GRACE: Graph Neural Networks for Locus-of-Care Prediction under Extreme Class Imbalance

TL;DR

This paper introduces GRACE, a graph neural network framework designed to predict the appropriate locus of care for addiction patients, effectively addressing severe class imbalance issues in clinical datasets.

Contribution

The paper presents a novel GNN-based approach with an unbiased meta-graph to improve locus of care prediction under class imbalance conditions.

Findings

11-35% improvement in F1 score for minority class

Joint finetuning boosts performance by 15.8%

Effective handling of class imbalance in real-world data

Abstract

Determining the appropriate locus of care for addiction patients is one of the most critical clinical decisions that affects patient treatment outcomes and effective use of resources. With a lack of sufficient specialized treatment resources, such as inpatient beds or staff, there is an unmet need to develop an automated framework for the same. Current decision-making approaches suffer from severe class imbalances in addiction datasets. To address this limitation, we propose a novel graph neural network (GRACE) framework that formalizes locus of care prediction as a structured learning problem. In addition, we propose a new approach of obtaining an unbiased meta-graph to train a GNN to overcome the class imbalance problem. Experimental results with real-world data show an improvement of 11-35% in terms of the F1 score of the minority class over competitive baselines. Further, if we jointly finetune the base embedding fed into GRACE as input together with the rest of the GNN component of GRACE, there is a remarkable boost of 15.8% in performance.