基于中性粒细胞-淋巴细胞比率和不成熟血小板分数构建ICU脓毒症患者预后模型的数据集

数据集获取（Figshare）

• 源站标题：Development of a prognostic model for intensive care unit patients with sepsis based on the neutrophil-to-lymphocyte ratio and immature platelet fraction_data.xlsx
• DOI：10.6084/m9.figshare.26304598.v1
• 发布日期：2024-07-15
• 文件数：2 个
• 文件总体积：57.91 KB
• 源站页面：https://figshare.com/articles/dataset/Development_of_a_prognostic_model_for_intensive_care_unit_patients_with_sepsis_based_on_the_neutrophil-to-lymphocyte_ratio_and_immature_platelet_fraction_data_xlsx/26304598

命令行下载

curl -L -o "Development of a prognostic model for intensive care unit patients with sepsis based on the neutrophil-to-lymphocyte ratio and immature platelet fraction_data.xlsx" "https://ndownloader.figshare.com/files/47693578"
curl -L -o "Development of a prognostic model for intensive care unit patients with sepsis based on the neutrophil-to-lymphocyte ratio and immature platelet fraction_data.xlsx" "https://ndownloader.figshare.com/files/47693641"

文件清单

• Development of a prognostic model for intensive care unit patients with sepsis based on the neutrophil-to-lymphocyte ratio and immature platelet fraction_data.xlsx（28.95 KB）
• Development of a prognostic model for intensive care unit patients with sepsis based on the neutrophil-to-lymphocyte ratio and immature platelet fraction_data.xlsx（28.95 KB）

文件总体积 57.91 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: We evaluated the relationship between the immature platelet fraction (IPF) and neutrophil-to-lymphocyte ratio (NLR) and their dynamic changes for sepsis prognosis.
Methods: This retrospective observational study included 58 patients with sepsis admitted to an intensive care unit. The baseline Sequential Organ Failure Assessment (SOFA), Acute Physiology and Chronic Health Evaluation II (APACHE II), IPF, NLR, albumin (ALB), lactate (LAC), and procalcitonin (PCT) values of the survival and non-survival groups were compared; IPF, NLR, ALB, LAC, and PCT were measured for three consecutive days. The IPF3rd and NLR3rd constructed a prognostic model and compared it with the APACHE II-score prediction model. Both models were evaluated using receiver operating characteristic (ROC) curves and decision curve analysis (DCA).
Results: To formulate a nomogram, age, sex, SOFA score, APACHE II score, IPF3rd, and NLR3rd were carefully screened. We analyzed the higher-score parameters in the nomogram (NLR3rd, IPF3rd, APACHE II, and SOFA) and established an ROC curve. NLR3rd had the highest sensitivity (88.2%), and IPF3rd had the highest specificity (94.7%) for predicting sepsis. Model 1 (-3.44526 + 0.11632 × APACHE II score) was constructed based on the APACHE II score (odds ratio (OR), 13.96; 95% confidence interval (CI), 0.679–0.807), while Model 2 was constructed based on the NLR3rd and IPF3rd values (-5.27848 + 0.11246 × NLR3rd + 0.23262 × IPF3rd) (OR: 78; 95% CI, 0.941–1.000). The AUC of Model 2 was 0.906 (95% CI, 0.807–1.000), while that of Model 1 was 0.810 (95% CI, 0.679–0.941). In the DCA curve evaluation, Model 2 showed a higher clinical benefit than Model 1.
Conclusions: The IPF and NLR on the third ICU admission day were closely associated with 28-day mortality in patients with sepsis. The prediction model established based on these parameters showed a higher clinical benefit than the APACHE-score prediction model.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.6084/m9.figshare.26304598.v1（source: https://figshare.com/articles/dataset/Development_of_a_prognostic_model_for_intensive_care_unit_patients_with_sepsis_based_on_the_neutrophil-to-lymphocyte_ratio_and_immature_platelet_fraction_data_xlsx/26304598）。