GRACE: GRaph-based Addiction Care prEdiction
This work addresses a critical clinical decision-making problem for addiction care providers, but it is incremental as it focuses on improving prediction accuracy through handling class imbalance in a specific domain.
The paper tackled the problem of predicting the appropriate locus of care for addiction patients, which suffers from severe class imbalances in datasets, and proposed a graph neural network framework (GRACE) that improved the F1 score of the minority class by 11-35% over competitive baselines on real-world data.
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. Further, we perform extensive feature engineering and propose a new approach of obtaining an unbiased meta-graph to train a GNN to overcome the class imbalance problem. Experimental results in real-world data show an improvement of 11-35% in terms of the F1 score of the minority class over competitive baselines. The codes and note embeddings are available at https://anonymous.4open.science/r/GRACE-F8E1/.