广西社区服务中心健康小屋身体健康指数数据

通过采集健康小屋平台上广西社区服务中心所服务用户的日常健康检测，完成对用户心脏健康评估，心血管疾病评估、体脂率、基础代谢、血液粘稠度、疲劳度、情绪压力等因素为自变量，综合分析个人的健康指数，健康小屋帮助用户更好地了解自己的健康状况，及时发现潜在问题，并提供个性化的健康建议和支持。
本数据适用于：
社区服务中心：为社区居民提供了一站式的健康管理解决方案，无论是日常监测、疾病管理还是康复训练，通过该指数为用户提供个性化的饮食和运动的建议。通过本公司健康小屋平台，采集广西社区服务中心的数据，完成对广西社区服务中心服务对象的健康检测和评估；将数据预处理后，输入到随机森林模型中，根据模型中各因素水平的分值得出膳食推荐指数。
综合多棵决策树的预测结果，最终的身体健康指数公式为：
= (1/N) * ∑(i=1 to N) Ti(x)

N 是随机森林中决策树的数量；
Σ(i=1 to N) 表示从1到N的求和；
Ti(x) 是第i个决策树对输入x的预测输出；
X是输入的身体指标特征向量（身高、体重、年龄、性别、心率、BMI、体脂率、基础代谢、收缩压、血液粘稠度、血清总胆固醇、糖尿病、吸烟、情绪压力、疲劳度）。

This dataset is constructed by collecting daily health examination data of users served by Guangxi Community Service Centers via the Health Cabin platform. Using factors including cardiac health assessment, cardiovascular disease assessment, body fat percentage, basal metabolism, blood viscosity, fatigue level and emotional stress as independent variables, it conducts a comprehensive analysis of individual health index. The Health Cabin helps users better understand their own health status, detect potential problems in a timely manner, and provide personalized health advice and support.

This dataset is applicable to:
Community Service Centers: They provide one-stop health management solutions for community residents, covering daily monitoring, disease management and rehabilitation training, and offer users personalized diet and exercise recommendations based on the health index. Data from Guangxi Community Service Centers is collected via our company's Health Cabin platform to complete health examinations and assessments for the service targets of Guangxi Community Service Centers. After data preprocessing, the data is input into a random forest model, and the dietary recommendation index is calculated based on the score values of each factor level in the model.

By integrating the prediction results of multiple decision trees, the final physical health index formula is:
$$H = frac{1}{N} sum_{i=1}^{N} T_i(x)$$

Where:
N is the number of decision trees in the random forest;
$sum_{i=1}^{N}$ denotes the summation from 1 to N;
$T_i(x)$ is the predicted output of the i-th decision tree for input $x$;
$X$ is the input physical indicator feature vector, including height, weight, age, gender, heart rate, BMI, body fat percentage, basal metabolism, systolic blood pressure, blood viscosity, total serum cholesterol, diabetes, smoking, emotional stress and fatigue level.