基于多维指标的青少年群体健康画像数据

本数据集遵循《数据安全法》及《个人信息安全规范》（GB/T 35273）要求，对原始采集数据进行了以下全流程标准化处理：
数据清洗与标准化 (Data Cleaning)：
异常值剔除： 利用统计学算法（如3σ原则）识别并剔除体检录入中的逻辑错误（如身高体重极值错误），确保数据源的准确性。
格式统一： 对不同来源的体检数据进行归一化处理，统一字段命名、计量单位及数据编码标准（遵循WS/T 456-2014《学龄儿童青少年营养不良筛查》等国标）。
隐私脱敏与去标识化 (De-identification & Anonymization) —— 核心部分，必写：
直接标识符删除： 在数据入库前，彻底删除学生姓名、身份证号、家庭住址、家长联系方式等能直接定位到特定个人的敏感字段。
泛化处理： 对特定敏感数据进行模糊化处理。

This dataset has completed full-process standardized processing of the originally collected data in compliance with the requirements of the Data Security Law of the People's Republic of China and the Personal Information Security Specification (GB/T 35273):

Data Cleaning and Standardization (Data Cleaning):
Outlier Removal: Use statistical algorithms (e.g., the 3σ principle) to identify and eliminate logical errors in physical examination entries (such as extreme height and weight errors) to ensure the accuracy of the data source.
Format Unification: Normalize physical examination data from different sources, unify field names, measurement units and data coding standards in compliance with national standards such as WS/T 456-2014 Screening for Malnutrition in School-Age Children and Adolescents.

Privacy Desensitization and De-identification (De-identification & Anonymization) – Core Mandatory Section:
Direct Identifier Removal: Before data is stored in the database, completely delete sensitive fields that can directly identify specific individuals, including student names, ID card numbers, home addresses, parents' contact information and other similar items.
Generalization Processing: Perform fuzzy processing on specific sensitive data.

搜集汇总

背景与挑战

背景概述

该数据集基于贵阳市观山湖区普瑞学校的学生体质健康监测活动，包含10000条记录，每年更新一次。它覆盖生长发育、身体机能、视力健康等多维指标，旨在反映区域青少年体质健康现状及演变趋势，并经过严格的清洗、标准化和隐私脱敏处理以确保数据安全。