A Comparative Study of Feature Selection Methods for EHR Diagnosis Codes in Opioid Use Disorder Prediction
This study focuses on diagnosis-related features and compares five feature selection paradigms for opioid use disorder prediction: recurrence enrichment, NTK-motivated early gradient sensitivity, LightGBM-SHAP, Elastic Net, and large language model (LLM)-guided semantic selection.
Zihan Ding, Yinan Liu, Tengfei Ma et al.
· 0 citations