Two-step interpretable modeling of Intensive Care Acquired Infections

arXiv:2301.11146v2 Announce Type: replace-cross
Abstract: We present a novel methodology for integrating high resolution longitudinal data with the dynamic prediction capabilities of survival models. The aim is two-fold: to improve the predictive power while maintaining interpretability of the models. To go beyond the black box paradigm of artificial neural networks, we propose a parsimonious and robust semi-parametric approach (i.e., a landmarking competing risks model) that combines routinely collected low-resolution data with predictive features extracted from a convolutional neural network, that …

abstract acquired aim artificial artificial neural networks arxiv beyond black box box capabilities cs.ne data dynamic interpretability methodology modeling networks neural networks novel paradigm power prediction predictive stat.ap stat.ml survival type