隐源性急性缺血性卒中-心房颤动连续监测系统性能评估

数据集获取（Figshare）

• 源站标题：Cryptogenic Acute Ischemic Stroke: Assessment of the Performance of a New Continuous Long-Term Monitoring System in the Detection of Atrial Fibrillation
• DOI：10.6084/m9.figshare.7045562.v1
• 发布日期：2018-09-05
• 文件数：8 个
• 文件总体积：553.40 KB
• 源站页面：https://scielo.figshare.com/articles/dataset/Cryptogenic_Acute_Ischemic_Stroke_Assessment_of_the_Performance_of_a_New_Continuous_Long-Term_Monitoring_System_in_the_Detection_of_Atrial_Fibrillation/7045562

命令行下载

curl -L -o "0066-782X-abc-20180112-gf01.jpg" "https://ndownloader.figshare.com/files/12948848"
curl -L -o "0066-782X-abc-20180112-gf02.jpg" "https://ndownloader.figshare.com/files/12948851"
curl -L -o "0066-782X-abc-20180112-gf03.jpg" "https://ndownloader.figshare.com/files/12948854"
curl -L -o "Table_1.xls" "https://ndownloader.figshare.com/files/12948857"
curl -L -o "Table_2.xls" "https://ndownloader.figshare.com/files/12948860"
curl -L -o "Table_3.xls" "https://ndownloader.figshare.com/files/12948863"
curl -L -o "Table_4.xls" "https://ndownloader.figshare.com/files/12948866"
curl -L -o "Table_5.xls" "https://ndownloader.figshare.com/files/12948869"

文件清单

• 0066-782X-abc-20180112-gf01.jpg（128.88 KB）
• 0066-782X-abc-20180112-gf02.jpg（170.50 KB）
• 0066-782X-abc-20180112-gf03.jpg（213.58 KB）
• Table_1.xls（9.73 KB）
• Table_2.xls（5.63 KB）
• Table_3.xls（5.63 KB）
• Table_4.xls（9.73 KB）
• Table_5.xls（9.73 KB）

文件总体积 553.40 KB（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 Background: Long-term monitoring has been advocated to enhance the detection of atrial fibrillation (AF) in patients with stroke. Objective: To evaluate the performance of a new ambulatory monitoring system with mobile data transmission (PoIP) compared with 24-hour Holter. We also aimed to evaluate the incidence of arrhythmias in patients with and without stroke or transient ischemic attack. Methods: Consecutive patients with and without stroke or TIA, without AF, were matched by propensity score. Participants underwent 24-hour Holter and 7-day PoIP monitoring. Results: We selected 52 of 84 patients (26 with stroke or TIA and 26 controls). Connection and recording times were 156.5 ± 22.5 and 148.8 ± 20.8 hours, with a signal loss of 6,8% and 11,4%, respectively. Connection time was longer in ambulatory (164.3 ± 15.8 h) than in hospitalized patients (148.8 ± 25.6 h) (p = 0.02), while recording time did not differ between them (153.7 ± 16.9 and 143.0 ± 23.3 h). AF episodes were detected in 1 patient with stroke by Holter, and in 7 individuals (1 control and 6 strokes) by PoIP. There was no difference in the incidence of arrhythmias between the groups. Conclusions: Holter and PoIP performed equally well in the first 24 hours. Data transmission loss (4.5%) occurred by a mismatch between signal transmission (2.5G) and signal reception (3G) protocols in cell phone towers (3G). The incidence of arrhythmias was not different between stroke/TIA and control groups.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.6084/m9.figshare.7045562.v1（source: https://scielo.figshare.com/articles/dataset/Cryptogenic_Acute_Ischemic_Stroke_Assessment_of_the_Performance_of_a_New_Continuous_Long-Term_Monitoring_System_in_the_Detection_of_Atrial_Fibrillation/7045562）。