Two-step interpretable modeling of Intensive Care Acquired Infections

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lancia, Giacomo, Varkila, Meri, Cremer, Olaf, Spitoni, Cristian
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913255410106368
author Lancia, Giacomo
Varkila, Meri
Cremer, Olaf
Spitoni, Cristian
author_facet Lancia, Giacomo
Varkila, Meri
Cremer, Olaf
Spitoni, Cristian
contents 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 was trained on high resolution time-dependent information. We then use saliency maps to analyze and explain the extra predictive power of this model. To illustrate our methodology, we focus on healthcare-associated infections in patients admitted to an intensive care unit.
format Preprint
id arxiv_https___arxiv_org_abs_2301_11146
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Two-step interpretable modeling of Intensive Care Acquired Infections
Lancia, Giacomo
Varkila, Meri
Cremer, Olaf
Spitoni, Cristian
Applications
Neural and Evolutionary Computing
Machine Learning
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 was trained on high resolution time-dependent information. We then use saliency maps to analyze and explain the extra predictive power of this model. To illustrate our methodology, we focus on healthcare-associated infections in patients admitted to an intensive care unit.
title Two-step interpretable modeling of Intensive Care Acquired Infections
topic Applications
Neural and Evolutionary Computing
Machine Learning
url https://arxiv.org/abs/2301.11146