低风险超重患者的风险分层患者基础模型

Accurate risk stratification in patients with overweight or obesity is essential for guiding preventive care and allocating high-cost therapies such as GLP-1 receptor agonists. The study presents PatientTPP, a neural temporal point process (TPP) model trained on over 500,000 real-world clinical trajectories to learn patient representations from sequences of diagnoses, labs, and medications. This model extends existing TPP modeling approaches by incorporating static and numeric features and integrating clinical knowledge for event encoding. PatientTPP representations support downstream prediction tasks, including the classification of obesity-associated outcomes in low-risk individuals, even for events not explicitly modeled during training. The findings hold significant implications for health economic evaluation.