研究数据集

数据集获取（Figshare）

• 源站标题：Data set of the study.
• DOI：10.1371/journal.pone.0313842.s001
• 发布日期：2025-01-09
• 文件数：1 个
• 文件总体积：64.69 KB
• 源站页面：https://plos.figshare.com/articles/dataset/Data_set_of_the_study_/28177344

命令行下载

curl -L -o "pone.0313842.s001.xlsx" "https://ndownloader.figshare.com/files/51583134"

文件清单

• pone.0313842.s001.xlsx（64.69 KB）

文件总体积 64.69 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
Predicting mortality and morbidity poses a significant challenge to physicians, leading to the development of various scoring systems. Among these, the hemoglobin, albumin, lymphocyte and platelet (HALP) score evaluates a patient’s nutritional and immune status. The primary aim of this study was to determine the predictive effect of the HALP score on 30-day and 1-year mortality in elderly patients with proximal femoral fractures (PFFs).
Materials and methods
Patient demographic, clinical, laboratory, and prognostic data were obtained. The patients were categorized into two groups: survival and nonsurvival at mortality endpoints. The HALP score was calculated and compared among the groups and with other mortality biomarkers such as C-reactive protein (CRP) and C-reactive protein to albumin ratio (CAR). The ability of the HALP score to predict mortality was compared between the groups. The mortality risk was also calculated at the optimal threshold.
Results
The HALP score had a statistically significant predictive effect on mortality endpoints and was lower in the non-surviving group. The ability of the HALP score to predict 1-year mortality at the optimal cut-off value (17.975) was superb, with a sensitivity of 0.66 and specificity of 0.86 (AUC: 0.826, 95% CI: 0.784–0.868). In addition, the power of the HALP score to differentiate survivors and non-survivors was more significant than that of other indices (p Conclusion
The results indicate that the HALP score demonstrates efficacy and utility in predicting 30-day and 1-year mortality risk among elderly patients with PFFs.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.1371/journal.pone.0313842.s001（source: https://plos.figshare.com/articles/dataset/Data_set_of_the_study_/28177344）。