|
审核状态: Project audit state: |
通过审核 Successful |
|
注册号: Registration number: |
ChiCTR2600126739 |
|
最近更新日期: Date of Last Refreshed on: |
2026-06-15 14:11:55 |
|
注册时间: Date of Registration: |
2026-06-15 00:00:00 |
|
注册号状态: |
预注册 |
|
Registration Status: |
Prospective registration |
|
注册题目: |
基于机器学习的骨质疏松脆性骨折预测模型的研究 |
|
Public title: |
Research on osteoporotic fragility fracture prediction model based on machine learning |
|
注册题目简写: |
|
|
English Acronym: |
|
|
研究课题的正式科学名称: |
基于机器学习的骨质疏松脆性骨折预测模型的研究 |
|
Scientific title: |
Research on osteoporotic fragility fracture prediction model based on machine learning |
|
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: |
司泽兵 |
研究负责人: |
司泽兵 |
|
Applicant: |
Si Zebing |
Study leader: |
Si Zebing |
|
申请注册联系人电话: Applicant telephone: |
+86 751 6913420 |
研究负责人电话: Study leader's telephone: |
+86 751 6913542 |
|
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: |
szb520zd@163.com |
研究负责人电子邮件: Study leader's E-mail: |
szb520zd@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: |
广东省韶关市武江区惠民南路133号 |
研究负责人通讯地址: |
广东省韶关市武江区惠民南路133号 |
|
Applicant address: |
No. 133, Huimin South Road, Wujiang District, Shaoguan City, Guangdong Province |
Study leader's address: |
133 Huimin South Road, Wujiang District, Shaoguan City, Guangdong Province |
|
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: |
粤北人民医院 |
||
|
Applicant's institution: |
Yuebei People's Hospital |
||
|
研究负责人所在单位: |
粤北人民医院 |
||
|
Affiliation of the Leader: |
Yuebei People’s Hospital |
||
|
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: |
YBSKY-2026-078-001 |
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: |
粤北人民医院医学伦理委员会 |
||
|
Name of the ethic committee: |
MEC, Yue Bei People's Hospital |
||
|
伦理委员会批准日期: Date of approved by ethic committee: |
2026-04-24 00:00:00 |
||
|
伦理委员会联系人: |
张登 |
||
|
Contact Name of the ethic committee: |
Zhang Deng |
||
|
伦理委员会联系地址: |
广东省韶关市武江区惠民南路133号 |
||
|
Contact Address of the ethic committee: |
133 Huimin South Road, Wujiang District, Shaoguan City, Guangdong Province |
||
|
伦理委员会联系人电话: Contact phone of the ethic committee: |
+86 751 6913198 |
伦理委员会联系人邮箱: Contact email of the ethic committee: |
345338517@qq.com |
|
研究实施负责(组长)单位: |
粤北人民医院 |
||||||||||||||||||||||
|
Primary sponsor: |
Yuebei People’s Hospital |
||||||||||||||||||||||
|
研究实施负责(组长)单位地址: |
广东省韶关市武江区惠民南路133号 |
||||||||||||||||||||||
|
Primary sponsor's address: |
133 Huimin South Road, Wujiang District, Shaoguan City, Guangdong Province |
||||||||||||||||||||||
|
试验主办单位(项目批准或申办者): Secondary sponsor: |
|
||||||||||||||||||||||
|
经费或物资来源: |
自选课题(自筹) |
||||||||||||||||||||||
|
Source(s) of funding: |
Self-selected topic (self-financed) |
||||||||||||||||||||||
|
Target disease: |
Osteoporotic fragility fracture |
||||||||||||||||||||||
|
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: |
主要目的:构建与优化骨质疏松性脆性骨折预测的机器学习模型:基于本中心收集的、具有明确低能量损伤史的住院患者的临床真实世界数据,分别构建支持向量机(SVM)、随机森林(Random Forest)、XGBoost、LightGBM及CatBoost等多种机器学习预测模型。通过对模型参数进行优化与训练,旨在建立一个能够有效预测此类患者发生骨质疏松性骨折(结局变量:根据临床影像学诊断定义的二分类变量,骨折=1,非骨折=0)风险的最优模型。次要目的:筛选关键预测特征:应用特征选择算法(如SelectKBest),从收集的基线特征(如年龄、性别、身高、体重)、生化指标(如红细胞分布宽度(RDW-SD)、单核细胞百分比等)及骨密度测量值(腰椎T值、髋部T值)中,识别并量化对低能量损伤后骨折结局最具预测价值的关键临床变量。 |
||||||||||||||||||||||
|
Objectives of Study: |
