左心室辅助装置植入学习曲线数据集
低容量中心LVAD植入学习曲线数据集,包含51例患者临床数据,用于分析手术例数与预后的关系。

基本信息
资源简介
左心室辅助装置植入学习曲线数据集
【一句话概览】
本数据集是 figshare 公开的结构化表格数据集,收录 9 个文件、合计 3.49 MB,主题涵盖 Postoperative Care,可用于统计建模、特征工程与队列分析,CC BY 4.0 许可开放获取。
【数据集背景】
本数据集源站标题为《Learning Curve in Left Ventricular Assist Device Implantation: Low Volumes Do Not Equate Bad Outcomes》。配套论文《Learning Curve in Left Ventricular Assist Device Implantation: Low Volumes Do Not Equate Bad Outcomes》发表于 Brazilian Journal of Cardiovascular Surgery(2022),DOI:10.21470/1678-9741-2021-0498。源站首次发布:2022-11-15。
【数据内容】
源站原始描述:ABSTRACT Introduction: Most implantations of left ventricular assist devices (LVAD) are performed in low-volume centers. This study aimed to evaluate the procedural learning curve of HeartMate II (HM2) implantations by comparing outcomes between two time periods in a low-volume center. Methods: All 51 consecutive patients undergoing HM2 implantation between January 2009 and December 2017 were reviewed and allocated into 2 groups: early-era group (from 2009 to 2014; n=25) and late-era group (from…
【数据结构与技术规格】
文件数 9 个,合计 3.49 MB。数据集 DOI:10.6084/m9.figshare.21557075.v1。
【主题与分类】
源站学科分类:Cardiology、Surgery。主题标签:Postoperative Care。
【适用方向】
结构化表格数据可直接用于统计建模、特征工程与队列分析。
【获取与许可】
源站页面:https://scielo.figshare.com/articles/dataset/Learning_Curve_in_Left_Ventricular_Assist_Device_Implantation_Low_Volumes_Do_Not_Equate_Bad_Outcomes/21557075
使用许可:CC BY 4.0(https://creativecommons.org/licenses/by/4.0/)。
规范引用:Hébert, Mélanie; Noly, Pierre-Emmanuel; Lamarche, Yoan; Dagher, Olina; Bouhout, Ismail; Hage-Moussa, Elie; et al. (2022). Learning Curve in Left Ventricular Assist Device Implantation: Low Volumes Do Not Equate Bad Outcomes. SciELO journals. Dataset
【使用注意】
· 源站最后修改于 2023-06-02,引用时请注意版本时效。
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。
免登录有偿下载
公开数据集受托下载与技术交付服务。
提供高速下载与技术交付服务(收技术服务费,非数据销售)
暂未开放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。
使用方式
数据集获取(Figshare)
- 源站标题:Learning Curve in Left Ventricular Assist Device Implantation: Low Volumes Do Not Equate Bad Outcomes
- DOI:10.6084/m9.figshare.21557075.v1
- 发布日期:2022-11-15
- 文件数:9 个
- 文件总体积:3.49 MB
- 源站页面:https://scielo.figshare.com/articles/dataset/Learning_Curve_in_Left_Ventricular_Assist_Device_Implantation_Low_Volumes_Do_Not_Equate_Bad_Outcomes/21557075
命令行下载
curl -L -o "6dbe54774e89c46872a44bfccea6897bbb619702.tif" "https://ndownloader.figshare.com/files/38213300"
curl -L -o "3603857e5901bc169bb87915cb906091ea443870.png" "https://ndownloader.figshare.com/files/38213303"
curl -L -o "07fb224ae3efabce5eed2bcce31d394053c70757.jpg" "https://ndownloader.figshare.com/files/38213306"
curl -L -o "1ab9e3effefc58706e504ad496facc3281e8eba3.tif" "https://ndownloader.figshare.com/files/38213309"
curl -L -o "5e37366782eb69662f6c2532ddb15a6a94bedb69.png" "https://ndownloader.figshare.com/files/38213312"
curl -L -o "8907fcf9a16119d9a0a1948df8e643717fcbc1c6.jpg" "https://ndownloader.figshare.com/files/38213315"
curl -L -o "9b6c11abc6637247552c4c1d43bc591248d1cd99.tif" "https://ndownloader.figshare.com/files/38213318"
curl -L -o "921cbe747cf1a68e575d968fa337388c9058a4fb.png" "https://ndownloader.figshare.com/files/38213321"
文件清单
6dbe54774e89c46872a44bfccea6897bbb619702.tif(449.94 KB)3603857e5901bc169bb87915cb906091ea443870.png(315.99 KB)07fb224ae3efabce5eed2bcce31d394053c70757.jpg(6.96 KB)1ab9e3effefc58706e504ad496facc3281e8eba3.tif(1.28 MB)5e37366782eb69662f6c2532ddb15a6a94bedb69.png(871.35 KB)8907fcf9a16119d9a0a1948df8e643717fcbc1c6.jpg(6.23 KB)9b6c11abc6637247552c4c1d43bc591248d1cd99.tif(383.28 KB)921cbe747cf1a68e575d968fa337388c9058a4fb.png(169.10 KB)7f04dbbc54b43a1903429ec87b6c04c4d430789c.jpg(4.75 KB)
文件总体积 3.49 MB(源站 API 实测)。
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。
数据说明
ABSTRACT Introduction: Most implantations of left ventricular assist devices (LVAD) are performed in low-volume centers. This study aimed to evaluate the procedural learning curve of HeartMate II (HM2) implantations by comparing outcomes between two time periods in a low-volume center. Methods: All 51 consecutive patients undergoing HM2 implantation between January 2009 and December 2017 were reviewed and allocated into 2 groups: early-era group (from 2009 to 2014; n=25) and late-era group (from 2015 to 2017; n=26). The primary outcome was the 90-day mortality rate, and the secondary outcome was a composite of mortality, neurological event, reoperation for bleeding, need for temporary right ventricular assist device, and pump thrombosis at 90 days. Median follow-up time was 51 months (0-136). A cumulative sum (CUSUM) control analysis was used to establish a threshold of implantations that optimizes outcomes. Results: Patients in the early era had a higher rate of diabetes, previous stroke, and inotrope support before HM2 implantation. The 90-day mortality rate was not significantly higher in the early era (24% vs. 15%, P=0.43), but the composite endpoint was significantly higher (76% vs. 42%, P=0.01). The CUSUM analysis found a threshold of 23 operations after which the composite endpoint was optimized. Conclusion: Patients undergoing HM2 implantation in a low-volume center have improving outcomes with number of cases and optimized results after a threshold of 23 cases. Significant changes in patient selection, surgical techniques, and patient management might lead to improved outcomes after LVAD implantation.
许可
CC BY 4.0
引用
学术使用请引用 DOI 10.6084/m9.figshare.21557075.v1(source: https://scielo.figshare.com/articles/dataset/Learning_Curve_in_Left_Ventricular_Assist_Device_Implantation_Low_Volumes_Do_Not_Equate_Bad_Outcomes/21557075)。
数据缺失?
依托陕西、四川两大基地,我们与超过十家三甲医院建立直接合作关系,覆盖合规授权、采集治理、专业标注、数据交付的全流程,为AI医疗团队提供即拿即用的高质量临床数据。
⚡️ 需要数据支持或标注服务?立即联系我们获取专业方案。




