had constructed and copyrighted. The case records obtained after 2013 are to retrieved directly, and the data will be sorted and aggregated before being input to the electronic medical records system. |
|
数据与安全监察委员会: Data and Safety Monitoring Committee: |
暂未确定/Not yet |