塞内加尔学龄儿童生物电阻抗分析预测全身水分与肥胖效度数据

数据集获取

源站：https://doi.org/10.5061/dryad.97v3161

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。

数据集大小约 167.2 KB。

数据说明

Introduction: Childhood obesity is currently a serious public health challenge in developing countries. Therefore, an accurate assessment of adiposity is required. The objective of this study was to validate BIA prediction equations for the assessment of total body water and adiposity or percentage of body fat for the first time in Senegalese school-aged children. Methods: One-hundred-fifty-one (151) pupils who were 8-11 years old were randomly selected from four public schools in Dakar. The body composition measured by deuterium dilution method (DDM) was used as the reference method and compared to that predicted by BIA using a multi-frequency analyser. Stepwise backward multiple linear regression was performed to calculate TBW and %BF in a subsample, which were then validated it in the rest of the sample. The Bland and Altman approach was used to assess the agreement between the two methods (bias and limits of agreement). Results: FFM was higher in boys (24.6±6.9 kg) compared to girls (21.2±3.3 kg; P<0.001), and %BF was lower in boys (5.1±4.6 kg) compared to girls (5.3±3.8 kg; P<0.05). Overall, 11.3% of children were obese (%BF ≥25% in boys, and ≥30% in girls) and 4.6% were overweight/obese according to their BMI-z score (>+1). The equations developed were as follows: TBW=0.376(Height²/Z50)-0.470 (sex) +0.076(weight) +0.065(height)-2.28. %BF= -1.10(height²/Z50) +3.14(sex)+1.57(weight)-4.347. These specific equations showed good precision and a low and non-significant mean bias (0.11 kg, P=0.279; and 0.19 kg, P=0.764) for TBW and %BF, respectively. Conclusion: The newly developed equations can be used as an accurate and alternative tool for screening for obesity among African school-aged children in various settings

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。