儿科脓毒症数据挑战数据集
该数据集是一个基于乌干达真实医院数据生成的合成临床表格数据集，包含儿科脓毒症患者的临床指标与实验室检测结果等结构化数据，主要用于脓毒症预测和医学数据分析研究，支持开发机器学习模型以预测儿科脓毒症患者的住院死亡率。
基本信息
资源简介
儿科脓毒症数据挑战数据集
【数据集背景】
本数据集源站标题为《Kamaleswaran-Lab/The-2024-Pediatric-Sepsis-Challenge》。源站首次发布：2024-10-29。
【数据内容】
源站原始描述：# Pediatric Sepsis Data Challenge: In-Hospital Mortality Prediction Task Welcome to the Pediatric Sepsis Data Challenge! This challenge focuses on predicting in-hospital mortality for pediatric sepsis cases using a synthetic dataset derived from real-world data. The ultimate goal is to improve early detection models for better resource allocation and clinical outcomes in low-resource healthcare settings. ## Objective Develop an open-source algorithm to predict in-hospital mortality among childre…
【获取与许可】
源站页面：https://github.com/Kamaleswaran-Lab/The-2024-Pediatric-Sepsis-Challenge
【使用注意】
· 源站最后修改于 2025-06-26，引用时请注意版本时效。
下载信息
注册下载
需要注册 Kaggle 账号并登录后下载，适合需要跟踪下载记录和使用 API 的用户。
暂未开放公开下载
无需注册即可直接获取公开样本或文档，适合快速预览和评估数据集质量。
免登录有偿下载
公开数据集受托下载与技术交付服务。
提供高速下载与技术交付服务（收技术服务费，非数据销售）
暂未开放当前数据集主要来源为 Kaggle 公开托管，完整影像包建议通过原始链接或 Kaggle API 获取。
使用方式
数据集获取
git clone https://github.com/Kamaleswaran-Lab/The-2024-Pediatric-Sepsis-Challenge.git
curl -L -o repo.zip https://github.com/Kamaleswaran-Lab/The-2024-Pediatric-Sepsis-Challenge/archive/refs/heads/main.zip
unzip repo.zip
源站 README 摘录（使用方式）
1. Data and Code Requirements
Dataset
- Provided Dataset: Synthetic data derived from real hospital data from Uganda, use file SyntheticData_Training.csv as training data, and SyntheticData_DataDictionary_V1.docx as data dictionary.
- Feature Constraints: Your algorithm should exclusively use the provided dataset variables for predictions.
Submission Requirements
- Code and Model: Submit both:
- Training Code: All scripts and code required for training the model.
- Trained Model: The model file generated from your code.
- Language: Submissions must be in Python; however, R, and MATLAB submissions are no longer acceptable. Python is recommended to facilitate baseline comparisons.
Code Validity
-
Environment: Code will run in a containerized setup.
-
Execution Time: Maximum 24 hours for training, with 8 hours allocated for validation and testing.
-
Autonomous Execution: Ensure your code can execute end-to-end without manual intervention.
- Dependencies: List all dependencies in
requirements.txtor a compatible environment configuration file.
- Dependencies: List all dependencies in
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。
完整仓库：github.com/Kamaleswaran-Lab/The-2024-Pediatric-Sepsis-Challenge
数据缺失？
依托陕西、四川两大基地，我们与超过十家三甲医院建立直接合作关系，覆盖合规授权、采集治理、专业标注、数据交付的全流程，为AI医疗团队提供即拿即用的高质量临床数据。
⚡️ 需要数据支持或标注服务？立即联系我们获取专业方案。
