udeezz/medical-checkup-synthetic-dataset

该数据集是一个合成的医疗检查数据集，包含模拟完整健康检查结果的数据（病史、体检、实验室结果、疫苗接种、职业风险因素等）。数据集专门设计用于：1) 临床分析：探索健康档案和风险因素聚类；2) 疾病预测：训练机器学习模型基于医疗输入数据预测主要诊断；3) 职业健康：评估职业风险因素（人体工程学/化学）与患者临床结果的关系。数据集包含10,000到100,000条记录，每条记录代表一次医疗访问或完整患者检查系列，所有患者身份信息已完全匿名化。主要数据类别包括：行政管理、病史、疫苗接种、职业暴露、生殖健康、体检、实验室结果以及结论与建议。This dataset contains synthetic data mimicking complete health check-up results (medical history, physical examination, laboratory results, vaccination, occupational risk factors, etc.). The dataset is specifically designed for: 1) Clinical Analysis: Exploring health profiles and clustering risk factors; 2) Disease Prediction: Training machine learning models to predict primary diagnoses based on medical input data; 3) Occupational Health: Evaluating the relationship between occupational risk factors (ergonomic/chemical) and patients clinical outcomes. The dataset contains between 10,000 to 100,000 records, with each row representing one medical visit or a complete series of patient examinations. All patient identities have been fully anonymized. Main data categories include: Administration, Anamnesis, Vaccination, Occupational Exposure, Reproduction, Physical Examination, Laboratory Results, and Conclusion & Recommendations.