医疗中风数据集

该数据集是一个包含患者人口统计信息、健康状况和生活方式等临床表格数据的医疗数据集，主要用于中风风险预测和医疗数据分析研究，通过分析高血压、心脏病、血糖水平、吸烟状况等多种因素，帮助识别中风相关风险并支持疾病预防和公共卫生决策。

github

2024-07-15 更新

医疗数据分析中风研究

基本信息

创建/更新时间

2024-07-15

资源简介

该数据集是一个公开的医疗数据集，专门用于研究中风相关的风险因素和预测分析。数据集包含患者唯一标识符、性别、年龄、高血压病史、心脏病史、婚姻状况、工作类型、居住类型、平均血糖水平、身体质量指数、吸烟状况以及是否经历过中风等多个字段。数据来源于医疗记录，可用于构建中风风险预测模型、分析中风相关因素，并应用于医疗数据分析、疾病预测和公共卫生研究等领域。

原始链接

https://github.com/Pratiksha012/Graph-Analytics-and-Algorithms-on-Stroke-Dataset

访问原始数据

官方服务

如需原始数据获取支持或标注服务，请联系我们。

帮我联系

下载信息

注册下载

Tips: 该数据集需要在对应的数据源网站注册通过后，才能进行数据下载，注册有对应要求，或者需要收费。

暂未开放

公开下载

Tips: 该数据集属于公开下载，应该可以免费公开下载。

免登录

有偿下载

Tips: 该数据集 Qianfanghub 可以协助提供有偿下载服务，注意，服务不针对数据相关产权，只是技术服务费。

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

千方医数集，医疗数据集部分，是为社区服务的公开医疗数据集搜索引擎，并不存储或者下载原始的任何数据。如果您有其他医疗数据需求，可以和客服联系，或者下工单。我们有强大的三甲医疗机构帮助您提供个性化的医疗数据定制、采集、标注服务。

使用方式

数据集获取

git clone https://github.com/Pratiksha012/Graph-Analytics-and-Algorithms-on-Stroke-Dataset.git

curl -L -o repo.zip https://github.com/Pratiksha012/Graph-Analytics-and-Algorithms-on-Stroke-Dataset/archive/refs/heads/main.zip
unzip repo.zip

源站 README 摘录（使用方式）

Graph Analytics and Algorithms on Healthcare Stroke Dataset

Introduction

This project explores the application of graph analytics and algorithms on a healthcare stroke dataset. We conduct a comprehensive case study involving data preprocessing, exploratory data analysis (EDA), graph centrality measures, and various machine learning models. The primary aim is to gain insights from the dataset and improve predictive modeling using graph-based approaches.

Dataset

The dataset used in this study is focused on healthcare data related to strokes. It contains the following columns:

id: Unique identifier for each patient.
gender: Gender of the patient.
age: Age of the patient.
hypertension: Whether the patient has hypertension (1) or not (0).
heart_disease: Whether the patient has heart disease (1) or not (0).
ever_married: Marital status of the patient.
work_type: Type of work the patient is involved in.
Residence_type: Type of residence (Urban/Rural).
avg_glucose_level: Average glucose level in the blood.
bmi: Body Mass Index of the patient.
smoking_status: Smoking status of the patient.
stroke: Whether the patient has experienced a stroke (1) or not (0).

Project Structure

1. Data Preprocessing and Cleaning

Data Cleaning: Handled missing values, outliers, and irrelevant data to ensure the dataset is suitable for analysis.
Label Encoding: Converted categorical data into numerical labels for analysis, making it easier to apply machine learning algorithms.
Exploratory Data Analysis (EDA): Conducted EDA to understand the distribution of various features, identify patterns, and gain initial insights into the data. This included visualizations and statistical analysis.

2. Graph Centrality Analysis

Graph Construction: Created graphs representing relationships within the data. Each node represents a patient, and edges represent relationships based on various features.
Centrality Measures:
- Degree Centrality: Identified nodes (patients) with the highest number of connections, indicating potential key influencers.
- Closeness Centrality: Measured the average shortest path from a node to all other nodes, indicating the speed of information spread within the network.
- Betweenness Centrality: Determined nodes that act as bridges between ot