基于机器学习的初产妇泌乳延迟风险预测模型构建与验证

注册号:

Registration number:

ChiCTR2600126217 

最近更新日期:

Date of Last Refreshed on:

2026-06-05 09:44:06 

注册时间:

Date of Registration:

2026-06-05 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于机器学习的初产妇泌乳延迟风险预测模型构建与验证

Public title:

Construction and Validation of a Machine Learning-Based Risk Prediction Model for Delayed Onset Of Lactogenesis in Primiparas

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于机器学习的初产妇泌乳延迟风险预测模型构建与验证

Scientific title:

Construction and Validation of a Machine Learning-Based Risk Prediction Model for Delayed Onset Of Lactogenesis in Primiparas

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:

罗琳虹 

研究负责人:

罗琳虹 

Applicant:

Luo Linhong 

Study leader:

Luo Linhong 

申请注册联系人电话:

Applicant telephone:

+86 13553398875

研究负责人电话:

Study leader's
telephone:

+86 754 83968888

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:

Luolh1972@163.com

研究负责人电子邮件:

Study leader's E-mail:

luolh1972@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:

中国广东省汕头市金平区长平路57号

研究负责人通讯地址:

中国广东省汕头市金平区长平路57号

Applicant address:

No. 57, Changping Road, Jinping District, Shantou, Guangdong, China

Study leader's address:

No. 57, Changping Road, Jinping District, Shantou, 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:

汕头大学医学院第一附属医院

Applicant's institution:

The First Affiliated Hospital of Shantou University Medical College

研究负责人所在单位:

汕头大学医学院第一附属医院

Affiliation of the Leader:

The First Affiliated Hospital of Shan Tou University Medical 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:

汕大医附一伦审第B-2026-053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:

汕头大学医学院第一附属医院临床科研伦理委员会

Name of the ethic committee:

The Ethics Committee of First Affiliated Hospital of Shantou University Medical College

伦理委员会批准日期:

Date of approved by ethic committee:

2026-03-03 00:00:00

伦理委员会联系人:

林宇洵

Contact Name of the ethic committee:

Lin Yuxun

伦理委员会联系地址:

中国广东省汕头市金平区长平路57号

Contact Address of the ethic committee:

No. 57, Changping Road, Jinping District, Shantou, Guangdong, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 754 88905647

伦理委员会联系人邮箱:

Contact email of the ethic committee:

sdfyllwyh@163.com

研究实施负责(组长)单位:

汕头大学医学院第一附属医院

Primary sponsor:

The First Affiliated Hospital of Shan Tou University Medical College

研究实施负责(组长)单位地址:

中国广东省汕头市金平区长平路57号

Primary sponsor's address:

No. 57, Changping Road, Jinping District, Shantou, Guangdong, China

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

广东

市(区县):

Country:

China

Province:

Guangdong

City:

单位(医院):

汕头大学医学院第一附属医院

具体地址:

中国广东省汕头市金平区长平路57号

Institution
hospital:

The First Affiliated Hospital of Shan Tou University Medical College

Address:

No. 57, Changping Road, Jinping District, Shantou, Guangdong, China

经费或物资来源:

自选课题(自筹)

Source(s) of funding:

Self-selected topic (self-funded)

研究疾病:

无  

Target disease:

N/A

研究疾病代码:

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:

横断面 

Study design:

Cross-sectional 

研究目的:

1.通过横断面研究收集初产妇多维度数据,分析DOLⅡ发生率,并运用LASSO回归筛选DOLⅡ的独立预测变量。 2.基于LASSO回归筛选的预测变量,进行交叉验证和超参数调优,运用5种机器学习算法构建DOLⅡ风险预测模型,并评估模型性能。 3.在数据集上对所构建的模型进行外部验证,从区分度、校准度及临床实用性等方面综合评价模型性能,选出最优模型,对最优的模型做可解释性分析,包括变量重要性排序、SHAP可解释性分析,以明确各个特征对预测结果的贡献,推动其在实际产科环境中的应用。  

Objectives of Study:

