Disentangled and reassociated deep representation for dynamic survival analysis with competing risks

Survival analysis has been extensively utilized to analyze when the event of interest occurs. However, most of present studies merely focus on single risk and static data, while incapable of handling the scenario where competing risks and longitudinal observations are involved, which is prevalent in clinical practice, especially in the ICU. Although some impressive progress has been made in recent years, they generally utilize a single encoder to learn patient representations and input identical representations into each cause-specific subnetwork to learn the survival distribution of competing risks, thereby neglecting the specificity and association of each risk factor. In this study, we propose a novel model, namely competing risks disentangled and reassociated deep representation for dynamic survival analysis. On one hand, we propose risks-disentangled autoencoders to learn specific representations for each risk factor with contrastive learning. On the other hand, a risks-reassociated representation fusion module is proposed to explicitly learn the association relationships among competing risk representations with attention mechanism. Through extensive experiments on two popular clinical datasets, i.e., MIMIC-III and eICU, we demonstrate that our proposed model achieves advanced survival prediction performance. Visualization and interpretability analysis experiments are also provided to indicate the superior performance of our model.