Multi Layered-Parallel Graph Convolutional Network (ML-PGCN) for Disease Prediction

TL;DR

This paper introduces ML-PGCN, a novel graph convolutional network with a weighting layer that enhances disease prediction from electronic health records, outperforming existing methods in accuracy and ROC metrics.

Contribution

The paper proposes a new multi-layered parallel graph convolutional network with a weighting layer for improved disease prediction from structural health data.

Findings

Outperforms state-of-the-art methods in accuracy and ROC AUC on ABIDE and Chest X-ray datasets.

Model is lightweight, fast, and easily trainable.

Achieves 5.31% and 8.15% improvements in accuracy, and 4.96% and 10.36% improvements in ROC AUC.

Abstract

Structural data from Electronic Health Records as complementary information to imaging data for disease prediction. We incorporate novel weighting layer into the Graph Convolutional Networks, which weights every element of structural data by exploring its relation to the underlying disease. We demonstrate the superiority of our developed technique in terms of computational speed and obtained encouraging results where our method outperforms the state-of-the-art methods when applied to two publicly available datasets ABIDE and Chest X-ray in terms of relative performance for the accuracy of prediction by 5.31 % and 8.15 % and for the area under the ROC curve by 4.96 % and 10.36 % respectively. Additionally, the model is lightweight, fast and easily trainable.