Multidimensional data of primiparas were collected through a cross-sectional study to analyze the incidence of stage Ⅱ delayed onset of lactation (DOL Ⅱ). The LASSO regression was used to screen independent predictive factors for DOL Ⅱ. Based on the predictors selected by LASSO regression, cross-validation and hyperparameter optimization were performed. Five machine learning algorithms were adopted to construct risk prediction models for DOL Ⅱ, and the performance of each model was evaluated. External validation of the established models was conducted on the dataset. The model performance was comprehensively evaluated in terms of discrimination, calibration and clinical practicality, and the optimal model was selected. Interpretability analysis of the optimal model was carried out, including variable importance ranking and SHAP analysis, to clarify the contribution of each feature to the prediction results and promote its application in clinical obstetric settings.

药物成份或治疗方案详述:

 

Description for medicine or protocol of treatment in detail:

 

纳入标准:

Inclusion criteria

排除标准:

1.既往乳腺手术史(如缩乳、隆乳)、乳腺组织发育异常、胎盘碎片滞留;
2.研究期间服用影响泌乳的药物,如多潘立酮、溴隐亭等;
3.病情危重、听力障碍、言语沟通等无法配合的产妇;

Exclusion criteria:

1.History of breast surgery (e.g., breast reduction, breast augmentation), abnormal breast tissue development, and retained placental fragments.
2.Use of lactation-affecting medications during the study period, such as domperidone, bromocriptine, etc.
3.Parturients with critical illness, hearing impairment, speech disorders or other conditions resulting in inability to cooperate;

研究实施时间:

Study execute time:

From 2026-06-15 00:00:00 To 2027-05-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-06-15 00:00:00 To 2027-02-01 00:00:00

干预措施:

Interventions:

组别:

建模组

样本量:

601

Group:

Modeling group

Sample size:

干预措施:

干预措施代码:

Intervention:

None

Intervention code:

组别:

验证组

样本量:

150

Group:

Verification group

Sample size:

干预措施:

干预措施代码:

Intervention:

None

Intervention code:

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

广东 

市(区县):

 

Country:

China

Province:

Guangdong

City:

单位(医院):

汕头大学医学院第一附属医院 

单位级别:

三级甲等 

Institution
hospital:

The First Affiliated Hospital of Shan Tou University Medical College

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

泌乳延迟

指标类型:

主要指标

Outcome:

Delayed onset of lactogenesis

Type:

Primary indicator

测量时间点:

产后3天内

测量方法:

泌乳启动将从以下两个方面进行判断:(1)乳房胀满感判断:①乳房无变化,记为1分;②乳房胀满感明显,记为3分;③乳房胀痛不适,记为5分,≥3分为泌乳启动。(2)乳房胀满感评分≥3分,并包含以下任一症状:①乳房饱满;②乳汁供应量明显增加;③乳汁颜色性状改变;④乳房肿胀

Measure time point of outcome:

Within 3 days postpartum

Measure method:

The initiation of lactation was assessed from the following two aspects: (1) Assessment of breast fullness: ① No breast changes, scored 1 point; ② Obvious breast fullness, scored 3 points; ③ Distending pain and discomfort of the breast, scored 5 points. A score of ≥ 3 points was defined as lactation initiation. (2) A breast fullness score of ≥ 3 points combined with any one of the following symptoms: ① Engorged breasts; ② Markedly increased milk supply; ③ Changes in milk color and properties; ④

采集人体标本:

Collecting sample(s)
from participants:

标本中文名:

组织:

Sample Name:

N/A

Tissue:

人体标本去向

其它  

说明

Fate of sample:

0thers  

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 18 years
最大 Max age years

性别:

女性

Gender:

Female

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:

不公开/Private

盲法:

Blinding:

None

是否共享原始数据:

IPD sharing

是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):

试验结束后6个月内上传,resman,网址:http://www.medresman.org.cn/pub/cn/proj/search.aspx

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

Upload within 6 months after trial completion via ResMan: http://www.medresman.org.cn/pub/cn/proj/search.aspx

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:

数据由量表及病例采集,由医院电子采集系统管理

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

Data were collected through scales and medical records and managed by the hospital’s electronic data collection system.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

无/No

注册人:

Name of Registration:

 2026-06-05 09:43:57