Disease staging is a critical component of clinical diagnosis, treatment, and prognosis assessment. However, structured clinical data typically exhibit high-dimensional, nonlinear feature interactions; stage-specific dominant features; and threshold-based discontinuities. These characteristics make it challenging for a single model to achieve both global feature modeling capability and local discriminative power, thereby limiting further improvements in prediction accuracy. To address this limitation, we propose a novel deep ensemble learning framework, ETGB-SEF (Entmax-TabNet Gradient Boosting Stacked Ensemble Framework), for multiclass disease staging. First, at the base model level, Entmax-1.5 replaces Sparsemax in TabNet, thereby enabling an adjustable sparse feature selection mechanism that enhances the ability to model weakly correlated clinical features while preserving interpretability. Second, at the model-fusion level, a stacked ensemble architecture in the probability space is developed. This architecture integrates the modified TabNet with Gradient Boosting Decision Trees (GBDT) in a complementary way, enabling the former to capture global nonlinear semantic dependencies while the latter captures threshold-based discriminative boundaries among clinical features. Extensive experiments on real-world datasets demonstrate that the proposed method consistently outperforms existing state-of-the-art approaches.
Yang et al. (Fri,) studied this question.