Machine Learning‐Based Predictive Modeling for the Development of Chronic Rhinosinusitis Using Longitudinal Health Records
作者
Justina R. Varghese,Sicong Chang,Akshay R. Prabhakar,Jason F. Zhang,Richard A. Balbin,Sebastian Guadarrama‐Sistos Vazquez,Aatin K. Dhanda,Renjie Hu,Michael T. Yim,Xin Fu,Masayoshi Takashima,Omar G. Ahmed
KEY POINTS: Machine learning identifies reproducible pre-diagnostic CRS trajectories in large EHR cohorts. Models show stable external performance (AUC ∼ 0.81), supporting real-world generalizability. Predictors highlight evolving CRS workups and models may serve as future decision support tools.