Mhdvav2323/bipolar-mixed-states-synthetic

这是一个高保真合成纵向数据集，模拟了具有混合特征的双相情感障碍（ICD-10: F31.6x）。该数据集使用CTGAN生成，并具备差分隐私保证，旨在用于机器学习/人工智能研究、临床决策支持开发和教学目的。数据集包含800名患者的5,550条记录，每位患者有7次访问记录，时间跨度为7个月。数据集包含35个变量，涵盖了多种临床评分量表和独特的心理现象，如身份危机、躁狂期间的睡眠厌恶、兴奋剂滥用模式和多药冲突等。数据集还提供了详细的诊断分布和隐私保护措施，确保数据的安全性和匿名性。

High-fidelity synthetic longitudinal dataset modeling bipolar disorder with mixed features (ICD-10: F31.6x). Generated using CTGAN with differential privacy guarantees for ML/AI research, clinical decision support development, and educational purposes. The dataset includes 800 patients with 5,550 total records, 7 visits per patient over a 7-month time span, and 35 variables. It features various clinical rating scales and unique psychological phenomena such as post-diagnosis identity crisis, sleep aversion in mania, stimulant misuse patterns, and polypharmacy conflict. The dataset also provides detailed diagnosis distribution and privacy measures ensuring data security and anonymity.