敏感性、特异性和预测值数据集

数据集获取（Figshare）

• 源站标题：Sensitivity, specificity, and predictive values.
• DOI：10.1371/journal.pone.0319145.t003
• 发布日期：2025-03-12
• 文件数：1 个
• 文件总体积：9.73 KB
• 源站页面：https://plos.figshare.com/articles/dataset/Sensitivity_specificity_and_predictive_values_/28583855

命令行下载

curl -L -o "Table 3.xls" "https://ndownloader.figshare.com/files/52949159"

文件清单

• Table 3.xls（9.73 KB）

文件总体积 9.73 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

Introduction
Infectious diarrheal diseases are one of the leading causes of worldwide morbidity and mortality. The incidence of diarrhea is higher in Low-Middle-Income Countries (LMIC), where more than 90% of deaths from diarrheal diseases occur. Diagnostic tests for infectious diarrhea are not readily available in Low-Middle-Income Countries. Our study evaluates a novel, cost-effective, easy-to-use DNA stool testing kit for infectious diarrhea that can easily be rolled out in low-resource settings and has comparable performance to current testing modalities in the USA in terms of diagnostic utility.
Methods
435 stool samples were tested using the novel stool testing Kit (Go-GutDx®). The stool samples were in groups of 8 and were tested using floating microspheres DNA extraction followed by Recombinase Polymerase Amplification (RPA) and lateral flow assay detection. Pathogens tested include Clostridium difficile, Campylobacter jejuni, Salmonella enterica Typhimurium, Shigella spp., STEC (stx1, stx2), Vibrio spp., and Yersinia enterocolitica. The same samples were tested using BioFire GI Panel (gold standard), and the results were compared. Descriptive analysis was summarized as raw counts and frequencies and compared using Fisher’s exact test. We conducted specificity and sensitivity analysis of the two diagnostic tests using the diagnostic testing package in STATA. Graphical illustrations were conducted using two-way line graphs with custom margins and axis. All analyses with p-values ≤ 0.05 were significant. All analyses were conducted using STATA version 17.
Results
Results showed a sensitivity of 56.1% for C. difficile, and 58.6% for Campylobacter jejuni. 46.1% for STEC (stx1, stx2), 83.3% for Salmonella, 0% for Yersinia enterocolitica, 66.7% for Vibrio spp and 65.0% for Shigella spp. Specificities were > 97% for all pathogens. The positive predictive value was highest for Campylobacter jejuni 94.4%, followed by C. difficile 93.5%, Salmonella 86.2%, Shigella 76.5%, STEC (stx1, stx2) 50%, Vibrio spp 40%, and Yersinia 0%. The negative predictive value was 75.8% for C. difficile, with all other pathogens being above 98.3%. Table 3. The concordance between BioFi

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.1371/journal.pone.0319145.t003（source: https://plos.figshare.com/articles/dataset/Sensitivity_specificity_and_predictive_values_/28583855）。