A Method to Improve the Reliability of Saliency Scores Applied to Graph Neural Network Models of ICDs in Patient Populations

EasyChair Preprint 7382

Abstract

Graph Neural Networks (GNN), a novel method to recognize features in heterogeneous information structures, have been recently used to model patients with similar diagnoses, extract relevant features and in this way predict for instance medical procedures and therapies. For applications in a medical field is relevant to leverage the interpretability of GNNs and evaluate which model inputs are involved in the computation of the model outputs, which is a useful information to analyze correlations between diagnose and therapy from large datasets. We applied here a method to sample the saliency scores computed with three different methods, gradient, integrated gradients, and DeepLIFT. The final sample of scores informs the customers if they are reliable if and only if all of them are convergent. This method will be relevant to inform customers which is the degree of confidence and interpretability of the computed predictions obtained with GNNs models.

Keyphrases: Graph Neural Networks, ICDs and TKs correlations, Medical processes, Saliency Methods

@booklet{EasyChair:7382,
  author    = {Juan G. Diaz Ochoa and Faizan E Mustafa},
  title     = {A Method to Improve the Reliability of Saliency Scores Applied to Graph Neural Network Models of ICDs in Patient Populations},
  howpublished = {EasyChair Preprint 7382},
  year      = {EasyChair, 2022}}