Main Objective: Constructing and optimizing a machine learning model for predicting osteoporotic fragility fractures: Based on the clinical real-world data collected from inpatients with a clear history of low-energy injury in our center, we will construct various machine learning prediction models such as Support Vector Machine (SVM), Random Forest, XGBoost, LightGBM, and CatBoost. Through optimizing and training the model parameters, we aim to establish an optimal model that can effectively predict the risk of osteoporotic fractures (outcome variable: a binary variable defined based on clinical imaging diagnosis, with fracture=1 and non-fracture=0) in such patients. Secondary Objective: Screening key predictive features: Using feature selection algorithms (such as SelectKBest), we will identify and quantify the key clinical variables with the most predictive value for fracture outcomes after low-energy injury from the collected baseline characteristics (such as age, gender, height, weight), biochemical indicators (such as red blood cell distribution width (RDW-SD), monocyte percentage, etc.), and bone density measurements (lumbar T-score, hip T-score). |
||||||||||||||||||||||
|
药物成份或治疗方案详述: |
|
||||||||||||||||||||||
|
Description for medicine or protocol of treatment in detail: |
|
||||||||||||||||||||||
|
纳入标准: |
1.住院期间完成腰椎及髋部骨密度检测,明确诊断为骨质疏松症者; 2.有明确低能量损伤暴露史; 3.临床资料(身高、体重、性别、年龄)、相关生化检查(红细胞分布宽度 (SD)、单核细胞百分比等)及骨密度数据完整度≥70%(符合数据清洗要求); |
||||||||||||||||||||||
|
Inclusion criteria |
1. Patients who have completed lumbar and hip bone density testing during hospitalization and have been diagnosed with osteoporosis; 2. Patients with a clear history of low-energy injury exposure; 3. Patients with complete clinical data (height, weight, gender, age), relevant biochemical tests (such as red blood cell distribution width (SD), monocyte percentage), and bone density data with a completeness rate of >=70% (meeting data cleaning requirements); |
||||||||||||||||||||||
|
排除标准: |
1. 骨折类型排除(非脆性骨折) 高能量创伤骨折:车祸、高处坠落、重物砸伤等导致的骨折 病理性骨折:骨肿瘤、骨转移癌、多发性骨髓瘤、畸形性骨炎(Paget 病)、骨结核等引发 继发性骨质疏松骨折:长期激素治疗(≥3 个月)、甲状旁腺功能亢进、库欣综合征、慢性肾病 / 肝病、类风湿关节炎等明确继发因素; 2. 基础疾病与状态排除 严重心、肺、肝、肾功能衰竭,恶性肿瘤晚期,预期生存期<12 个月 精神疾病、认知障碍、长期卧床 / 瘫痪; 3. 数据与研究可行性排除 临床资料严重缺失(核心变量:年龄、性别、骨密度、骨折史、关键用药缺失) 随访失联、数据造假 / 异常值无法校正 同时参与其他干扰本研究的临床干预试验; |
||||||||||||||||||||||
|
Exclusion criteria: |
1. Exclusion of fracture types (non-fragile fractures) High-energy trauma fractures: fractures caused by car accidents, falls from heights, heavy object injuries, etc. Pathological fractures: secondary osteoporosis caused by bone tumors, metastatic cancer of the bone, multiple myeloma, Paget's disease, bone tuberculosis, etc. Fragility Fracture Secondary to Osteoporosis: Fractures due to long-term hormone therapy (>=3 months), hyperparathyroidism, Cushing's syndrome, chronic kidney/liver disease, rheumatoid arthritis, etc. with clear secondary factors. 2. Exclusion of underlying diseases and conditions Severe heart, lung, liver, and kidney failure, advanced malignant tumors, expected survival <12 months, mental illness, cognitive impairment, long-term bedridden/paralysis. 3. Data and study feasibility Exclusion of clinical data with severe missingness (core variables: age, gender, bone density, fracture history, missing key medications), loss to follow-up, data falsification/outliers that cannot be corrected, and participation in other clinical intervention trials that interfere with this study; |
||||||||||||||||||||||
|
研究实施时间: Study execute time: |
从 From 2026-06-15 00:00:00至 To 2026-06-30 00:00:00 |
征募观察对象时间: Recruiting time: |
从From 2026-06-15 00:00:00 至 To 2026-06-30 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: |
尚未开始 Not yet recruiting |
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: |
不公开/Private |
|
盲法: |
无 |
|
Blinding: |
None |
|
是否共享原始数据: IPD sharing |
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): |
否 |
|
The way of sharing IPD”(include metadata and protocol, If use web-based public database, please provide the url): |
no |
|
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: |
EDC |
|
Data collection and Management (A standard data collection and management system include a CRF and an electronic data capture: |
EDC |
|
数据与安全监察委员会: Data and Safety Monitoring Committee: |
无/No |