基于人工神经网络的肾小球滤过率估计改进

数据集获取（Figshare）

• 源站标题：Improved Glomerular Filtration Rate Estimation by an Artificial Neural Network
• DOI：10.1371/journal.pone.0058242
• 发布日期：2013-03-14
• 文件数：24 个
• 文件总体积：1.14 MB
• 源站页面：https://plos.figshare.com/articles/dataset/Improved_Glomerular_Filtration_Rate_Estimation_by_an_Artificial_Neural_Network__/650922

命令行下载

curl -L -o "Figure_S1.doc" "https://ndownloader.figshare.com/files/985631"
curl -L -o "Figure_S2.doc" "https://ndownloader.figshare.com/files/985633"
curl -L -o "Figure_S3.doc" "https://ndownloader.figshare.com/files/985635"
curl -L -o "Figure_S4.doc" "https://ndownloader.figshare.com/files/985637"
curl -L -o "Table_S1.doc" "https://ndownloader.figshare.com/files/985638"
curl -L -o "Table_S2.doc" "https://ndownloader.figshare.com/files/985640"
curl -L -o "Table_S3.doc" "https://ndownloader.figshare.com/files/985642"
curl -L -o "Table_S4.doc" "https://ndownloader.figshare.com/files/985643"

文件清单

• Figure_S1.doc（71.68 KB）
• Figure_S2.doc（114.69 KB）
• Figure_S3.doc（54.78 KB）
• Figure_S4.doc（87.55 KB）
• Table_S1.doc（62.46 KB）
• Table_S2.doc（30.21 KB）
• Table_S3.doc（44.03 KB）
• Table_S4.doc（37.89 KB）
• Table_S5.doc（37.38 KB）
• Table_S6.doc（36.35 KB）
• Table_S7.doc（37.89 KB）
• Table_S8.doc（35.33 KB）
• Table_S9.doc（36.35 KB）
• Table_S10.doc（34.82 KB）
• Table_S11.doc（37.38 KB）
• Table_S12.doc（33.28 KB）
• Table_S13.doc（36.35 KB）
• Table_S14.doc（32.77 KB）
• Table_S15.doc（36.35 KB）
• Table_S16.doc（38.40 KB）

文件总体积 1.14 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

Background
Accurate evaluation of glomerular filtration rates (GFRs) is of critical importance in clinical practice. A previous study showed that models based on artificial neural networks (ANNs) could achieve a better performance than traditional equations. However, large-sample cross-sectional surveys have not resolved questions about ANN performance.
Methods
A total of 1,180 patients that had chronic kidney disease (CKD) were enrolled in the development data set, the internal validation data set and the external validation data set. Additional 222 patients that were admitted to two independent institutions were externally validated. Several ANNs were constructed and finally a Back Propagation network optimized by a genetic algorithm (GABP network) was chosen as a superior model, which included six input variables; i.e., serum creatinine, serum urea nitrogen, age, height, weight and gender, and estimated GFR as the one output variable. Performance was then compared with the Cockcroft-Gault equation, the MDRD equations and the CKD-EPI equation.
Results
In the external validation data set, Bland-Altman analysis demonstrated that the precision of the six-variable GABP network was the highest among all of the estimation models; i.e., 46.7 ml/min/1.73 m2 vs. a range from 71.3 to 101.7 ml/min/1.73 m2, allowing improvement in accuracy (15% accuracy, 49.0%; 30% accuracy, 75.1%; 50% accuracy, 90.5% [PPConclusions
A new ANN model (the six-variable GABP network) for CKD patients was developed that could provide a simple, more accurate and reliable means for the estimation of GFR and stage of CKD than traditional equations. Further validations are needed to assess the ability of the ANN model in diverse populations.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.1371/journal.pone.0058242（source: https://plos.figshare.com/articles/dataset/Improved_Glomerular_Filtration_Rate_Estimation_by_an_Artificial_Neural_Network__/650922）。