远端胆管癌胰十二指肠切除术后生存预测模型验证数据集

数据集获取（Figshare）

• 源站标题：Prediction of survival after pancreatoduodenectomy for distal cholangiocarcinoma: independent external validation of a prognostic model for 3-year overall survival in Sweden
• DOI：10.6084/m9.figshare.28136880.v1
• 发布日期：2025-01-04
• 文件数：2 个
• 文件总体积：174.62 KB
• 源站页面：https://tandf.figshare.com/articles/dataset/Prediction_of_survival_after_pancreatoduodenectomy_for_distal_cholangiocarcinoma_independent_external_validation_of_a_prognostic_model_for_3-year_overall_survival_in_Sweden/28136880

命令行下载

curl -L -o "sgas-2024-or-0682-File001.doc" "https://ndownloader.figshare.com/files/51480639"
curl -L -o "sgas-2024-or-0682-File002.docx" "https://ndownloader.figshare.com/files/51480642"

文件清单

• sgas-2024-or-0682-File001.doc（83.97 KB）
• sgas-2024-or-0682-File002.docx（90.65 KB）

文件总体积 174.62 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

The only treatment with curative potential for distal cholangiocarcinoma (dCCA) is radical surgery which can be complemented with adjuvant chemotherapy. The aim of the present study was to perform an independent external validation of a prognostic model for 3-year overall survival based on routine clinicopathological variables for patients treated with pancreatoduodenectomy for dCCA.
All patients with a histopathological confirmed dCCA that underwent pancreatoduodenectomy in Sweden from 2009 through 2019 were identified in the Swedish National Registry for Pancreatic and Periampullary Cancer. Model performance was estimated using the C-index and calibration plots.
In total 220 patients were included in the study. The median survival was 33 months (IQR 26–40) and 3-year survival rate 47% (95% CI 40–53%). The prognostic model had a C-index of 0.69 (95% CI 0.62–0.72). Calibration plots revealed overestimated risk of death across risk groups in the full cohort. Calibration was good in the subgroup of patients that did not receive adjuvant treatment.
The prognostic model showed reasonable discriminative ability but some miscalibration likely since the effect of adjuvant treatment is not included in the model. Given that the model was developed in cohorts treated prior to the current adjuvant standard of care the model can be used to estimate baseline risk prior to risk/benefit decision for adjuvant treatment as well as stratification for clinical trials but with a risk to underestimate 3-year overall survival for patients that receive adjuvant treatment.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.6084/m9.figshare.28136880.v1（source: https://tandf.figshare.com/articles/dataset/Prediction_of_survival_after_pancreatoduodenectomy_for_distal_cholangiocarcinoma_independent_external_validation_of_a_prognostic_model_for_3-year_overall_survival_in_Sweden/28136880）。