血液透析血管声音指数作为血管通路狭窄诊断工具：一项前瞻性病例对照研究

数据集获取（Figshare）

• 源站标题：Hemodialysis Vascular Sound Index as a Diagnostic Tool for Vascular Access Stenosis: A Prospective Case-Control Study
• DOI：10.6084/m9.figshare.28636406.v2
• 发布日期：2025-08-06
• 文件数：2 个
• 文件总体积：25.53 KB
• 源站页面：https://figshare.com/articles/dataset/Hemodialysis_Vascular_Sound_Index_as_a_Diagnostic_Tool_for_Vascular_Access_Stenosis_A_Prospective_Case-Control_Study/28636406

命令行下载

curl -L -o "Reproducibility Verification.csv" "https://ndownloader.figshare.com/files/53138171"
curl -L -o "VSI_MP.csv" "https://ndownloader.figshare.com/files/56934518"

文件清单

• Reproducibility Verification.csv（1.02 KB）
• VSI_MP.csv（24.51 KB）

文件总体积 25.53 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

Background and objectives
Vascular access (VA) monitoring is critical for hemodialysis patients. While Doppler ultrasound (US) provides high diagnostic accuracy for VA stenosis, its reliance on specialized training limits its routine use. The Hemodialysis Vascular Sound Index (HVSI), derived from vascular murmur analysis, may provide a simple, objective alternative. This study evaluates the diagnostic performance of the HVSI in detecting VA stenosis and reduced flow volume (FV).
Methods
This prospective case-control study included 202 hemodialysis patients (101 with stenosis in the study group, 101 in the control group). Participants were matched based on age, sex, dialysis duration, diabetes status, Kt/V, and blood data. HVSI was measured with an electronic stethoscope placed over the VA site. FV and resistance index (RI) were assessed by Doppler US. Stenosis was diagnosed by clinical criteria and confirmed by Doppler US. Diagnostic accuracy was determined from receiver operating characteristics, including sensitivity, specificity, and area under the curve (AUC).
Results
HVSI showed significant correlations with FV (R² = 0.58) and RI (R² = 0.32). For FV thresholds ≤500, ≤400, and ≤350 mL/min, HVSI showed sensitivities of 86.3-94.4%, specificities of 78.7-82.9%, and AUCs of 0.90-0.94. Diagnostic accuracy was higher in non-bifurcated vessels.
Discussion and Conclusion
HVSI has significant potential to improve routine surveillance of VA. Further research is warranted to validate its applicability across diverse patient populations.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.6084/m9.figshare.28636406.v2（source: https://figshare.com/articles/dataset/Hemodialysis_Vascular_Sound_Index_as_a_Diagnostic_Tool_for_Vascular_Access_Stenosis_A_Prospective_Case-Control_Study/28636406）。