Cardiovascular Risk Prediction Dataset from Bangladeshi Survey Data with Demographic, Behavioral, Lifestyle, and Clinical Features

This dataset contains survey-based health data collected from 328 individuals, capturing a comprehensive set of demographic, lifestyle, clinical, and behavioral risk factors associated with heart disease. Each record represents one respondent and includes self-reported information on physical health indicators, daily habits, medical history, and a binary label indicating whether the individual is a heart patient. Sensitive or identifying information has been removed from the final released dataset to ensure privacy and prevent data leakage. The dataset can be used for binary CVD risk prediction, classification benchmarking, and explainable machine learning research. Keywords: Cardiovascular Risk Prediction, Survey-Based Dataset, Machine Learning, Demographic Features, Lifestyle Factors, Clinical Data本数据集包含从328名受访者处收集的基于问卷调查的健康数据，涵盖了与心脏病相关的全套人口统计学、生活方式、临床及行为风险因素。每条记录对应一名受访者，包含受访者自行报告的身体健康指标、日常习惯、病史信息，以及用于标识该个体是否为心脏病患者的二分类标签。 为保障隐私并防止数据泄露，最终发布的数据集中已移除所有敏感信息及可识别个人身份的内容。本数据集可用于二分类心血管疾病（Cardiovascular Disease, CVD）风险预测、分类任务基准测试以及可解释机器学习相关研究。 关键词：心血管风险预测、基于问卷的数据集、机器学习、人口统计学特征、生活方式因素、临床数据