肝硬化患者肝性脑病适当管理（内科住院患者）

数据集获取

源站：https://clinicaltrials.gov/study/NCT07727070

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。

数据说明

Conditions: Cirrhoses, Liver, Portal Hypertension Related to Cirrhosis, Liver Stiffness, Hepatic Encephalopathy. Patients with decompensated liver cirrhosis are mostly managed in Internal Medicine outpatient clinics and wards; among these patients, overt hepatic encephalopathy represents one of the most frequent causes of emergency hospital admission. Furthermore, hospitalizations for decompensated cirrhosis are expected to increase steadily, given the progressive rise in chronic liver diseases of metabolic and alcohol-related origin. Therefore, the skills of the Internal Medicine physician must increasingly include screening for minimal hepatic encephalopathy, identification and treatment of overt hepatic encephalopathy, and prevention of relapses. In view of the lack of data from prospective studies on the incidence, management, and outcomes of hepatic encephalopathy in patients admitted to Internal Medicine wards in Italy, it is considered important to collect and analyze a large case series in order to identify critical issues in management during hospitalization and at discharge, also with the aim of preventing rehospitalizations. On this basis, Fondazione FADOI has decided to promote the FADOI-HEPTAGON study, a prospective, multicenter, observational study involving approximately 45 Internal Medicine Units across Italy, which will competitively enroll at least 400 consecutive inpatient cases of liver cirrhosis over a one-year period, collecting data on management, treatment, and clinical outcomes during the acute phase and at 3 and 9 months after discharge (follow-up). Among these subjects, patients with hepatic encephalopathy will also be identified in order to assess its incidence.

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。