理解囊性纤维化严重急性加重中的炎症、感染与干预

该数据集来自 clinicaltrials.gov,聚焦囊性纤维化(CF)及其肺部急性加重,研究炎症、感染与干预。研究对象为在英国参与中心接受照护的囊性纤维化患者,仅纳入未来 24 个月内被认为存在严重急性加重风险者,计划在 6 个中心招募最多 300 名参与者

Alexander HorsleyAlexander Horsley
clinicaltrials
浏览 2
其他预测Cystic Fibrosis (CF)Cystic Fibrosis Pulmonary Exacerbation
Understanding Inflammation, InFection and Interventions in Severe Exacerbations of Cystic Fibrosis

基本信息

模态
其他
任务类型
预测
创建/更新时间
2026-10-12

资源简介

理解囊性纤维化严重急性加重中的炎症、感染与干预

该数据集来自 clinicaltrials.gov,聚焦囊性纤维化(CF)及其肺部急性加重,研究炎症、感染与干预。研究对象为在英国参与中心接受照护的囊性纤维化患者,仅纳入未来 24 个月内被认为存在严重急性加重风险者,计划在 6 个中心招募最多 300 名参与者。数据可用于分析急性加重的风险因素、炎症与感染相关指标及干预效果,支持对严重急性加重的预测与临床研究(来源 clinicaltrials.gov)。

【数据内容】

源站描述(机器翻译,仅供参考):条件:囊性纤维化(CF)、囊性纤维化肺部急性加重。参与者将由英国 CF 中心照护范围内的 staff 招募。初步讨论将在常规门诊复查、电话咨询或住院期间进行。知情同意将在任何其他程序之前完成。研究者将提供选项,允许将 CF-Tracker 研究的基线稳定期访视重新用作 UNIFIED-CF 研究的稳定期访视。对此的同意在 UNIFIED 中专门获取,研究者已将其添加为一个选项,参与者可以选择重复该访视。参与者将是在英国参与中心接受照护的囊性纤维化患者。该研究将仅纳入那些被认为在未来 24 个月内存在严重急性加重风险的人。将在 6 个中心招募最多 300 名参与者(expecte

【主题与分类】

主题标签:Cystic Fibrosis (CF)、Cystic Fibrosis Pulmonary Exacerbation。本站分类:呼吸系统疾病。

【获取与许可】

源站页面:https://clinicaltrials.gov/study/NCT07484607

官方服务

专家保障全链路合规授权与标注交付

陕川双基地 × 超十家三甲医院直连

从合规授权、采集治理、专业标注到数据集交付,我们提供全链路闭环服务,让高质量临床数据即拿即用。

⚡️ 需要原始数据或标注支持?联系我们获取定制方案。

帮我联系

下载信息

注册下载

需要注册 Kaggle 账号并登录后下载,适合需要跟踪下载记录和使用 API 的用户。

暂未开放

公开下载

无需注册即可直接获取公开样本或文档,适合快速预览和评估数据集质量。

免登录

当前数据集主要来源为 Kaggle 公开托管,完整影像包建议通过原始链接或 Kaggle API 获取。

免费样本无法满足模型训练要求?千方提供经三甲医院脱敏、带病理回证与专家标注的商业级专病数据集。

使用方式

数据集获取

源站:https://clinicaltrials.gov/study/NCT07484607

标准获取流程:

  1. 访问源站链接,注册/登录账号;
  2. 进入数据集详情页,按页面指引申请权限或直接下载;
  3. 部分平台提供 SDK,例如:
    • OpenDataLab: pip install openxlab 后 openxlab.dataset.get(...)
    • ModelScope: pip install modelscope 后 modelscope download
    • 天池: 登录后页面提供直链下载
      以源站「数据下载/使用文档」页面为准。

数据说明

Conditions: Cystic Fibrosis (CF), Cystic Fibrosis Pulmonary Exacerbation. Participants will be recruited by staff within the care of UK CF centres. Initial discussions will occur either during routine outpatient reviews, telephone consultations or during admissions. Consent will take place prior to any other procedures. The investigators will provide the option of re-using baseline stable visits from the CF-Tracker study as stable visits for the UNIFIED-CF study. Consent to do this is specifically taken in UNIFIED, the investigators have added this as an option, and participants can opt to repeat the visit. Participants will be people living with cystic fibrosis being cared for at a participating centre in the UK. The study will enrol only those who are considered to be at risk for severe exacerbation in the next 24 months. Up to 300 participants will be recruited across 6 sites (expected number needed to get 125 exacerbations = 200). Participants will be assessed during a period of clinical stability. Participants taking part in another hub study (CF-Tracker, IRAS: 338539) where the same data and samples are being collected will not need to repeat this visit and will be given the option of re-using the outcomes from the previous visit, or participants can also opt to repeat the visit. If a participant has had a stable baseline visit but has not undergone any eligible CF exacerbations, they will be monitored for two years. They will be invited to a second stable baseline visit to repeat the same measurements after 12 months (range 10-14 months). If participants are admitted to one of the participating CF units for treatment of a pulmonary exacerbation, they will be eligible to take part in the Exacerbation Treatment arm of the UNIFIED study and will be monitored during their admission for up to a maximum of 17 days. In this arm, participants will undergo repeated assessments at pre-specified timepoints before and during their treatment at Pre-IV antibiotic baseline, Day 3 (range = day 2-4), Day 7 (range = day 6-8), Day 10 (range = day 9-1

数据加载示例(图像类)

from PIL import Image
import glob, os

files = (glob.glob(os.path.join(path, "**", "*.png"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.jpg"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.tif"), recursive=True))
print("图像文件数:", len(files))
img = Image.open(files[0]); print("尺寸/模式:", img.size, img.mode)

# torchvision Dataset 方式:
# from torchvision import datasets
# ds = datasets.ImageFolder(path)  # 要求 子目录=类别

目录组织与标注格式以源站说明和下载后实际文件为准。

需要用于商业化训练或医疗器械注册(NMPA/FDA)?

公开数据往往缺乏完整的病理回证与专家标注。千方医数集依托陕川双基地与超十家三甲医院直连,提供完全合规、去标识化、支持注册级质控的专病数据集交易服务。