Two-step interpretable modeling of Intensive Care Acquired Infections

Although Artificial Neural Networks (ANNs) are very accurate predicting tools if compared to more conventional survival models (Topol, 2019; Zeng et al., 2022; Ivanov et al., 2022), they are often seen as black boxes. ANN models are indeed very difficult to interpret and it is challenging to identify which predictors are the most relevant (May et al., 2011). In contrast, semi-parametric hazard based survival models (Andersen et al. (1993)) are examples of interpretable models, whose hazards can measure (directly or indirectly) the effect of each covariate on the outcome of interest. In order to properly model the temporal evolution of the survival process, including longitudinal information (e.g., biomarkers, health status, clinical measurements) as time-dependent covariates is often informative. These covariates are usually internal and they require extra modeling to predict survival functions accurately (Cortese and Andersen, 2010).